GPT-NeoX-20B: An Open-Source Autoregressive Language Model
Comments To appear in the Proceedings of the ACL Workshop on Challenges & Perspectives in Creating Large Language Models
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity
Comments To appear in Transactions of the Association for Computational Linguistics
Chart-to-Text: A Large-Scale Benchmark for Chart Summarization
Comments Accepted by ACL 2022 Main Conference
Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning
Comments ACL 2022 main + camera-ready version
Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
Comments ACL 2022
Your fairness may vary: Pretrained language model fairness in toxic text classification
Comments Findings of ACL 2022
Fast Few-shot Debugging for NLU Test Suites
Comments To appear at ACL 2022 Deep Learning Inside Out (DeeLIO) workshop
Can Question Rewriting Help Conversational Question Answering?
Comments Accepted at Workshop on Insights from Negative Results in NLP at ACL2022
Decomposed Meta-Learning for Few-Shot Named Entity Recognition
Comments This paper has been accepted for publication in Findings of ACL 2022. Code is available at: https://github.com/microsoft/vert-papers/tree/master/papers/DecomposedMetaNER
Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions
Comments Accepted to the 2022 ACL Workshop on Learning with Natural Language Supervision. 12 pages total, 9 figures, 2 tables
Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation
Comments Accepted to ACL 2022. Code will be available at [https://github.com/ghchen18/acl22-sixtp]
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
Comments Long paper accepted to ACL 2022 Findings
Quantified Reproducibility Assessment of NLP Results
Comments To be published in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL'22)
Mining Logical Event Schemas From Pre-Trained Language Models
Comments To appear at ACL SRW 2022
Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
Comments ACL 2022 Findings
MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages
Comments Accepted for oral presentation at ACL 2022 Workshop on Speech and Language Technologies for Dravidian Languages
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks
Comments ACL 2022
Not always about you: Prioritizing community needs when developing endangered language technology
Comments To appear in ACL 2022
A Comparative Study of Faithfulness Metrics for Model Interpretability Methods
Comments Accepted as a long paper to ACL 2022 main conference
Unified Speech-Text Pre-training for Speech Translation and Recognition
Comments ACL 2022 main conference
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
Comments Long paper accepted by ACL2022 main conference. arXiv admin note: substantial text overlap with arXiv:2104.02308
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering
Comments Accepted by ACL 2022 main conference; The dataset and code are available at https://github.com/jzhoubu/HLP
Meta-learning via Language Model In-context Tuning
Comments ACL 2022 camera-ready version
Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP
Comments accepted to appear at the ACL 2022 Main conference, see also: arXiv:2204.03954 for an extension with multi-label classification
Toward More Effective Human Evaluation for Machine Translation
Comments ACL 2022 Workshop on Human Evaluation of NLP Systems
Linguistic communication as (inverse) reward design
Comments 6 pages, 3 figures. Accepted at Learning from Natural Language Supervision workshop (ACL 2022)
End-to-End Speech Translation for Code Switched Speech
Comments Accepted to Findings of ACL 2022
A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition
Comments Accepted at Repl4NLP 2022 (ACL)
Assessment of Massively Multilingual Sentiment Classifiers
Comments Accepted for WASSA at ACL 2022
Same Author or Just Same Topic? Towards Content-Independent Style Representations
Comments accepted to the 7th workshop on RepL4NLP at ACL 2022
