Danushka Bollegala

CASE – Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement EACL 2026 Synthetic Data Generation for Training Diversified Commonsense Reasoning Models ACL 2026 Map of Encoders – Mapping Sentence Encoders using Quantum Relative Entropy ACL 2026 A Multilingual Social Bias Benchmark Incorporating Thinking Processes ACL 2026 Evaluating the Effect of Retrieval Augmentation on Social Biases EACL 2026 Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset EMNLP 2025 SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detection EMNLP 2025 An Ethical Dataset from Real-World Interactions Between Users and Large Language Models IJCAI 2025 Improving Unsupervised Constituency Parsing via Maximizing Semantic Information ICLR 2025 Evaluating the Evaluation of Diversity in Commonsense Generation ACL 2025 The Gaps between Fine Tuning and In-context Learning in Bias Evaluation and Debiasing COLING 2025 Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes COLING 2025 Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models EMNLP 2025 In-Contextual Gender Bias Suppression for Large Language Models EACL 2024 Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER NAACL 2024 Unsupervised Parsing by Searching for Frequent Word Sequences among Sentences with Equivalent Predicate-Argument Structures ACL 2024 A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection ACL 2024 Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings COLING 2024 Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning EMNLP 2024 Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models EMNLP 2024 The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated IJCNLP 2023 Learning to Predict Concept Ordering for Common Sense Generation IJCNLP 2023 Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation ACL 2023 Learning to Predict Concept Ordering for Common Sense Generation AACL 2023 A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings IJCNLP 2023 A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings AACL 2023 The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated AACL 2023 Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples EACL 2023 A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models EMNLP 2023 Can Word Sense Distribution Detect Semantic Changes of Words? EMNLP 2023 Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddings ACL 2023 Solving Cosine Similarity Underestimation between High Frequency Words by ℓ2 Norm Discounting ACL 2023 Swap and Predict – Predicting the Semantic Changes in Words across Corpora by Context Swapping EMNLP 2023 Evaluating the Robustness of Discrete Prompts EACL 2023 Together We Make Sense–Learning Meta-Sense Embeddings ACL 2023 A Survey on Word Meta-Embedding Learning IJCAI 2022 Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings ACL 2022 Position-based Prompting for Health Outcome Generation ACL 2022 Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks COLING 2022 On the Curious Case of l2 norm of Sense Embeddings EMNLP 2022 Gender Bias in Meta-Embeddings EMNLP 2022 Zero-shot Cross-Lingual Counterfactual Detection via Automatic Extraction and Prediction of Clue Phrases EMNLP 2022 Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings IJCAI 2022 Unmasking the Mask – Evaluating Social Biases in Masked Language Models AAAI 2022 Gender Bias in Masked Language Models for Multiple Languages NAACL 2022 Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion NAACL 2022 Detect and Classify – Joint Span Detection and Classification for Health Outcomes EMNLP 2021 I Wish I Would Have Loved This One, But I Didn’t – A Multilingual Dataset for Counterfactual Detection in Product Review EMNLP 2021 Debiasing Pre-trained Contextualised Embeddings EACL 2021 Dictionary-based Debiasing of Pre-trained Word Embeddings EACL 2021 RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding EACL 2021 Multi-Source Attention for Unsupervised Domain Adaptation AACL 2020 Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction COLING 2020 Autoencoding Improves Pre-trained Word Embeddings COLING 2020 Tree-Structured Neural Topic Model ACL 2020 Gender-preserving Debiasing for Pre-trained Word Embeddings ACL 2019 An Empirical Study on Fine-Grained Named Entity Recognition COLING 2018 Why does PairDiff work? - A Mathematical Analysis of Bilinear Relational Compositional Operators for Analogy Detection COLING 2018 Think Globally, Embed Locally --- Locally Linear Meta-embedding of Words IJCAI 2018 Learning Word Meta-Embeddings by Autoencoding COLING 2018 Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings NAACL 2018 Is Something Better than Nothing? Automatically Predicting Stance-based Arguments Using Deep Learning and Small Labelled Dataset NAACL 2018 Unsupervised Cross-Domain Word Representation Learning IJCNLP 2015 Embedding Semantic Relations into Word Representations IJCAI 2015 Unsupervised Cross-Domain Word Representation Learning ACL 2015 Learning to Predict Distributions of Words Across Domains ACL 2014 Mining for Analogous Tuples from an Entity-Relation Graph IJCAI 2013 Using Multiple Sources to Construct a Sentiment Sensitive Thesaurus for Cross-Domain Sentiment Classification ACL 2011 A Semi-Supervised Approach to Improve Classification of Infrequent Discourse Relations Using Feature Vector Extension EMNLP 2010 A Relational Model of Semantic Similarity between Words using Automatically Extracted Lexical Pattern Clusters from the Web EMNLP 2009 A Co-occurrence Graph-based Approach for Personal Name Alias Extraction from Anchor Texts IJCNLP 2008 An Integrated Approach to Measuring Semantic Similarity between Words Using Information Available on the Web NAACL 2007 A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization ACL 2006 A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization COLING 2006 A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation IJCNLP 2005