Anna Rumshisky

Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models EMNLP 2025 MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs NAACL 2025 On Localizing and Deleting Toxic Memories in Large Language Models NAACL 2025 Deconstructing In-Context Learning: Understanding Prompts via Corruption COLING 2024 Emergent Abilities in Reduced-Scale Generative Language Models NAACL 2024 NarrativeTime: Dense Temporal Annotation on a Timeline COLING 2024 Prompt Perturbation Consistency Learning for Robust Language Models EACL 2024 ReLoRA: High-Rank Training Through Low-Rank Updates ICLR 2024 Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale. ACL 2023 Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning EMNLP 2023 Reasoning Circuits: Few-shot Multi-hop Question Generation with Structured Rationales ACL 2023 Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models ACL 2023 Sampling bias in NLU models: Impact and Mitigation Interspeech 2023 Chasing the Tail with Domain Generalization: A Case Study on Frequency-Enriched Datasets AACL 2022 Controlled Data Generation via Insertion Operations for NLU NAACL 2022 Down and Across: Introducing Crossword-Solving as a New NLP Benchmark ACL 2022 Federated Learning with Noisy User Feedback NAACL 2022 Learning to Ask Like a Physician NAACL 2022 Life after BERT: What do Other Muppets Understand about Language? ACL 2022 BERT Busters: Outlier Dimensions that Disrupt Transformers ACL 2021 A guide to the dataset explosion in QA, NLI, and commonsense reasoning COLING 2020 Getting Closer to AI Complete Question Answering: A Set of Prerequisite Real Tasks AAAI 2020 Towards Visual Dialog for Radiology ACL 2020 When BERT Plays the Lottery, All Tickets Are Winning EMNLP 2020 Adversarial Decomposition of Text Representation NAACL 2019 Calls to Action on Social Media: Detection, Social Impact, and Censorship Potential EMNLP 2019 Proceedings of the 2nd Clinical Natural Language Processing Workshop NAACL 2019 Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP NAACL 2019 Revealing the Dark Secrets of BERT EMNLP 2019 What’s in a Name? Reducing Bias in Bios without Access to Protected Attributes NAACL 2019 Context-Aware Neural Model for Temporal Information Extraction ACL 2018 Evaluating Creative Language Generation: The Case of Rap Lyric Ghostwriting NAACL 2018 RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian COLING 2018 Similarity-Based Reconstruction Loss for Meaning Representation EMNLP 2018 Triad-based Neural Network for Coreference Resolution COLING 2018 What’s in Your Embedding, And How It Predicts Task Performance COLING 2018 Here’s My Point: Joint Pointer Architecture for Argument Mining EMNLP 2017 HumorHawk at SemEval-2017 Task 6: Mixing Meaning and Sound for Humor Recognition SemEval 2017 Length, Interchangeability, and External Knowledge: Observations from Predicting Argument Convincingness IJCNLP 2017 SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor SemEval 2017 Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture EMNLP 2017 Towards Debate Automation: a Recurrent Model for Predicting Debate Winners EMNLP 2017 MUTT: Metric Unit TesTing for Language Generation Tasks ACL 2016 SimiHawk at SemEval-2016 Task 1: A Deep Ensemble System for Semantic Textual Similarity SemEval 2016 GhostWriter: Using an LSTM for Automatic Rap Lyric Generation EMNLP 2015 TwitterHawk: A Feature Bucket Based Approach to Sentiment Analysis SemEval 2015 SemEval-2010 Task 7: Argument Selection and Coercion SemEval 2010 Automating Temporal Annotation with TARSQI ACL 2005 Automated Induction of Sense in Context COLING 2004