EMNLP - arXivDaily 期刊&会议

2109.04443 2021-09-10 cs.CL cs.AI cs.LG

HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints

Sahana Ramnath, Melvin Johnson, Abhirut Gupta, Aravindan Raghuveer

Comments 17 pages including references and appendix. Accepted at EMNLP 2021

2109.04413 2021-09-10 cs.CL

AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models

Harish Tayyar Madabushi, Edward Gow-Smith, Carolina Scarton, Aline Villavicencio

Comments Findings of EMNLP 2021. Code available at: https://github.com/H-TayyarMadabushi/AStitchInLanguageModels

2109.04404 2021-09-10 cs.CL cs.LG

All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality

William Timkey, Marten van Schijndel

Comments Accepted at EMNLP 2021

2109.04385 2021-09-10 cs.CL

Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification

Maximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin

Comments EMNLP 2021

2109.04367 2021-09-10 cs.CL cs.CR cs.LG

Multi-granularity Textual Adversarial Attack with Behavior Cloning

Yangyi Chen, Jin Su, Wei Wei

Comments Accepted by the main conference of EMNLP 2021

2109.04349 2021-09-10 cs.CL

Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance

Carel van Niekerk, Andrey Malinin, Christian Geishauser, Michael Heck, Hsien-chin Lin, Nurul Lubis, Shutong Feng, Milica Gašić

Comments 14 pages, 2 figures, accepted at EMNLP 2021 Main conference, Code at: https://gitlab.cs.uni-duesseldorf.de/general/dsml/setsumbt-public

2109.04325 2021-09-10 cs.CL cs.AI cs.LG

Learning Opinion Summarizers by Selecting Informative Reviews

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Comments EMNLP 2021

2109.04319 2021-09-10 cs.CL cs.AI cs.LG

Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data

Massimo Nicosia, Zhongdi Qu, Yasemin Altun

Comments Accepted to EMNLP 2021 (Findings)

2109.04312 2021-09-10 cs.CL cs.AI cs.IR cs.LG

MATE: Multi-view Attention for Table Transformer Efficiency

Julian Martin Eisenschlos, Maharshi Gor, Thomas Müller, William W. Cohen

Comments Accepted to EMNLP 2021

2109.04144 2021-09-10 cs.CL cs.AI

Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning

Prasetya Ajie Utama, Nafise Sadat Moosavi, Victor Sanh, Iryna Gurevych

Comments Accepted at EMNLP 2021

2109.04108 2021-09-10 cs.CL cs.AI

MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction

Manqing Dong, Chunguang Pan, Zhipeng Luo

Comments Accepted as a long paper in the main conference of EMNLP 2021

2109.04101 2021-09-10 cs.LG cs.AI cs.CL

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He

Comments EMNLP 2021

2109.04096 2021-09-10 cs.CL cs.AI

A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation

Shilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren, Longhui Zhang, Shujuan Yin

Comments Accepted by EMNLP 2021 main conference

2109.04095 2021-09-10 cs.CL

Debiasing Methods in Natural Language Understanding Make Bias More Accessible

Michael Mendelson, Yonatan Belinkov

Comments Accepted at EMNLP 2021

2109.04084 2021-09-10 cs.CL

Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

Yicheng Zou, Zhihua Liu, Xingwu Hu, Qi Zhang

Comments Accepted by EMNLP 2021, 12 pages

2109.04053 2021-09-10 cs.CL cs.AI cs.LG

Table-based Fact Verification with Salience-aware Learning

Fei Wang, Kexuan Sun, Jay Pujara, Pedro Szekely, Muhao Chen

Comments EMNLP 2021 (Findings)

2109.04030 2021-09-10 cs.LG

Bag of Tricks for Optimizing Transformer Efficiency

Ye Lin, Yanyang Li, Tong Xiao, Jingbo Zhu

Comments accepted by EMNLP (Findings) 2021

2109.04018 2021-09-10 cs.CL

Graphine: A Dataset for Graph-aware Terminology Definition Generation

Zequn Liu, Shukai Wang, Yiyang Gu, Ruiyi Zhang, Ming Zhang, Sheng Wang

Comments EMNLP 2021

2109.04014 2021-09-10 cs.CL

Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering

Man Luo, Yankai Zeng, Pratyay Banerjee, Chitta Baral

Comments accepted at EMNLP 2021

2109.04008 2021-09-10 cs.CL

Graph Based Network with Contextualized Representations of Turns in Dialogue

Bongseok Lee, Yong Suk Choi

Comments EMNLP 2021

2109.04002 2021-09-10 cs.CL

Competence-based Curriculum Learning for Multilingual Machine Translation

Mingliang Zhang, Fandong Meng, Yunhai Tong, Jie Zhou

Comments Accepted by Findings of EMNLP 2021. We release the codes at https://github.com/zml24/ccl-m

2109.03939 2021-09-10 cs.CL cs.AI

What's Hidden in a One-layer Randomly Weighted Transformer?

Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael W. Mahoney

Comments EMNLP 2021 (short)

2109.03888 2021-09-10 cs.CL

Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems

Potsawee Manakul, Mark J. F. Gales

Comments EMNLP 2021 (short paper, main conference)

2109.03853 2021-09-10 cs.CL cs.IT math.IT

A Bayesian Framework for Information-Theoretic Probing

Tiago Pimentel, Ryan Cotterell

Comments Accepted for publication in EMNLP 2021. Code available in https://github.com/rycolab/bayesian-mi

2109.03821 2021-09-10 cs.IR cs.LG

Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction

Zeyu Li, Wei Cheng, Reema Kshetramade, John Houser, Haifeng Chen, Wei Wang

Comments 16 pages; Accepted to Findings of EMNLP-2021

2109.03819 2021-09-10 cs.CL cs.LG

Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer

Zeyu Li, Yilong Qin, Zihan Liu, Wei Wang

Comments 13 pages; EMNLP-2021 Main Conference

2109.03160 2021-09-10 cs.CL

How much pretraining data do language models need to learn syntax?

Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner

Comments To be published in proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)

2109.02747 2021-09-10 cs.CV cs.CL

WhyAct: Identifying Action Reasons in Lifestyle Vlogs

Oana Ignat, Santiago Castro, Hanwen Miao, Weiji Li, Rada Mihalcea

Comments Accepted at EMNLP 2021

2109.00922 2021-09-10 cs.LG cs.AI cs.CL

Improving Multimodal fusion via Mutual Dependency Maximisation

Pierre Colombo, Emile Chapuis, Matthieu Labeau, Chloe Clavel

Journal ref EMNLP 2021

2108.12870 2021-09-10 cs.CL

Multiplex Graph Neural Network for Extractive Text Summarization

Baoyu Jing, Zeyu You, Tao Yang, Wei Fan, Hanghang Tong

Comments Accepted by EMNLP'2021