Publications
Selected publications
- Jointly learning word embeddings using a corpus and a knowledge base (Journal article - 2018)
- Using k-Way Co-Occurrences for Learning Word Embeddings (Conference Paper - 2018)
- A Cross-Lingual Similarity Measure for Detecting Biomedical Term Translations (Journal article - 2015)
- Gender-preserving Debiasing for Pre-trained Word Embeddings (Conference Paper - 2019)
- Think Globally, Embed Locally - Locally Linear Meta-embedding of Words. (Conference Paper - 2018)
2024
Community knowledge graph abstraction for enhanced link prediction: A study on pubmed knowledge graph.
Zhao, Y., Bollegala, D., Hirose, S., Jin, Y., & Kozu, T. (2024). Community knowledge graph abstraction for enhanced link prediction: A study on pubmed knowledge graph.. Journal of biomedical informatics, 104725. doi:10.1016/j.jbi.2024.104725
A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection.
Aida, T., & Bollegala, D. (2024). A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection.. In L. -W. Ku, A. Martins, & V. Srikumar (Eds.), ACL (Findings) (pp. 7570-7584). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2024.findings-acl/
A qualitative exploration of barriers to efficient and effective structured medication reviews in primary care: Findings from the DynAIRx study.
Abuzour, A. S., Wilson, S. A., Woodall, A. A., Mair, F. S., Clegg, A., Shantsila, E., . . . Walker, L. E. (2024). A qualitative exploration of barriers to efficient and effective structured medication reviews in primary care: Findings from the DynAIRx study.. PloS one, 19(8), e0299770. doi:10.1371/journal.pone.0299770
Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings.
Zhang, G., Zhou, Y., & Bollegala, D. (2024). Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings.. In N. Calzolari, M. -Y. Kan, V. Hoste, A. Lenci, S. Sakti, & N. Xue (Eds.), LREC/COLING (pp. 6530-6543). ELRA and ICCL. Retrieved from https://aclanthology.org/volumes/2024.lrec-main/
In-Contextual Gender Bias Suppression for Large Language Models.
Oba, D., Kaneko, M., & Bollegala, D. (2024). In-Contextual Gender Bias Suppression for Large Language Models.. In Y. Graham, & M. Purver (Eds.), EACL (Findings) (pp. 1722-1742). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2024.findings-eacl/
Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings
Zhang, G., Zhou, Y., & Bollegala, D. (2024). Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings. In 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings (pp. 6530-6543).
Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER
Abaho, M., Bollegala, D., Leeming, G., Joyce, D., & Buchan, I. (2024). Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (pp. 5013-5029). Association for Computational Linguistics. doi:10.18653/v1/2024.naacl-long.280
Multimodal zero-shot learning for tactile texture recognition.
Cao, G., Jiang, J., Bollegala, D., Li, M., & Luo, S. (2024). Multimodal zero-shot learning for tactile texture recognition.. Robotics Auton. Syst., 176, 104688.
2023
Report on the 1st Symposium on NLP for Social: Good (NSG 2023)
Sen, P., Saha, T., & Bollegala, D. (2023). Report on the 1st Symposium on NLP for Social: Good (NSG 2023). ACM SIGIR Forum, 57(2), 1-9. doi:10.1145/3642979.3642989
How might dynamic artificial intelligence (DynAIRx) be used to support prescribing to ensure efficient medication reviews?
Abuzour, A., Wilson, S., Woodall, A., Mair, F., Bollegala, D., Cant, H., . . . Walker, L. (2023). How might dynamic artificial intelligence (DynAIRx) be used to support prescribing to ensure efficient medication reviews?. American Academy of Family Physicians. doi:10.1370/afm.22.s1.4823
Learning to Predict Concept Ordering for Common Sense Generation
Zhang, T., Bollegala, D., & Peng, B. (2023). Learning to Predict Concept Ordering for Common Sense Generation. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 10-19). Association for Computational Linguistics. doi:10.18653/v1/2023.ijcnlp-short.2
The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated
Kaneko, M., Bollegala, D., & Okazaki, N. (2023). The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 29-36). Association for Computational Linguistics. doi:10.18653/v1/2023.ijcnlp-short.4
Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders
Cao, G., Jiang, J., Bollegala, D., & Luo, S. (2023). Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders. In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE. doi:10.1109/iros55552.2023.10341788
Vis2Hap: Vision-based Haptic Rendering by Cross-modal Generation
Cao, G., Jiang, J., Mao, N., Bollegala, D., Li, M., & Luo, S. (2023). Vis2Hap: Vision-based Haptic Rendering by Cross-modal Generation. In 2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023) (pp. 12443-12449). doi:10.1109/ICRA48891.2023.10160373
A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings
Bollegala, D., Otake, S., Machide, T., & Kawarabayashi, K. -I. (2023). A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings) (pp. 65-79). Association for Computational Linguistics. doi:10.18653/v1/2023.findings-ijcnlp.7
A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings.
Bollegala, D., Otake, S., Machide, T., & Kawarabayashi, K. -I. (2023). A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings.. In J. C. Park, Y. Arase, B. Hu, W. Lu, D. Wijaya, A. Purwarianti, & A. A. Krisnadhi (Eds.), IJCNLP (Findings) (pp. 65-79). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2023.findings-ijcnlp/
A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models
Zhou, Y., Camacho-Collados, J., & Bollegala, D. (2023). A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 11082-11100). Association for Computational Linguistics. doi:10.18653/v1/2023.emnlp-main.683
A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models.
Zhou, Y., Camacho-Collados, J., & Bollegala, D. (2023). A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models.. In H. Bouamor, J. Pino, & K. Bali (Eds.), EMNLP (pp. 11082-11100). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2023.emnlp-main/
A Word Sense Distribution-based approach for Semantic Change Prediction
Tang, X., Zhou, Y., Aida, T., Sen, P., & Bollegala, D. (2023). A Word Sense Distribution-based approach for Semantic Change Prediction. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 3575-3590). Association for Computational Linguistics. doi:10.18653/v1/2023.findings-emnlp.231
Can Word Sense Distribution Detect Semantic Changes of Words?
Tang, X., Zhou, Y., Aida, T., Sen, P., & Bollegala, D. (2023). Can Word Sense Distribution Detect Semantic Changes of Words?. In Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 3575-3590).
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples
Kaneko, M., Bollegala, D., & Okazaki, N. (2023). Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 2849-2855).
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples
Kaneko, M., Bollegala, D., & Okazaki, N. (2023). Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (pp. 2857-2863). Association for Computational Linguistics. doi:10.18653/v1/2023.eacl-main.209
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples.
Kaneko, M., Bollegala, D., & Okazaki, N. (2023). Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples.. In EACL (pp. 2849-2855).
Evaluating the Robustness of Discrete Prompts
Ishibashi, Y., Bollegala, D., Sudoh, K., & Nakamura, S. (2023). Evaluating the Robustness of Discrete Prompts. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 2365-2376).
Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders.
Cao, G., Jiang, J., Bollegala, D., & Luo, S. (2023). Learn from Incomplete Tactile Data: Tactile Representation Learning with Masked Autoencoders.. In IROS (pp. 10800-10805).
Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation
Tang, X., Zhou, Y., & Bollegala, D. (2023). Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 9352-9369). Association for Computational Linguistics. doi:10.18653/v1/2023.acl-long.520
Learning to Predict Concept Ordering for Common Sense Generation.
Zhang, T., Bollegala, D., & Peng, B. (2023). Learning to Predict Concept Ordering for Common Sense Generation.. In J. C. Park, Y. Arase, B. Hu, W. Lu, D. Wijaya, A. Purwarianti, & A. A. Krisnadhi (Eds.), IJCNLP (2) (pp. 10-19). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2023.ijcnlp-short/
Solving Cosine Similarity Underestimation between High Frequency Words by \ell₂ Norm Discounting.
Wannasuphoprasit, S., Zhou, Y., & Bollegala, D. (2023). Solving Cosine Similarity Underestimation between High Frequency Words by \ell₂ Norm Discounting.. In ACL (Findings) (pp. 8644-8652).
Solving Cosine Similarity Underestimation between High Frequency Words by ℓ2 Norm Discounting Norm Discounting
Wannasuphoprasit, S., Zhou, Y., & Bollegala, D. (2023). Solving Cosine Similarity Underestimation between High Frequency Words by ℓ2 Norm Discounting Norm Discounting. In Findings of the Association for Computational Linguistics: ACL 2023 (pp. 8644-8652). Association for Computational Linguistics. doi:10.18653/v1/2023.findings-acl.550
Swap and Predict - Predicting the Semantic Changes in Words across Corpora by Context Swapping.
Aida, T., & Bollegala, D. (2023). Swap and Predict - Predicting the Semantic Changes in Words across Corpora by Context Swapping.. In H. Bouamor, J. Pino, & K. Bali (Eds.), EMNLP (Findings) (pp. 7753-7772). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2023.findings-emnlp/
The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated.
Kaneko, M., Bollegala, D., & Okazaki, N. (2023). The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated.. In J. C. Park, Y. Arase, B. Hu, W. Lu, D. Wijaya, A. Purwarianti, & A. A. Krisnadhi (Eds.), IJCNLP (2) (pp. 29-36). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2023.ijcnlp-short/
Together We Make Sense-Learning Meta-Sense Embeddings.
Luo, H., Zhou, Y., & Bollegala, D. (2023). Together We Make Sense-Learning Meta-Sense Embeddings.. In ACL (Findings) (pp. 2638-2651).
