NAACL - arXivDaily 期刊&会议

2104.03945 2021-04-09 cs.CL

On Biasing Transformer Attention Towards Monotonicity

Annette Rios, Chantal Amrhein, Noëmi Aepli, Rico Sennrich

Comments To be published in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2021)

2104.03879 2021-04-09 cs.CL

COVID-19 Named Entity Recognition for Vietnamese

Thinh Hung Truong, Mai Hoang Dao, Dat Quoc Nguyen

Comments To appear in Proceedings of NAACL 2021

2104.03848 2021-04-09 cs.CL

Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification

Wilson Fearn, Orion Weller, Kevin Seppi

Comments Accepted to NAACL 2021

2104.03523 2021-04-09 cs.CL

User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization

Shohei Higashiyama, Masao Utiyama, Taro Watanabe, Eiichiro Sumita

Comments NAACL-HLT 2021

2104.03514 2021-04-09 cs.CL

Low-Complexity Probing via Finding Subnetworks

Steven Cao, Victor Sanh, Alexander M. Rush

Comments NAACL-HLT 2021

2104.03474 2021-04-09 cs.CL

Revisiting Simple Neural Probabilistic Language Models

Simeng Sun, Mohit Iyyer

Comments To appear at NAACL 2021

2104.03465 2021-04-09 cs.CL

Nutribullets Hybrid: Multi-document Health Summarization

Darsh J Shah, Lili Yu, Tao Lei, Regina Barzilay

Comments NAACL 2021 Camera Ready

2103.14349 2021-04-09 cs.CL

DAGN: Discourse-Aware Graph Network for Logical Reasoning

Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang

Comments Accepted by NAACL 2021

2101.01476 2021-04-09 cs.CL

PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing

Linh The Nguyen, Dat Quoc Nguyen

Comments To appear in Proceedings of NAACL 2021: Demonstrations

2005.00174 2021-04-09 cs.CL cs.CR

Universal Adversarial Attacks with Natural Triggers for Text Classification

Liwei Song, Xinwei Yu, Hsuan-Tung Peng, Karthik Narasimhan

Comments Accepted by NAACL 2021, code is available at https://github.com/Hsuan-Tung/universal_attack_natural_trigger

2104.02947 2021-04-08 cs.LG

Distantly Supervised Transformers For E-Commerce Product QA

Happy Mittal, Aniket Chakrabarti, Belhassen Bayar, Animesh Anant Sharma, Nikhil Rasiwasia

Comments NAACL 2021 (10 pages)

2010.11784 2021-04-08 cs.CL cs.AI cs.LG

Self-Alignment Pretraining for Biomedical Entity Representations

Fangyu Liu, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, Nigel Collier

Comments NAACL 2021 camera-ready version

2007.07834 2021-04-08 cs.CL

InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training

Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, Ming Zhou

Comments NAACL 2021

1911.00234 2021-04-08 cs.LG cs.IR stat.ML

Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation

Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir, Ambedkar Dukkipati

Comments Accepted in NAACL-HLT 2021

2104.02484 2021-04-07 cs.CL cs.AI cs.LG

OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation

Petr Marek, Vishal Ishwar Naik, Vincent Auvray, Anuj Goyal

Comments NAACL 2021 Industry track

2104.02205 2021-04-07 cs.CL

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

Shuyang Cao, Lu Wang

Comments Accepted at NAACL 2021 (short paper)

2103.08493 2021-04-07 cs.LG

How Many Data Points is a Prompt Worth?

Teven Le Scao, Alexander M. Rush

Comments NAACL HLT 2021

2103.08490 2021-04-07 cs.CL

Multi-view Subword Regularization

Xinyi Wang, Sebastian Ruder, Graham Neubig

Comments Accepted at NAACL 2021

2104.01853 2021-04-06 cs.CL cs.LG

Rethinking Perturbations in Encoder-Decoders for Fast Training

Sho Takase, Shun Kiyono

Comments Accepted at NAACL-HLT 2021

2104.01782 2021-04-06 cs.CL

BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification

Ishani Mondal

Comments To appear in NAACL 2021

2104.01726 2021-04-06 cs.CL

A New Approach to Overgenerating and Scoring Abstractive Summaries

Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu

Comments NAACL 2021 (Long Paper)

2104.01724 2021-04-06 cs.CL

Inference Time Style Control for Summarization

Shuyang Cao, Lu Wang

Comments Accepted at NAACL 2021 (short paper)

2104.01697 2021-04-06 cs.CL

A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution

Tuan Lai, Heng Ji, Trung Bui, Quan Hung Tran, Franck Dernoncourt, Walter Chang

Comments Accepted by NAACL 2021

2104.01666 2021-04-06 cs.CL

Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning

Hui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu

Comments Accepted to Main Conference of NAACL 2021 as Long Paper

2103.16057 2021-04-06 cs.CL cs.LG

Grounding Open-Domain Instructions to Automate Web Support Tasks

Nancy Xu, Sam Masling, Michael Du, Giovanni Campagna, Larry Heck, James Landay, Monica S Lam

Comments To be published in NAACL 2021

2104.00783 2021-04-05 cs.CL

Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems

Derek Chen, Howard Chen, Yi Yang, Alex Lin, Zhou Yu

Comments 16 pages, 5 figures. Accepted at NAACL 2021

2103.12440 2021-04-05 cs.IR cs.CL

Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness

Florian Boudin, Ygor Gallina

Comments Accepted at NAACL 2021

2104.00664 2021-04-02 cs.CL cs.LG

Sampling and Filtering of Neural Machine Translation Distillation Data

Vilém Zouhar

Comments 6 pages (without references); to be published in NAACL-SRW

2004.03137 2021-04-02 cs.CL

Cross-lingual Supervision Improves Unsupervised Neural Machine Translation

Mingxuan Wang, Hongxiao Bai, Hai Zhao, Lei Li

Comments NAACL Industry Track

2010.08318 2021-04-01 cs.CL

Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification

Andrew Moore, Jeremy Barnes

Comments To appear at NAACL 2021 (long)