Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models
Comments 9 pages (excluding references), accepted at ACL Findings 2023
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Comments Accepted to ACL 2023 Main Conference (Long Paper)
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Comments Findings of the Association for Computational Linguistics: ACL 2023. 10 pages, 2 tables, 4 figures (20 pages, 8 tables, 7 figures including references and appendices)
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP
Comments ACL 2023
MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages
Comments Accepted to ACL 2023 (Main conference)
Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction
Comments Findings of ACL 2023
Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks
Comments Accepted at ACL 2023 Findings
Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation
Comments ACL 2023
TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation
Comments 10 pages, accepted in main conference of ACL 2023
Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker
Comments Findings of ACL 2023 Camera Ready
Exploring Large Language Models for Classical Philology
Comments Paper accepted for publication at ACL 2023 Main; 10 pages, 7 appendix pages, 4 figures, 13 tables
Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations
Comments ACL 2023; Github: https://github.com/allenai/mslr-annotated-dataset
mPMR: A Multilingual Pre-trained Machine Reader at Scale
Comments To appear at ACL 2023 main conference
AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese
Comments 16 pages, 6 figures, 8 tables, appearing in Findings of the ACL: ACL 2023. This version compiled using pdfLaTeX-compatible Assamese script font. Assamese text may appear differently here than in official ACL 2023 proceedings
FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models
Comments Accepted by ACL 2023 (Findings)
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
Comments 11 pages, 2 figures, 8 tables, accepted as a long paper to ACL 203
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
Comments Accepted by ACL 2023
Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method
Comments Accepted by ACL 2023
On the Limitations of Simulating Active Learning
Comments To appear at Findings of ACL 2023
LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development
Comments 9 pages, long paper at ACL 2023 proceedings
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
Comments ACL 2023, main conference
Putting Natural in Natural Language Processing
Comments Findings of the ACL 2023
Understanding Differential Search Index for Text Retrieval
Comments Accepted to Findings of ACL 2023
Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications
Comments 17 pages, 11 figures, to appear in Findings of the Association for Computational Linguistics 2023
The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources in Natural Language Understanding Systems
Comments Accepted at ACL 2023. Code available at https://github.com/mpoemsl/kitmus
Robustness of Learning from Task Instructions
Comments ACL'23 Finding Accepted
Prompted Opinion Summarization with GPT-3.5
Comments Accepted to ACL (Findings) 2023
In-sample Curriculum Learning by Sequence Completion for Natural Language Generation
Comments ACL'23
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings
Comments Accepted to ACL 2023
A Study on the Efficiency and Generalization of Light Hybrid Retrievers
Comments accepted to ACL23