Together We Make Sense–Learning Meta-Sense Embeddings
Luo, H., Zhou, Y., & Bollegala, D. (2023). Together We Make Sense–Learning Meta-Sense Embeddings. In Findings of the Association for Computational Linguistics: ACL 2023 (pp. 2638-2651). Association for Computational Linguistics. doi:10.18653/v1/2023.findings-acl.165
Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddings.
Aida, T., & Bollegala, D. (2023). Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddings.. In ACL (Findings) (pp. 6868-6882).
Vis2Hap: Vision-based Haptic Rendering by Cross-modal Generation.
Cao, G., Jiang, J., Mao, N., Bollegala, D., Li, M., & Luo, S. (2023). Vis2Hap: Vision-based Haptic Rendering by Cross-modal Generation.. In ICRA (pp. 12443-12449).
2022
Random projections and kernelised leave one cluster out cross validation: universal baselines and evaluation tools for supervised machine learning of material properties
Durdy, S., Gaultois, M. W., Gusev, V. V., Bollegala, D., & Rosseinsky, M. J. (n.d.). Random projections and kernelised leave one cluster out cross validation: universal baselines and evaluation tools for supervised machine learning of material properties. Digital Discovery, 1(6), 763-778. doi:10.1039/d2dd00039c
Improvement of intervention information detection for automated clinical literature screening during systematic review
Tsubota, T., Bollegala, D., Zhao, Y., Jin, Y., & Kozu, T. (2022). Improvement of intervention information detection for automated clinical literature screening during systematic review. JOURNAL OF BIOMEDICAL INFORMATICS, 134. doi:10.1016/j.jbi.2022.104185
Unmasking the Mask - Evaluating Social Biases in Masked Language Models
Kaneko, M., & Bollegala, D. (2022). Unmasking the Mask - Evaluating Social Biases in Masked Language Models. In THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE (pp. 11954-11962). Retrieved from https://www.webofscience.com/
Position-based Prompting for Health Outcome Generation
Abaho, M., Bollegala, D., Williamson, P., & Dodd, S. (2022). Position-based Prompting for Health Outcome Generation. Retrieved from http://arxiv.org/abs/2204.03489v1
Assessment of contextualised representations in detecting outcome phrases in clinical trials
<i>Learning to Borrow</i> - Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion
Hakami, H., Hakami, M., Mandya, A., & Bollegala, D. (2022). <i>Learning to Borrow</i> - Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion. In NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (pp. 2887-2898). Retrieved from https://www.webofscience.com/
<i>Sense Embeddings are also Biased</i> - Evaluating Social Biases in Static and Contextualised Sense Embeddings
Zhou, Y., Kaneko, M., & Bollegala, D. (2022). <i>Sense Embeddings are also Biased</i> - Evaluating Social Biases in Static and Contextualised Sense Embeddings. In PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS) (pp. 1924-1935). Retrieved from https://www.webofscience.com/
A Survey on Word Meta-Embedding Learning
Bollegala, D., & O' Neill, J. (2022). A Survey on Word Meta-Embedding Learning. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (pp. 5402-5409). International Joint Conferences on Artificial Intelligence Organization. doi:10.24963/ijcai.2022/758
Debiasing Isn't Enough! - on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks.
Kaneko, M., Bollegala, D., & Okazaki, N. (2022). Debiasing Isn't Enough! - on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks.. In N. Calzolari, C. -R. Huang, H. Kim, J. Pustejovsky, L. Wanner, K. -S. Choi, . . . S. -H. Na (Eds.), COLING (pp. 1299-1310). International Committee on Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2022.coling-1/
Debiasing isn’t enough! – On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks
Kaneko, M., Bollegala, D., & Okazaki, N. (2022). Debiasing isn’t enough! – On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks. In Proceedings - International Conference on Computational Linguistics, COLING Vol. 29 (pp. 1299-1310).
Gender Bias in Masked Language Models for Multiple Languages
Kaneko, M., Imankulova, A., Bollegala, D., & Okazaki, N. (2022). Gender Bias in Masked Language Models for Multiple Languages. In NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (pp. 2740-2750). Retrieved from https://www.webofscience.com/
Gender Bias in Masked Language Models for Multiple Languages.
Kaneko, M., Imankulova, A., Bollegala, D., & Okazaki, N. (2022). Gender Bias in Masked Language Models for Multiple Languages.. In M. Carpuat, M. -C. D. Marneffe, & I. V. M. Ruíz (Eds.), NAACL-HLT (pp. 2740-2750). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2022.naacl-main/
Gender Bias in Meta-Embeddings
Kaneko, M., Bollegala, D., & Okazaki, N. (2022). Gender Bias in Meta-Embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2022 (pp. 3118-3133). Association for Computational Linguistics. doi:10.18653/v1/2022.findings-emnlp.227
Gender Bias in Meta-Embeddings.
Kaneko, M., Bollegala, D., & Okazaki, N. (2022). Gender Bias in Meta-Embeddings.. In EMNLP (Findings) (pp. 3118-3133).
Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings
Bollegala, D. (2022). Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (pp. 4058-4064). International Joint Conferences on Artificial Intelligence Organization. doi:10.24963/ijcai.2022/563
Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings.
Bollegala, D. (2022). Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings.. In L. D. Raedt (Ed.), IJCAI (pp. 4058-4064). ijcai.org. Retrieved from https://www.ijcai.org/proceedings/2022/
Learning to Borrow- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion.
Hakami, H., Hakami, M., Mandya, A., & Bollegala, D. (2022). Learning to Borrow- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion.. In M. Carpuat, M. -C. D. Marneffe, & I. V. M. Ruíz (Eds.), NAACL-HLT (pp. 2887-2898). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2022.naacl-main/
On the Curious Case of l2 norm of Sense Embeddings
Zhou, Y., & Bollegala, D. (2022). On the Curious Case of l2 norm of Sense Embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2022 (pp. 2593-2602). Association for Computational Linguistics. doi:10.18653/v1/2022.findings-emnlp.190
On the Curious Case of l2 norm of Sense Embeddings.
Zhou, Y., & Bollegala, D. (2022). On the Curious Case of l2 norm of Sense Embeddings.. In EMNLP (Findings) (pp. 2593-2602).
Position-based Prompting for Health Outcome Generation
Abaho, M., Bollegala, D., Williamson, P. R., & Dodd, S. (2022). Position-based Prompting for Health Outcome Generation. In PROCEEDINGS OF THE 21ST WORKSHOP ON BIOMEDICAL LANGUAGE PROCESSING (BIONLP 2022) (pp. 26-36). Retrieved from https://www.webofscience.com/
Position-based Prompting for Health Outcome Generation.
Abaho, M., Bollegala, D., Williamson, P., & Dodd, S. (2022). Position-based Prompting for Health Outcome Generation.. In D. Demner-Fushman, K. B. Cohen, S. Ananiadou, & J. Tsujii (Eds.), BioNLP@ACL (pp. 26-36). Association for Computational Linguistics. Retrieved from https://aclanthology.org/volumes/2022.bionlp-1/
Query Obfuscation by Semantic Decomposition
Bollegala, D., Machide, T., & Kawarabayashi, K. -I. (2022). Query Obfuscation by Semantic Decomposition. In LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (pp. 6200-6211). Retrieved from https://www.webofscience.com/
The DynAIRx Project Protocol: Artificial Intelligence for dynamic prescribing optimisation and care integration in multimorbidity.
Walker, L. E., Abuzour, A. S., Bollegala, D., Clegg, A., Gabbay, M., Griffiths, A., . . . Buchan, I. (2022). The DynAIRx Project Protocol: Artificial Intelligence for dynamic prescribing optimisation and care integration in multimorbidity.. Journal of multimorbidity and comorbidity, 12, 26335565221145493. doi:10.1177/26335565221145493
Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models
Takahashi, K., & Bollegala, D. (2022). Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models. In LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (pp. 7155-7163). Retrieved from https://www.webofscience.com/
Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models.
Takahashi, K., & Bollegala, D. (2022). Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models.. In N. Calzolari, F. Béchet, P. Blache, K. Choukri, C. Cieri, T. Declerck, . . . S. Piperidis (Eds.), LREC (pp. 7155-7163). European Language Resources Association. Retrieved from https://aclanthology.org/volumes/2022.lrec-1/
Zero-shot Cross-Lingual Counterfactual Detection via Automatic Extraction and Prediction of Clue Phrases
Ushio, A., & Bollegala, D. (2022). Zero-shot Cross-Lingual Counterfactual Detection via Automatic Extraction and Prediction of Clue Phrases. In Proceedings of the The 2nd Workshop on Multi-lingual Representation Learning (MRL) (pp. 28-37). Association for Computational Linguistics. doi:10.18653/v1/2022.mrl-1.3
2021
Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
Alsuhaibani, M., & Bollegala, D. (2021). Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021. doi:10.1155/2021/9761163
Detect and Classify - Joint Span Detection and Classification for Health Outcomes
Abaho, M., Bollegala, D., Williamson, P., & Dodd, S. (2021). Detect and Classify - Joint Span Detection and Classification for Health Outcomes. In 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021) (pp. 8709-8721). Retrieved from https://www.webofscience.com/
<i>I Wish I Would Have Loved This One, But I Didn't</i> - A Multilingual Dataset for Counterfactual Detection in Product Reviews
O'Neill, J., Rozenshtein, P., Kiryo, R., Kubota, M., & Bollegala, D. (2021). <i>I Wish I Would Have Loved This One, But I Didn't</i> - A Multilingual Dataset for Counterfactual Detection in Product Reviews. In 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021) (pp. 7092-7108). Retrieved from https://www.webofscience.com/
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy
Zhou, Y., & Bollegala, D. (2021). Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy. Retrieved from http://arxiv.org/abs/2110.02204v2
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance.
