What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?
Comments To appear at ACL 2023
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT
Comments Accepted at ACL 2023
LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction
Comments ACL 2023
Exploring Lottery Prompts for Pre-trained Language Models
Comments Accepted to ACL 2023
Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers
Comments Accepted to ACL2023 Main Conference
Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses
Comments Accepted to ACL (Findings) 2023
Controlled Text Generation with Hidden Representation Transformations
Comments Accepted at ACL 2023 as a long paper (Findings)
Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Comments Accepted to Findings of ACL2023
Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale
Comments Accepted to ACL 2023 Findings
Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion
Comments Accept at ACL2023
QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations
Comments ACL 2023; Dataset available at https://github.com/google-research/language/tree/master/language/quest
Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System
Comments Accepted to Findings of ACL2023
Continual Contrastive Finetuning Improves Low-Resource Relation Extraction
Comments ACL 2023
Generic Temporal Reasoning with Differential Analysis and Explanation
Journal ref Proceedings of ACL 2023
ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations
Comments Accepted to ACL 2023 main conference, 9 pages + bibliography + appendix
I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons
Comments Accepted to ACL 2023. 18 pages, 11 figures, 5 Tables
Synthetic Pre-Training Tasks for Neural Machine Translation
Comments Accepted to ACL2023-Findings. New added Phrase-cat for synthetic pre-training. 17 pages including 5-page appendix
PAD-Net: An Efficient Framework for Dynamic Networks
Comments Proceedings of ACL 2023
RARR: Researching and Revising What Language Models Say, Using Language Models
Comments ACL 2023
Are Sample-Efficient NLP Models More Robust?
Comments 18 pages, 14 figures; to appear at ACL 2023
CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
Comments ACL 2023 Camera Ready. 14 pages, 7 figures, 4 tables
Multi-Document Summarization with Centroid-Based Pretraining
Comments ACL 2023 camera-ready
Do Question Answering Modeling Improvements Hold Across Benchmarks?
Comments 31 pages, 13 figures; to appear at ACL 2023
Concise Answers to Complex Questions: Summarization of Long-form Answers
Comments ACL 2023 Long Paper
Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning
Comments To appear in the Findings of ACL 2023. Code available at https://github.com/umgupta/jointly-reparametrized-finetuning
The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
Comments Findings of ACL 2023. Code and data are available at https://github.com/xxxiaol/magic-if
SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages
Comments ACL 2023, Long Paper
An AMR-based Link Prediction Approach for Document-level Event Argument Extraction
Comments Accepted to ACL 2023
Comparing and combining some popular NER approaches on Biomedical tasks
Comments Accepted to the ACL BioNLP Workshop, 2023
Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings
Comments Accepted to Findings of ACL 2023