Isonuma, M., Mori, J., Bollegala, D., & Sakata, I. (2021). Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance.. Trans. Assoc. Comput. Linguistics, 9, 945-961.
Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora.
Fain, M., Twomey, N., & Bollegala, D. (2021). Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora.. In F. Diaz, C. Shah, T. Suel, P. Castells, R. Jones, & T. Sakai (Eds.), SIGIR (pp. 2106-2110). ACM. Retrieved from https://doi.org/10.1145/3404835
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora
Debiasing Pre-trained Contextualised Embeddings
Kaneko, M., & Bollegala, D. (2021). Debiasing Pre-trained Contextualised Embeddings. In 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021) (pp. 1256-1266). Retrieved from https://www.webofscience.com/
Dictionary-based Debiasing of Pre-trained Word Embeddings
Kaneko, M., & Bollegala, D. (2021). Dictionary-based Debiasing of Pre-trained Word Embeddings. In 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021) (pp. 212-223). Retrieved from https://www.webofscience.com/
RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding
Bollegala, D., Hakami, H., Yoshida, Y., & Kawarabayashi, K. -I. (2021). RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding. In 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021) (pp. 1551-1565). Retrieved from https://www.webofscience.com/
Unmasking the Mask -- Evaluating Social Biases in Masked Language Models
I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews
Discrimination of human-written and human and machine written sentences using text consistency
Harada, A., Bollegala, D., & Chandrasiri, N. P. (2021). Discrimination of human-written and human and machine written sentences using text consistency. In 2021 IEEE INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION, AND INTELLIGENT SYSTEMS (ICCCIS) (pp. 41-47). doi:10.1109/ICCCIS51004.2021.9397237
Semantically-Conditioned Negative Samples for Efficient Contrastive Learning
RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding
Debiasing Pre-trained Contextualised Embeddings
Dictionary-based Debiasing of Pre-trained Word Embeddings
$k$-Neighbor Based Curriculum Sampling for Sequence Prediction
Document Ranking for Curated Document Databases Using BERT and Knowledge Graph Embeddings: Introducing GRAB-Rank
Muhammad, I., Bollegala, D., Coenen, F., Gamble, C., Kearney, A., & Williamson, P. (2021). Document Ranking for Curated Document Databases Using BERT and Knowledge Graph Embeddings: Introducing GRAB-Rank. In BIG DATA ANALYTICS AND KNOWLEDGE DISCOVERY (DAWAK 2021) Vol. 12925 (pp. 116-127). doi:10.1007/978-3-030-86534-4_10
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy.
Bollegala, D., & Zhou, Y. (2021). Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy.. In K. Hu, J. -B. Kim, C. Zong, & E. Chersoni (Eds.), PACLIC (pp. 493-502). Association for Computational Lingustics. Retrieved from https://aclanthology.org/volumes/2021.paclic-1/
2020
Multi-Source Attention for Unsupervised Domain Adaptation
Cui, X., & Bollegala, D. (2020). Multi-Source Attention for Unsupervised Domain Adaptation. In 1ST CONFERENCE OF THE ASIA-PACIFIC CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 10TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (AACL-IJCNLP 2020) (pp. 873-883). Retrieved from https://www.webofscience.com/
Explanation in AI and law: Past, present and future
Atkinson, K., Bench-Capon, T., & Bollegala, D. (2020). Explanation in AI and law: Past, present and future. ARTIFICIAL INTELLIGENCE, 289. doi:10.1016/j.artint.2020.103387
Autoencoding Improves Pre-trained Word Embeddings
DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach
Khemchandani, Y., O'Hagan, S., Samanta, S., Swainston, N., Roberts, T. J., Bollegala, D., & Kell, D. B. (2020). DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach. Journal of Cheminformatics, 12(1). doi:10.1186/s13321-020-00454-3
Meta-Embedding as Auxiliary Task Regularization.
O'Neill, J., & Bollegala, D. (2020). Meta-Embedding as Auxiliary Task Regularization.. In G. D. Giacomo, A. Catalá, B. Dilkina, M. Milano, S. Barro, A. Bugarín, & J. Lang (Eds.), ECAI Vol. 325 (pp. 2124-2131). IOS Press. Retrieved from https://doi.org/10.3233/FAIA325
Spatio-temporal Attention Model for Tactile Texture Recognition
Spatio-temporal Attention Model for Tactile Texture Recognition
Cao, G., Zhou, Y., Bollegala, D., & Luo, S. (2020). Spatio-temporal Attention Model for Tactile Texture Recognition. In 2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (pp. 9896-9902). doi:10.1109/IROS45743.2020.9341333
DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach
Khemchandani, Y., O'Hagan, S., Samanta, S., Swainston, N., Roberts, T., Bollegala, D., & Kell, D. (2020). DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach. doi:10.21203/rs.3.rs-32446/v2
A Pilot Study on Argument Simplification in Stance-Based Opinions
Rajendran, P., Bollegala, D., & Parsons, S. (2020). A Pilot Study on Argument Simplification in Stance-Based Opinions. In International Conference of the Pacific Association for Computational Linguistics (pp. 218-230). Hanoi, Vietnam: Springer Singapore. doi:10.1007/978-981-15-6168-9_19
Context-Guided Self-supervised Relation Embeddings
Hakami, H., & Bollegala, D. (2020). Context-Guided Self-supervised Relation Embeddings. In International Conference of the Pacific Association for Computational Linguistics (pp. 67-78). Hanoi, Vietnam: Springer Singapore. doi:10.1007/978-981-15-6168-9_6
Evaluating Co-reference Chains based Conversation History in Conversational Question Answering
Mandya, A. A., Bollegala, D., & Coenen, F. P. (2020). Evaluating Co-reference Chains based Conversation History in Conversational Question Answering. In L. -M. Nguyen, X. -H. Phan, K. Hasida, & S. Tojo (Eds.), Computational Linguistics (pp. 283-292). Singapore: Springer. doi:10.1007/978-981-15-6168-9_24
Learning to Compose Relational Embeddings in Knowledge Graphs
Chen, W., Hakami, H., & Bollegala, D. (2020). Learning to Compose Relational Embeddings in Knowledge Graphs. In International Conference of the Pacific Association for Computational Linguistics (pp. 56-66). Hanoi, Vietnam: Springer Singapore. doi:10.1007/978-981-15-6168-9_5
DeepGraphMol, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach
Khemchandani, Y., O'Hagan, S., Samanta, S., Swainston, N., Roberts, T., Bollegala, D., & Kell, D. (2020). DeepGraphMol, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach. doi:10.21203/rs.3.rs-32446/v1
DeepGraphMol, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach
Khemchandani, Y., O’Hagan, S., Samanta, S., Swainston, N., Roberts, T., Bollegala, D., & Kell, D. (2020). DeepGraphMol, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach. doi:10.1101/2020.05.25.114165
Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction.
Bollegala, D., Kiryo, R., Tsujino, K., & Yukawa, H. (2020). Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction.. In N. Calzolari, F. Béchet, P. Blache, K. Choukri, C. Cieri, T. Declerck, . . . S. Piperidis (Eds.), LREC (pp. 3851-3860). European Language Resources Association. Retrieved from https://aclanthology.org/volumes/2020.lrec-1/
<i>Do not let the history haunt you</i> - Mitigating Compounding Errors in Conversational Question Answering
Mandya, A., O'Neill, J., Bollegala, D., & Coenen, F. (2020). <i>Do not let the history haunt you</i> - Mitigating Compounding Errors in Conversational Question Answering. In PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020) (pp. 2017-2025). Retrieved from https://www.webofscience.com/
Do not let the history haunt you -- Mitigating Compounding Errors in Conversational Question Answering
Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
Contextualised Graph Attention for Improved Relation Extraction
Multi-source Attention for Unsupervised Domain Adaptation
Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction
Autoencoding Improves Pre-trained Word Embeddings
Kaneko, M., & Bollegala, D. (2020). Autoencoding Improves Pre-trained Word Embeddings. In Proceedings of the 28th International Conference on Computational Linguistics (pp. 1699-1713). International Committee on Computational Linguistics. doi:10.18653/v1/2020.coling-main.149
Do not let the history haunt you: Mitigating Compounding Errors in Conversational Question Answering.
Mandya, A., O'Neill, J., Bollegala, D., & Coenen, F. (2020). Do not let the history haunt you: Mitigating Compounding Errors in Conversational Question Answering.. In N. Calzolari, F. Béchet, P. Blache, K. Choukri, C. Cieri, T. Declerck, . . . S. Piperidis (Eds.), LREC (pp. 2017-2025). European Language Resources Association. Retrieved from https://aclanthology.org/volumes/2020.lrec-1/
Evaluating Co-reference Chains Based Conversation History in Conversational Question Answering
Mandya, A., Bollegala, D., & Coenen, F. (2020). Evaluating Co-reference Chains Based Conversation History in Conversational Question Answering. In Computational Linguistics (Vol. 1215, pp. 280-292). Springer Nature. doi:10.1007/978-981-15-6168-9_24
Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction
Mandya, A., Bollegala, D., & Coenen, F. (2020). Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction. In Proceedings of the 28th International Conference on Computational Linguistics (pp. 6424-6435). International Committee on Computational Linguistics. doi:10.18653/v1/2020.coling-main.565
Learning to Evaluate Neural Language Models
O’Neill, J., & Bollegala, D. (2020). Learning to Evaluate Neural Language Models. In Unknown Conference (pp. 123-133). Springer Singapore. doi:10.1007/978-981-15-6168-9_11
Maintaining Curated Document Databases Using a Learning to Rank Model: The ORRCA Experience
Muhammad, I., Bollegala, D., Coenen, F., Gamble, C., Kearney, A., & Williamson, P. (2020). Maintaining Curated Document Databases Using a Learning to Rank Model: The ORRCA Experience. In Unknown Conference (pp. 345-357). Springer International Publishing. doi:10.1007/978-3-030-63799-6_26
Spatio-temporal Attention Model for Tactile Texture Recognition.
Cao, G., Zhou, Y., Bollegala, D., & Luo, S. (2020). Spatio-temporal Attention Model for Tactile Texture Recognition.. In IROS (pp. 9896-9902). IEEE. Retrieved from https://doi.org/10.1109/IROS45743.2020
Tree-Structured Neural Topic Model
Isonuma, M., Mori, J., Bollegala, D., & Sakata, I. (2020). Tree-Structured Neural Topic Model. In 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020) (pp. 800-806). Retrieved from https://www.webofscience.com/
2019
Combining Textual and Visual Information for Typed and Handwritten Text Separation in Legal Documents
Torrisi, A., Bevan, R., Atkinson, K., Bollegala, D., & Coenen, F. (2019). Combining Textual and Visual Information for Typed and Handwritten Text Separation in Legal Documents. In LEGAL KNOWLEDGE AND INFORMATION SYSTEMS (JURIX 2019) Vol. 322 (pp. 223-228). doi:10.3233/FAIA190329
Dividing and Conquering Cross-Modal Recipe Retrieval: from Nearest Neighbours Baselines to SoTA
Self-Adaptation for Unsupervised Domain Adaptation
Cui, X., & Bollegala, D. (2019). Self-Adaptation for Unsupervised Domain Adaptation. In Proceedings - Natural Language Processing in a Deep Learning World (pp. 213-222). Incoma Ltd., Shoumen, Bulgaria. doi:10.26615/978-954-452-056-4_025
Query Obfuscation Semantic Decomposition
Transfer Reward Learning for Policy Gradient-Based Text Generation
Gender-preserving Debiasing for Pre-trained Word Embeddings
Masahiro, K., & Bollegala, D. (2019). Gender-preserving Debiasing for Pre-trained Word Embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy.
Automated Bundle Pagination Using Machine Learning
Torrisi, A., Bevan, R., Atkinson, K., Bollegala, D., & Coenen, F. (2019). Automated Bundle Pagination Using Machine Learning. In Proceedings of the Seventeenth International Conference on Artificial Intelligence and Law Vol. 105 (pp. 244-248). ACM. doi:10.1145/3322640.3326726
Gender-preserving Debiasing for Pre-trained Word Embeddings
"Touching to See" and "Seeing to Feel": Robotic Cross-modal Sensory Data Generation for Visual-Tactile Perception
Lee, J. -T., Bollegala, D., & Luo, S. (2019). "Touching to See" and "Seeing to Feel": Robotic Cross-modal Sensory Data Generation for Visual-Tactile Perception. In 2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (pp. 4276-4282). Retrieved from https://www.webofscience.com/
"Touching to See" and "Seeing to Feel": Robotic Cross-modal SensoryData Generation for Visual-Tactile Perception
Error-Correcting Neural Sequence Prediction
"Touching to See" and "Seeing to Feel": Robotic Cross-modal Sensory Data Generation for Visual-Tactile Perception.
Lee, J. -T., Bollegala, D., & Luo, S. (2019). "Touching to See" and "Seeing to Feel": Robotic Cross-modal Sensory Data Generation for Visual-Tactile Perception.. In ICRA (pp. 4276-4282). IEEE. Retrieved from https://ieeexplore.ieee.org/xpl/conhome/8780387/proceeding
A Dataset for Inter-Sentence Relation Extraction using Distant Supervision
Mandya, A., Bollegala, D., Coenen, F., & Atkinson, K. (2018). A Dataset for Inter-Sentence Relation Extraction using Distant Supervision. In PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018) (pp. 1559-1565). Retrieved from https://www.webofscience.com/
Behavioural Biometric Continuous User Authentication Using Multivariate Keystroke Streams in the Spectral Domain
Alshehri, A., Coenen, F., & Bollegala, D. (2019). Behavioural Biometric Continuous User Authentication Using Multivariate Keystroke Streams in the Spectral Domain. In Communications in Computer and Information Science (pp. 43-66). Springer International Publishing. doi:10.1007/978-3-030-15640-4_3
Combining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction.
Mandya, A., Bollegala, D., Coenen, F., & Atkinson, K. (2019). Combining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction.. In AKBC. Retrieved from https://openreview.net/group?id=AKBC.ws/2019/Conference
Correcting crowdsourced annotations to improve detection of outcome types in evidence based medicine
Abaho, M., Bollegala, D., Williamson, P., & Dodd, S. (2019). Correcting crowdsourced annotations to improve detection of outcome types in evidence based medicine. In CEUR Workshop Proceedings Vol. 2429 (pp. 1-5).
Extracting supporting evidence from medical negligence claim texts
Bevany, R., Torrisiy, A., Bollegalay, D., Coeneny, F., & Atkinsony, K. (2019). Extracting supporting evidence from medical negligence claim texts. In CEUR Workshop Proceedings Vol. 2429 (pp. 50-54).
Gender-preserving Debiasing for Pre-trained Word Embeddings
Kaneko, M., & Bollegala, D. (2019). Gender-preserving Debiasing for Pre-trained Word Embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 1641-1650). Association for Computational Linguistics. doi:10.18653/v1/p19-1160
Joint Learning of Hierarchical Word Embeddings from a Corpus and a Taxonomy.
Alsuhaibani, M., Maehara, T., & Bollegala, D. (2019). Joint Learning of Hierarchical Word Embeddings from a Corpus and a Taxonomy.. In AKBC. Retrieved from https://openreview.net/group?id=AKBC.ws/2019/Conference
Joint Learning of Sense and Word Embeddings
Alsuhaibani, M., & Bollegala, D. (2018). Joint Learning of Sense and Word Embeddings. In PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018) (pp. 223-229). Retrieved from https://www.webofscience.com/
Learning Relation Representations from Word Representations.
Hakami, H., & Bollegala, D. (2019). Learning Relation Representations from Word Representations.. In AKBC. Retrieved from https://openreview.net/group?id=AKBC.ws/2019/Conference
Sentiment-Stance-Specificity (SSS) Dataset: Identifying Support-based Entailment among Opinions
Rajendran, P., Bollegala, D., & Parsons, S. (2018). Sentiment-Stance-Specificity (SSS) Dataset: Identifying Support-based Entailment among Opinions. In PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018) (pp. 619-626). Retrieved from https://www.webofscience.com/
Sub-Sequence-Based Dynamic Time Warping
Alshehri, M., Coenen, F., & Dures, K. (2019). Sub-Sequence-Based Dynamic Time Warping. In KDIR: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE DISCOVERY, KNOWLEDGE ENGINEERING AND KNOWLEDGE MANAGEMENT - VOL 1: KDIR (pp. 274-281). doi:10.5220/0008053402740281
Tick parasitism classification from noisy medical records
Neill, J. O., Bollegala, D., Radford, A. D., & Noble, P. J. (2019). Tick parasitism classification from noisy medical records. In CEUR Workshop Proceedings Vol. 2429 (pp. 30-34).
Unsupervised Evaluation of Human Translation Quality
Zhou, Y., & Bollegala, D. (2019). Unsupervised Evaluation of Human Translation Quality. In KDIR: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE DISCOVERY, KNOWLEDGE ENGINEERING AND KNOWLEDGE MANAGEMENT - VOL 1: KDIR (pp. 55-64). doi:10.5220/0008064500550064
2018
Analysing Dropout and Compounding Errors in Neural Language Models
Combining Long Short Term Memory and Convolutional Neural Network for Cross-Sentence n-ary Relation Extraction
Iterative Keystroke Continuous Authentication: A Time Series Based Approach
Alshehri, A., Coenen, F., & Bollegala, D. (2018). Iterative Keystroke Continuous Authentication: A Time Series Based Approach. KUNSTLICHE INTELLIGENZ, 32(4), 231-243. doi:10.1007/s13218-018-0526-z
Curriculum-Based Neighborhood Sampling For Sequence Prediction
Meta-Embedding as Auxiliary Task Regularization
Meta-Embedding as Auxiliary Task Regularization
O'Neill, J., & Bollegala, D. (2020). Meta-Embedding as Auxiliary Task Regularization. ECAI 2020: 24TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 325, 2124-2131. doi:10.3233/FAIA200336
Angular-Based Word Meta-Embedding Learning
(OS招待講演)Webからの関係抽出とそれを利用した関係検索
Bollegala, D. (n.d.). (OS招待講演)Webからの関係抽出とそれを利用した関係検索. Unknown Journal, 4k1os25. doi:10.11517/pjsai.jsai2012.0_4k1os25
Webからの人物の属性情報抽出
啓吾, 渡., Bollegala, D., 豊, 松., & 満, 石. (n.d.). Webからの人物の属性情報抽出. Unknown Journal, 3b22. doi:10.11517/pjsai.jsai2009.0_3b22
多項関係を活用した行為データからの興味予測
のぞみ, 則., Bollegala, D., & 満, 石. (n.d.). 多項関係を活用した行為データからの興味予測. Unknown Journal, 3e3os202. doi:10.11517/pjsai.jsai2011.0_3e3os202
ClassiNet - Predicting Missing Features for Short-Text Classification.
Bollegala, D., Atanasov, V., Maehara, T., & Kawarabayashi, K. -I. (2018). ClassiNet - Predicting Missing Features for Short-Text Classification.. ACM Transactions on Knowledge Discovery from Data, 12(5). doi:10.1145/3201578
Learning Neural Word Salience Scores
Samardzhiev, K., Gargett, A., & Bollegala, D. (2018). Learning Neural Word Salience Scores. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics (pp. 33-42). Association for Computational Linguistics. doi:10.18653/v1/s18-2004
ClassiNet -- Predicting Missing Features for Short-Text Classification
Bollegala, D., Atanasov, V., Maehara, T., & Kawarabayashi, K. -I. (2018). ClassiNet -- Predicting Missing Features for Short-Text Classification. ACM Transactions on Knowledge Discovery from Data.
Causality Patterns for Detecting Adverse Drug Reactions From Social Media: Text Mining Approach
Bollegala, D., Maskell, S., Sloane, R., Hajne, J., & Pirmohamed, M. (2018). Causality Patterns for Detecting Adverse Drug Reactions From Social Media: Text Mining Approach. JMIR PUBLIC HEALTH AND SURVEILLANCE, 4(2), 292-303. doi:10.2196/publichealth.8214
ClassiNet -- Predicting Missing Features for Short-Text Classification
Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings
Coates, J., & Bollegala, D. (2018). Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings. Retrieved from http://arxiv.org/abs/1804.05262v1
Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings
A Comparative Study of Pivot Selection Strategies for Unsupervised Domain Adaptation
Cui, X., Al-Bazzas, N., Bollegala, D., & Coenen, F. P. (2018). A Comparative Study of Pivot Selection Strategies for Unsupervised Domain Adaptation. The Knowledge Engineering Review.
Jointly learning word embeddings using a corpus and a knowledge base
Alsuhaibani, M., Bollegala, D., Maehara, T., & Kawarabayashi, K. -I. (2018). Jointly learning word embeddings using a corpus and a knowledge base. PLOS ONE, 13(3). doi:10.1371/journal.pone.0193094
Using $k$-way Co-occurrences for Learning Word Embeddings
Bollegala, D., Yoshida, Y., & Kawarabayashi, K. -I. (2018). Using $k$-way Co-occurrences for Learning Word Embeddings. Proceedings of the National Conference on Artificial Intelligence. Retrieved from http://arxiv.org/abs/1709.01199v1
An empirical study on fine-grained named entity recognition
Mai, K., Pham, T. H., Trung, N. M., Duc, N. T., Bolegala, D., Sasano, R., & Sekine, S. (2018). An empirical study on fine-grained named entity recognition. In COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings (pp. 711-722).
Classifier-Based Pattern Selection Approach for Relation Instance Extraction
Mandya, A., Bollegala, D., Coenen, F., & Atkinson, K. (2018). Classifier-Based Pattern Selection Approach for Relation Instance Extraction. In COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING (CICLING 2017), PT I Vol. 10761 (pp. 418-434). doi:10.1007/978-3-319-77113-7_33
Discovering Representative Space for Relational Similarity Measurement
Hakami, H., Mandya, A., & Bollegala, D. (2018). Discovering Representative Space for Relational Similarity Measurement. In COMPUTATIONAL LINGUISTICS, PACLING 2017 Vol. 781 (pp. 76-87). doi:10.1007/978-981-10-8438-6_7
Efficient and Effective Case Reject-Accept Filtering: A Study Using Machine Learning
Coenen, F. P., Bevan, R., Torrisi, A., Atkinson, K., & Bollegala, D. (n.d.). Efficient and Effective Case Reject-Accept Filtering: A Study Using Machine Learning. In JURIX 2018.
Frame-Based Semantic Patterns for Relation Extraction
Mandya, A., Bollegala, D., Coenen, F., & Atkinson, K. (2018). Frame-Based Semantic Patterns for Relation Extraction. In COMPUTATIONAL LINGUISTICS, PACLING 2017 Vol. 781 (pp. 51-62). doi:10.1007/978-981-10-8438-6_5
Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings
Coates, J., & Bollegala, D. (2018). Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) (pp. 194-198). Association for Computational Linguistics. doi:10.18653/v1/n18-2031
Is Something Better than Nothing? Automatically Predicting Stance-based Arguments Using Deep Learning and Small Labelled Dataset
Rajendran, P., Bollegala, D., & Parsons, S. (2018). Is Something Better than Nothing? Automatically Predicting Stance-based Arguments Using Deep Learning and Small Labelled Dataset. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) (pp. 28-34). Association for Computational Linguistics. doi:10.18653/v1/n18-2005
Learning word meta-embeddings by autoencoding
Bao, C., & Bollegala, D. (2018). Learning word meta-embeddings by autoencoding. In COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings (pp. 1650-1661).
Solving Feature Sparseness in Text Classification using Core-Periphery Decomposition
Cui, X., Kojaku, S., Masuda, N., & Bollegala, D. (2018). Solving Feature Sparseness in Text Classification using Core-Periphery Decomposition. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics (pp. 255-264). Association for Computational Linguistics. doi:10.18653/v1/s18-2030
Spectral Analysis of Keystroke Streams: Towards Effective Real-time Continuous User Authentication
Alshehri, A., Coenen, F., & Bollegala, D. (2018). Spectral Analysis of Keystroke Streams: Towards Effective Real-time Continuous User Authentication. In ICISSP: PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS SECURITY AND PRIVACY (pp. 62-73). doi:10.5220/0006606100620073
Think Globally, Embed Locally - Locally Linear Meta-embedding of Words.
Bollegala, D., Hayashi, K., & Kawarabayashi, K. -I. (2018). Think Globally, Embed Locally - Locally Linear Meta-embedding of Words.. In J. Lang (Ed.), IJCAI (pp. 3970-3976). ijcai.org. Retrieved from http://www.ijcai.org/proceedings/2018/
Using k-Way Co-Occurrences for Learning Word Embeddings
Bollegala, D., Yoshida, Y., & Kawarabayashi, K. -I. (n.d.). Using k-Way Co-Occurrences for Learning Word Embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 32. Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v32i1.12010
Why does PairDiff work? – A mathematical analysis of bilinear relational compositional operators for analogy detection
Hakami, H., Hayashi, K., & Bollegala, D. (2018). Why does PairDiff work? – A mathematical analysis of bilinear relational compositional operators for analogy detection. In COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings (pp. 2493-2504).
2017
TSP: Learning Task-Specific Pivots for Unsupervised Domain Adaptation
Coenen, F. P., Cui., & bollegala. (2017). TSP: Learning Task-Specific Pivots for Unsupervised Domain Adaptation. In ECML-PKDD.
Spectral Keyboard Streams: Towards Effective and Continuous Authentication
Coenen, F. P., alshehri., & bollegala. (2017). Spectral Keyboard Streams: Towards Effective and Continuous Authentication.
Compositional approaches for representing relations between words: A comparative study.
Hakami, H., & Bollegala, D. (2017). Compositional approaches for representing relations between words: A comparative study.. Knowl.-Based Syst., 136, 172-182.
Beyond co-occurrence-based ADR detection from Social Media
Bollegala, D., Maskell, S., & Pirmohamed, M. (2017). Beyond co-occurrence-based ADR detection from Social Media. Poster session presented at the meeting of Unknown Conference. Retrieved from https://www.webofscience.com/
Learning Linear Transformations between Counting-based and Prediction-based Word Embeddings
Bollegala, D., Hayashi, K., & Kawarabayashi, K. -I. (2017). Learning Linear Transformations between Counting-based and Prediction-based Word Embeddings. PLoS One, 12(9). doi:10.1371/journal.pone.0184544
Think Globally, Embed Locally --- Locally Linear Meta-embedding of Words
Why PairDiff works? -- A Mathematical Analysis of Bilinear Relational Compositional Operators for Analogy Detection
Compositional approaches for representing relations between words: A comparative study
Hakami, H., & Bollegala, D. (2017). Compositional approaches for representing relations between words: A comparative study. KNOWLEDGE-BASED SYSTEMS, 136, 172-182. doi:10.1016/j.knosys.2017.09.008
Compositional Approaches for Representing Relations Between Words: A Comparative Study
Learning Neural Word Salience Scores
Using $k$-way Co-occurrences for Learning Word Embeddings
An iterative approach for the global estimation of sentence similarity
Kajiwara, T., Bollegala, D., Yoshida, Y., & Kawarabayashi, K. -I. (2017). An iterative approach for the global estimation of sentence similarity. PLOS ONE, 12(9). doi:10.1371/journal.pone.0180885
Identifying Argument based Relation Properties in Opinions
Rajendran., Bollegala, D., & Parsons. (2017). Identifying Argument based Relation Properties in Opinions. In Springer LNCS. Myanmar.
Causality Patterns for Detecting Adverse Drug Reactions From Social Media: Text Mining Approach (Preprint)
Bollegala, D., Maskell, S., Sloane, R., Hajne, J., & Pirmohamed, M. (2017). Causality Patterns for Detecting Adverse Drug Reactions From Social Media: Text Mining Approach (Preprint). doi:10.2196/preprints.8214
CLIEL
García-Constantino, M., Atkinson, K., Bollegala, D., Chapman, K., Coenen, F., Roberts, C., & Robson, K. (2017). CLIEL. In Proceedings of the 16th edition of the International Conference on Articial Intelligence and Law Vol. 3 (pp. 79-87). ACM. doi:10.1145/3086512.3086520
Dynamic feature scaling for online learning of binary classifiers
Bollegala, D. (2017). Dynamic feature scaling for online learning of binary classifiers. Knowledge-Based Systems, 129, 97-105. doi:10.1016/j.knosys.2017.05.010
A classification approach for detecting cross-lingual biomedical term translations
Hakami, H., & Bollegala, D. (2017). A classification approach for detecting cross-lingual biomedical term translations. NATURAL LANGUAGE ENGINEERING, 23(1), 31-51. doi:10.1017/S1351324915000431
Accurate Continuous and Non-intrusive User Authentication with Multivariate Keystroke Streaming
Alshehri, A., Coenen, F., & Bollegala, D. (2017). Accurate Continuous and Non-intrusive User Authentication with Multivariate Keystroke Streaming. In Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (pp. 61-70). SCITEPRESS - Science and Technology Publications. doi:10.5220/0006497200610070
Effect of Data Imbalance on Unsupervised Domain Adaptation of Part-of-Speech Tagging and Pivot Selection Strategies.
Cui, X., Coenen, F., & Bollegala, D. (2017). Effect of Data Imbalance on Unsupervised Domain Adaptation of Part-of-Speech Tagging and Pivot Selection Strategies.. In LIDTA@PKDD/ECML Vol. 74 (pp. 103-115). PMLR. Retrieved from http://proceedings.mlr.press/v74/
User-to-User Recommendation using the Concept of Movement Patterns: A Study using a Dating Social Network
Al-Zeyadi, M., Coenen, F., & Lisitsa, A. (2017). User-to-User Recommendation using the Concept of Movement Patterns: A Study using a Dating Social Network. In Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (pp. 173-180). SCITEPRESS - Science and Technology Publications. doi:10.5220/0006494601730180
2016
Towards Keystroke Continuous Authentication Using Time Series Analytics
Alshehri, A., Coenen, F., & Bollegala, D. (2016). Towards Keystroke Continuous Authentication Using Time Series Analytics. In Unknown Conference (pp. 325-339). Springer International Publishing. doi:10.1007/978-3-319-47175-4_24
Keyboard Usage Authentication using Multi-variant Time Series Analysis
Coenen, F. P., Alshehri., & Bollegala. (2016). Keyboard Usage Authentication using Multi-variant Time Series Analysis. In Springer LNCS. Porto, Portugal.
Cross-domain Sentiment Classification using Sentiment Sensitive Embeddings
Bollegala, D., Mu, T., & Goulermas, Y. (2016). Cross-domain Sentiment Classification using Sentiment Sensitive Embeddings. IEEE Transactions on Knowledge and Data Engineering, 28(02), 389-410. doi:10.1109/TKDE.2015.2475761
Assessing Weight of Opinion by Aggregating Coalitions of Arguments
Rajendran, P., Bollegala, D., & Parsons, S. (2016). Assessing Weight of Opinion by Aggregating Coalitions of Arguments. In COMPUTATIONAL MODELS OF ARGUMENT Vol. 287 (pp. 431-438). doi:10.3233/978-1-61499-686-6-431
Contextual stance classification of opinions: A step towards enthymeme reconstruction in online reviews
Rajendran, P., Bollegala, D., & Parsons, S. (2016). Contextual stance classification of opinions: A step towards enthymeme reconstruction in online reviews. In Proceedings of the Third Workshop on Argument Mining (ArgMining2016). Association for Computational Linguistics. doi:10.18653/v1/w16-2804
Joint Word Representation Learning Using a Corpus and a Semantic Lexicon
Bollegala, D., Alsuhaibani, M., Maehara, T., & Kawarabayashi, K. -I. (n.d.). Joint Word Representation Learning Using a Corpus and a Semantic Lexicon. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 30. Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v30i1.10340
2015
Joint Word Representation Learning Using a Corpus and a Semantic Lexicon
Bollegala, D., Mohammed, A., Maehara, T., & Kawarabayashi, K. -I. (2016). Joint Word Representation Learning Using a Corpus and a Semantic Lexicon. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2690-2696. Retrieved from https://www.webofscience.com/
Joint Word Representation Learning using a Corpus and a Semantic Lexicon
Prediction of User Ratings of Oral Presentations using Label Relations
Yamasaki, T., Fukushima, Y., Furuta, R., Sun, L., Aizawa, K., & Bollegala, D. (2015). Prediction of User Ratings of Oral Presentations using Label Relations. In Proceedings of the 1st International Workshop on Affect & Sentiment in Multimedia (pp. 33-38). ACM. doi:10.1145/2813524.2813533
Social media and pharmacovigilance: A review of the opportunities and challenges
Sloane, R., Osanlou, O., Lewis, D., Bollegala, D., Maskell, S., & Pirmohamed, M. (2015). Social media and pharmacovigilance: A review of the opportunities and challenges. BRITISH JOURNAL OF CLINICAL PHARMACOLOGY, 80(4), 910-920. doi:10.1111/bcp.12717
Improved sampling using loopy belief propagation for probabilistic model building genetic programming
Sato, H., Hasegawa, Y., Bollegala, D., & Iba, H. (2015). Improved sampling using loopy belief propagation for probabilistic model building genetic programming. SWARM AND EVOLUTIONARY COMPUTATION, 23, 1-10. doi:10.1016/j.swevo.2015.02.002
A Cross-Lingual Similarity Measure for Detecting Biomedical Term Translations
Bollegala, D., Kontonatsios, G., & Ananiadou, S. (2015). A Cross-Lingual Similarity Measure for Detecting Biomedical Term Translations. PLoS One, 10(6). doi:10.1371/journal.pone.0126196
Unsupervised Cross-Domain Word Representation Learning
Bollegala, D., Maehara, T., & Kawarabayashi, K. -I. (2015). Unsupervised Cross-Domain Word Representation Learning. In Proceedings of the conference. Association for Computational Linguistics. Meeting Vol. 1 (pp. 730-740). Beijing, China,. doi:10.3115/v1/P15-1071
Unsupervised Cross-Domain Word Representation Learning
Embedding Semantic Relations into Word Representations
Bollegala, D., Maehara, T., & Kawarabayashi, K. -I. (2015). Embedding Semantic Relations into Word Representations. In PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI) (pp. 1222-1228). Retrieved from https://www.webofscience.com/
Embedding Semantic Relations into Word Representations
Simultaneous Higher-order Relation Prediction via Collective Incidence Matrix Embedding
Nori, N., Bollegala, D., & Kashima, H. (2015). Simultaneous Higher-order Relation Prediction via Collective Incidence Matrix Embedding. Transactions of the Japanese Society for Artificial Intelligence, 30(2), 459-465. doi:10.1527/tjsai.30.459
A Discourse Search Engine Based on Rhetorical Structure Theory
Kuyten, P., Bollegala, D., Hollerit, B., Prendinger, H., & Aizawa, K. (2015). A Discourse Search Engine Based on Rhetorical Structure Theory. In Unknown Conference (pp. 80-91). Springer International Publishing. doi:10.1007/978-3-319-16354-3_10
Embedding Semantic Relations into Word Representations.
Bollegala, D., Maehara, T., & Kawarabayashi, K. -I. (2015). Embedding Semantic Relations into Word Representations.. In Q. Yang, & M. J. Wooldridge (Eds.), IJCAI (pp. 1222-1228). AAAI Press. Retrieved from http://ijcai.org/proceedings/2015
Interest Prediction via Users' Actions on Social Media
Nori, N., Bollegala, D., & Ishizuka, M. (2015). Interest Prediction via Users' Actions on Social Media. Transactions of the Japanese Society for Artificial Intelligence, 30(4), 613-625. doi:10.1527/tjsai.30_613
Unsupervised Cross-Domain Word Representation Learning.
Bollegala, D., Maehara, T., & Kawarabayashi, K. -I. (2015). Unsupervised Cross-Domain Word Representation Learning.. CoRR, abs/1505.07184.
2014
Learning Word Representations from Relational Graphs
Bollegala, D., Maehara, T., Yoshida, Y., & Kawarabayashi, K. -I. (2015). Learning Word Representations from Relational Graphs. In PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE (pp. 2146-2152). Retrieved from https://www.webofscience.com/
Learning Word Representations from Relational Graphs
Dynamic Feature Scaling for Online Learning of Binary Classifiers
Bollegala, D. (2017). Dynamic feature scaling for online learning of binary classifiers. KNOWLEDGE-BASED SYSTEMS, 129, 97-105. doi:10.1016/j.knosys.2017.05.010
Dynamic Feature Scaling for Online Learning of Binary Classifiers
A Dimension Reduction Approach to Multinomial Relation Prediction
Nori, N., Bollegala, D., & Kashima, H. (2014). A Dimension Reduction Approach to Multinomial Relation Prediction. Transactions of the Japanese Society for Artificial Intelligence, 29(1), 168-176. doi:10.1527/tjsai.29.168
Learning Word Representations from Relational Graphs
Bollegala, D., Maehara, T., Yoshida, Y., & Kawarabayashi, K. -I. (n.d.). Learning Word Representations from Relational Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). doi:10.1609/aaai.v29i1.9494
Learning to Predict Distributions of Words Across Domains
Bollegala, D., Weir, D., & Carroll, J. (2014). Learning to Predict Distributions of Words Across Domains. In PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1 (pp. 613-623). Retrieved from https://www.webofscience.com/
2013
Mining for analogous tuples from an entity-relation graph
Bollegala, D., Kusumoto, M., Yoshida, Y., & Kawarabayashi, K. I. (2013). Mining for analogous tuples from an entity-relation graph. In IJCAI International Joint Conference on Artificial Intelligence (pp. 2064-2070).
Multi-Tweet Summarization of Real-Time Events
Khan, M. A. H., Bollegala, D., Liu, G., & Sezaki, K. (2013). Multi-Tweet Summarization of Real-Time Events. In 2013 ASE/IEEE INTERNATIONAL CONFERENCE ON SOCIAL COMPUTING (SOCIALCOM) (pp. 128-133). doi:10.1109/SocialCom.2013.26
Metaphor interpretation using paraphrases extracted from the web.
Bollegala, D., & Shutova, E. (2013). Metaphor interpretation using paraphrases extracted from the web.. PloS one, 8(9), e74304. doi:10.1371/journal.pone.0074304
Learning non-linear ranking functions for web search using probabilistic model building GP
Sato, H., Bollegala, D., Hasegawa, Y., & Iba, H. (2013). Learning non-linear ranking functions for web search using probabilistic model building GP. In 2013 IEEE Congress on Evolutionary Computation Vol. 308 (pp. 3371-3378). IEEE. doi:10.1109/cec.2013.6557983
Cross-Domain Sentiment Classification Using a Sentiment Sensitive Thesaurus
Bollegala, D., Weir, D., & Carroll, J. (2013). Cross-Domain Sentiment Classification Using a Sentiment Sensitive Thesaurus. IEEE Transactions on Knowledge and Data Engineering, 25(8), 1719-1731. doi:10.1109/tkde.2012.103
Minimally Supervised Novel Relation Extraction Using a Latent Relational Mapping
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2013). Minimally Supervised Novel Relation Extraction Using a Latent Relational Mapping. IEEE Transactions on Knowledge and Data Engineering, 25(2), 419-432. doi:10.1109/tkde.2011.250
A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization
Bollegala, D., Okazaki, N., & Ishizuka, M. (2013). A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization. In Theory and Applications of Natural Language Processing (pp. 253-276). Springer Berlin Heidelberg. doi:10.1007/978-3-642-28569-1_12
Improving relational similarity measurement using symmetries in proportional word analogies
Bollegala, D., Goto, T., Duc, N. T., & Ishizuka, M. (2013). Improving relational similarity measurement using symmetries in proportional word analogies. Information Processing & Management, 49(1), 355-369. doi:10.1016/j.ipm.2012.05.007
Jointly Learning Similarity Transformations for Textual Entailment
Yokote, K. -I., Bollegala, D., & Ishizuka, M. (2013). Jointly Learning Similarity Transformations for Textual Entailment. Transactions of the Japanese Society for Artificial Intelligence, 28(2), 220-229. doi:10.1527/tjsai.28.220
2012
A preference learning approach to sentence ordering for multi-document summarization
Bollegala, D., Okazaki, N., & Ishizuka, M. (2012). A preference learning approach to sentence ordering for multi-document summarization. Information Sciences, 217, 78-95. doi:10.1016/j.ins.2012.06.015
A Context Expansion Method for Supervised Word Sense Disambiguation
Tacoa, F., Bollegala, D., & Ishizuka, M. (2012). A Context Expansion Method for Supervised Word Sense Disambiguation. In 2012 IEEE Sixth International Conference on Semantic Computing Vol. 4 (pp. 339-341). IEEE. doi:10.1109/icsc.2012.27
Multinomial Relation Prediction in Social Data: A Dimension Reduction Approach
Nori, N., Bollegala, D., & Kashima, H. (n.d.). Multinomial Relation Prediction in Social Data: A Dimension Reduction Approach. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 26 (pp. 115-121). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v26i1.8110
Similarity Is Not Entailment — Jointly Learning Similarity Transformation for Textual Entailment
Yokote, K. -I., Bollegala, D., & Ishizuka, M. (n.d.). Similarity Is Not Entailment — Jointly Learning Similarity Transformation for Textual Entailment. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 26 (pp. 1720-1726). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v26i1.8348
Probabilistic model building GP with Belief propagation
Sato, H., Hasegawa, Y., Bollegala, D., & Iba, H. (2012). Probabilistic model building GP with Belief propagation. In 2012 IEEE Congress on Evolutionary Computation Vol. 3447 (pp. 1-8). IEEE. doi:10.1109/cec.2012.6256483
Cross-Language Latent Relational Search between Japanese and English Languages Using a Web Corpus
Duc, N. T., Bollegala, D., & Ishizuka, M. (2012). Cross-Language Latent Relational Search between Japanese and English Languages Using a Web Corpus. ACM Transactions on Asian Language Information Processing, 11(3), 1-33. doi:10.1145/2334801.2334805
AUTOMATIC ANNOTATION OF AMBIGUOUS PERSONAL NAMES ON THE WEB
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2012). AUTOMATIC ANNOTATION OF AMBIGUOUS PERSONAL NAMES ON THE WEB. Computational Intelligence, 28(3), 398-425. doi:10.1111/j.1467-8640.2012.00449.x
Improving the Accuracy of Attribute Extraction using the Relatedness between Attribute Values
Bollegala, D., Tani, N., & Ishizuka, M. (2012). Improving the Accuracy of Attribute Extraction using the Relatedness between Attribute Values. Transactions of the Japanese Society for Artificial Intelligence, 27(4), 245-252. doi:10.1527/tjsai.27.245
Measuring the Degree of Synonymy between Words Using Relational Similarity between Word Pairs as a Proxy
BOLLEGALA, D., MATSUO, Y., & ISHIZUKA, M. (2012). Measuring the Degree of Synonymy between Words Using Relational Similarity between Word Pairs as a Proxy. IEICE Transactions on Information and Systems, E95.D(8), 2116-2123. doi:10.1587/transinf.e95.d.2116
Multinomial Relation Prediction in Social Data: A Dimension Reduction Approach
Nori, N., Bollegala, D., & Kashima, H. (2012). Multinomial Relation Prediction in Social Data: A Dimension Reduction Approach. In Proceedings of the 26th AAAI Conference on Artificial Intelligence, AAAI 2012 (pp. 115-121).
Similarity Is Not Entailment - Jointly Learning Similarity Transformations for Textual Entailment
Yokote, K. I., Bollegala, D., & Ishizuka, M. (2012). Similarity Is Not Entailment - Jointly Learning Similarity Transformations for Textual Entailment. In Proceedings of the 26th AAAI Conference on Artificial Intelligence, AAAI 2012 (pp. 1720-1726).
2011
Interest prediction on multinomial, time-evolving social graphs
Nori, N., Bollegala, D., & Ishizuka, M. (2011). Interest prediction on multinomial, time-evolving social graphs. In IJCAI International Joint Conference on Artificial Intelligence (pp. 2507-2512). doi:10.5591/978-1-57735-516-8/IJCAI11-417
Relation adaptation: Learning to extract novel relations with minimum supervision
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2011). Relation adaptation: Learning to extract novel relations with minimum supervision. In IJCAI International Joint Conference on Artificial Intelligence (pp. 2205-2210). doi:10.5591/978-1-57735-516-8/IJCAI11-368
Using multiple sources to construct a sentiment sensitive thesaurus for cross-domain sentiment classification
Bollegala, D., Weir, D., & Carroll, J. (2011). Using multiple sources to construct a sentiment sensitive thesaurus for cross-domain sentiment classification. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies Vol. 1 (pp. 132-141).
Cross-Language Latent Relational Search: Mapping Knowledge across Languages
Tuan Duc, N., Bollegala, D., & Ishizuka, M. (n.d.). Cross-Language Latent Relational Search: Mapping Knowledge across Languages. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 25 (pp. 1237-1242). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v25i1.8075
Collaborative exploratory search in real-world context
Tani, N., Bollegala, D., Chandrasiri, N., Okamoto, K., Nawa, K., Iitsuka, S., & Matsuo, Y. (2011). Collaborative exploratory search in real-world context. In Proceedings of the 20th ACM international conference on Information and knowledge management (pp. 2137-2140). ACM. doi:10.1145/2063576.2063909
Improving Relational Search Performance using Relational Symmetries and Predictors
Goto, T., Tuan Duc, N., Danushka, B., & Ishizuka, M. (2011). Improving Relational Search Performance using Relational Symmetries and Predictors. Transactions of the Japanese Society for Artificial Intelligence, 26(6), 649-656. doi:10.1527/tjsai.26.649
An adaptive differential evolution algorithm
Noman, N., Bollegala, D., & Iba, H. (2011). An adaptive differential evolution algorithm. In 2011 IEEE Congress of Evolutionary Computation (CEC) (pp. 2229-2236). IEEE. doi:10.1109/cec.2011.5949891
Cross-Language Latent Relational Search: Mapping Knowledge across Languages
Duc, N. T., Bollegala, D., & Ishizuka, M. (2011). Cross-Language Latent Relational Search: Mapping Knowledge across Languages. In Proceedings of the 25th AAAI Conference on Artificial Intelligence, AAAI 2011 (pp. 1237-1242).
Exploiting User Interest on Social Media for Aggregating Diverse Data and Predicting Interest
Nori, N., Bollegala, D., & Ishizuka, M. (n.d.). Exploiting User Interest on Social Media for Aggregating Diverse Data and Predicting Interest. In Proceedings of the International AAAI Conference on Web and Social Media Vol. 5 (pp. 241-248). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/icwsm.v5i1.14114
Differential evolution with self adaptive local search
Noman, N., Bollegala, D., & Iba, H. (2011). Differential evolution with self adaptive local search. In Proceedings of the 13th annual conference on Genetic and evolutionary computation. ACM. doi:10.1145/2001576.2001725
RankDE
Bollegala, D., Noman, N., & Iba, H. (2011). RankDE. In Proceedings of the 13th annual conference on Genetic and evolutionary computation Vol. 4 (pp. 1771-1778). ACM. doi:10.1145/2001576.2001814
Total Environment for Text Data Mining
Sunayama, W., Takama, Y., Bollegala, D., Nishihara, Y., Tokunaga, H., Kushima, M., & Matsushita, M. (2011). Total Environment for Text Data Mining. Transactions of the Japanese Society for Artificial Intelligence, 26(4), 483-493. doi:10.1527/tjsai.26.483
From actors, politicians, to CEOs
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2011). From actors, politicians, to CEOs. In Proceedings of the 20th international conference companion on World wide web (pp. 13-14). ACM. doi:10.1145/1963192.1963200
Automatic Discovery of Personal Name Aliases from the Web
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2011). Automatic Discovery of Personal Name Aliases from the Web. IEEE Transactions on Knowledge and Data Engineering, 23(6), 831-844. doi:10.1109/tkde.2010.162
Semi-supervised Discourse Relation Classification with Structural Learning
Hernault, H., Bollegala, D., & Ishizuka, M. (2011). Semi-supervised Discourse Relation Classification with Structural Learning. In Unknown Conference (pp. 340-352). Springer Berlin Heidelberg. doi:10.1007/978-3-642-19400-9_27
Using Graph Based Method to Improve Bootstrapping Relation Extraction
Li, H., Bollegala, D., Matsuo, Y., & Ishizuka, M. (2011). Using Graph Based Method to Improve Bootstrapping Relation Extraction. In Unknown Conference (pp. 127-138). Springer Berlin Heidelberg. doi:10.1007/978-3-642-19437-5_10
Relation Representation and Indexing Method for a Fast and High Precision Latent Relational Web Search Engine
Tuan Duc, N., Bollegala, D., & Ishizuka, M. (2011). Relation Representation and Indexing Method for a Fast and High Precision Latent Relational Web Search Engine. Transactions of the Japanese Society for Artificial Intelligence, 26(2), 307-312. doi:10.1527/tjsai.26.307
A Supervised Classification Approach for Measuring Relational Similarity between Word Pairs
BOLLEGALA, D., MATSUO, Y., & ISHIZUKA, M. (2011). A Supervised Classification Approach for Measuring Relational Similarity between Word Pairs. IEICE Transactions on Information and Systems, E94-D(11), 2227-2233. doi:10.1587/transinf.e94.d.2227
A Web Search Engine-Based Approach to Measure Semantic Similarity between Words
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2011). A Web Search Engine-Based Approach to Measure Semantic Similarity between Words. IEEE Transactions on Knowledge and Data Engineering, 23(7), 977-990. doi:10.1109/tkde.2010.172
Automatic Extraction of Related Terms using Web Search Engines
WATANABE, K., BOLLEGALA, D., MATSUO, Y., & ISHIZUKA, M. (2011). Automatic Extraction of Related Terms using Web Search Engines. Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, 23(5), 739-748. doi:10.3156/jsoft.23.739
2010
A Sequential Model for Discourse Segmentation
Hernault, H., Bollegala, D., & Ishizuka, M. (2010). A Sequential Model for Discourse Segmentation. In Unknown Conference (pp. 315-326). Springer Berlin Heidelberg. doi:10.1007/978-3-642-12116-6_26
Using Relational Similarity between Word Pairs for Latent Relational Search on the Web
Duc, N. T., Bollegala, D., & Ishizuka, M. (2010). Using Relational Similarity between Word Pairs for Latent Relational Search on the Web. In 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (pp. 196-199). IEEE. doi:10.1109/wi-iat.2010.167
A semi-supervised approach to improve classification of infrequent discourse relations using feature vector extension
Hernault, H., Bollegala, D., & Ishizuka, M. (2010). A semi-supervised approach to improve classification of infrequent discourse relations using feature vector extension. In EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 399-409).
A supervised ranking approach for detecting relationally similar word pairs
Bollegala, D. (2010). A supervised ranking approach for detecting relationally similar word pairs. In 2010 Fifth International Conference on Information and Automation for Sustainability Vol. 11 (pp. 323-328). IEEE. doi:10.1109/iciafs.2010.5715681
Towards semi-supervised classification of discourse relations using feature correlations
Hernault, H., Bollegala, D., & Ishizuka, M. (2010). Towards semi-supervised classification of discourse relations using feature correlations. In Proceedings of the SIGDIAL 2010 Conference: 11th Annual Meeting of the Special Interest Group onDiscourse and Dialogue (pp. 55-58).
Exploiting Symmetry in Relational Similarity for Ranking Relational Search Results
Goto, T., Duc, N. T., Bollegala, D., & Ishizuka, M. (2010). Exploiting Symmetry in Relational Similarity for Ranking Relational Search Results. In Unknown Conference (pp. 595-600). Springer Berlin Heidelberg. doi:10.1007/978-3-642-15246-7_55
Relational duality
Bollegala, D. T., Matsuo, Y., & Ishizuka, M. (2010). Relational duality. In Proceedings of the 19th international conference on World wide web (pp. 151-160). ACM. doi:10.1145/1772690.1772707
A bottom-up approach to sentence ordering for multi-document summarization
Bollegala, D., Okazaki, N., & Ishizuka, M. (2010). A bottom-up approach to sentence ordering for multi-document summarization. Information Processing & Management, 46(1), 89-109. doi:10.1016/j.ipm.2009.07.004
2009
Measuring the similarity between implicit semantic relations from the web
Bollegala, D. T., Matsuo, Y., & Ishizuka, M. (2009). Measuring the similarity between implicit semantic relations from the web. In Proceedings of the 18th international conference on World wide web Vol. 3 (pp. 651-660). ACM. doi:10.1145/1526709.1526797
A study on attributional and relational similarity between word pairs on the Web
BOLLEGALA, D. (2009). A study on attributional and relational similarity between word pairs on the Web. doi:10.15083/00002426
Measuring the similarity between implicit semantic relations using web search engines
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2009). Measuring the similarity between implicit semantic relations using web search engines. In Proceedings of the Second ACM International Conference on Web Search and Data Mining Vol. 3 (pp. 104-113). ACM. doi:10.1145/1498759.1498815
A relational model of semantic similarity between words using automatically extracted lexical pattern clusters from the web
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2009). A relational model of semantic similarity between words using automatically extracted lexical pattern clusters from the web. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing Volume 2 - EMNLP '09 Vol. 2 (pp. 803). Association for Computational Linguistics. doi:10.3115/1699571.1699617
2008
Automatically Extracting Personal Name Aliases from the Web
Bollegala, D., Honma, T., Matsuo, Y., & Ishizuka, M. (2008). Automatically Extracting Personal Name Aliases from the Web. In Unknown Conference (pp. 77-88). Springer Berlin Heidelberg. doi:10.1007/978-3-540-85287-2_8
WWW sits the SAT: Measuring relational similarity on the web
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2008). WWW sits the SAT: Measuring relational similarity on the web. In Frontiers in Artificial Intelligence and Applications Vol. 178 (pp. 333-337). doi:10.3233/978-1-58603-891-5-333
Mining for personal name aliases on the web
Bollegala, D., Honma, T., Matsuo, Y., & Ishizuka, M. (2008). Mining for personal name aliases on the web. In Proceedings of the 17th international conference on World Wide Web (pp. 1107-1108). ACM. doi:10.1145/1367497.1367679
A Co-occurrence graph-based approach for personal name alias extraction from anchor texts
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2008). A Co-occurrence graph-based approach for personal name alias extraction from anchor texts. In IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference Vol. 2 (pp. 865-870).
2007
An integrated approach to measuring semantic similarity between words using information available on the Web
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2007). An integrated approach to measuring semantic similarity between words using information available on the Web. In NAACL HLT 2007 - Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference (pp. 340-347).
Measuring semantic similarity between words using web search engines
Measuring semantic similarity between words using web search engines (2007). In Proceedings of the 16th international conference on World Wide Web. ACM. doi:10.1145/1242572.1242675
2006
Spinning multiple social networks for Semantic Web
Matsuo, Y., Hamasaki, M., Nakamura, Y., Nishimura, T., Hasida, K., Takeda, H., . . . Ishizuka, M. (2006). Spinning multiple social networks for Semantic Web. In Proceedings of the National Conference on Artificial Intelligence Vol. 2 (pp. 1381-1387).
Extracting Key Phrases to Disambiguate Personal Names on the Web
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2006). Extracting Key Phrases to Disambiguate Personal Names on the Web. In Unknown Conference (pp. 223-234). Springer Berlin Heidelberg. doi:10.1007/11671299_24
A bottom-up approach to sentence ordering for multi-document summarization
Bollegala, D., Okazaki, N., & Ishizuka, M. (2006). A bottom-up approach to sentence ordering for multi-document summarization. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06 (pp. 385-392). Association for Computational Linguistics. doi:10.3115/1220175.1220224
Disambiguating personal names on the web using automatically extracted key phrases
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2006). Disambiguating personal names on the web using automatically extracted key phrases. Frontiers in Artificial Intelligence and Applications, 141, 553-557.
Extracting key phrases to disambiguate personal name queries in web search
Bollegala, D., Matsuo, Y., & Ishizuka, M. (2006). Extracting key phrases to disambiguate personal name queries in web search. In Proceedings of the Workshop on How Can Computational Linguistics Improve Information Retrieval? - CLIIR '06 (pp. 17). Association for Computational Linguistics. doi:10.3115/1629808.1629812
2005
A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation
Bollegala, D., Okazaki, N., & Ishizuka, M. (2005). A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation. In Unknown Conference (pp. 624-635). Springer Berlin Heidelberg. doi:10.1007/11562214_55