EMNLP - arXivDaily 期刊&会议

2108.12465 2021-09-10 cs.CL cs.AI

Code-switched inspired losses for generic spoken dialog representations

Emile Chapuis, Pierre Colombo, Matthieu Labeau, Chloe Clavel

Journal ref EMNLP 2021

2108.12463 2021-09-10 cs.CL cs.AI

Automatic Text Evaluation through the Lens of Wasserstein Barycenters

Pierre Colombo, Guillaume Staerman, Chloe Clavel, Pablo Piantanida

Journal ref EMNLP 2021

2104.08825 2021-09-10 cs.CL cs.AI

Flexible Generation of Natural Language Deductions

Kaj Bostrom, Xinyu Zhao, Swarat Chaudhuri, Greg Durrett

Comments Accepted to EMNLP 2021 (long paper). 9 pages (13 with references and appendix), 8 figures

2104.08803 2021-09-10 cs.CL cs.AI cs.LG

Consistent Accelerated Inference via Confident Adaptive Transformers

Tal Schuster, Adam Fisch, Tommi Jaakkola, Regina Barzilay

Comments EMNLP 2021

2104.08801 2021-09-10 cs.CL cs.AI cs.LG

Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval

Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban, Siva Reddy

Comments EMNLP 2021

2104.08530 2021-09-10 cs.CL

The Topic Confusion Task: A Novel Scenario for Authorship Attribution

Malik H. Altakrori, Jackie Chi Kit Cheung, Benjamin C. M. Fung

Comments 15 pages (9 + ref./appin.), 6 figures, Accepted to Findings of EMNLP 2021

2104.08202 2021-09-10 cs.CL

$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering

Or Honovich, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend

Comments Accepted to EMNLP 2021

2104.08164 2021-09-10 cs.CL cs.AI cs.LG

Editing Factual Knowledge in Language Models

Nicola De Cao, Wilker Aziz, Ivan Titov

Comments Accepted at EMNLP2021 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Code at https://github.com/nicola-decao/KnowledgeEditor . 16 pages, 6 figures, 2 tables

2104.08027 2021-09-10 cs.CL cs.AI cs.LG

Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders

Fangyu Liu, Ivan Vulić, Anna Korhonen, Nigel Collier

Comments EMNLP 2021 camera-ready version

2103.12235 2021-09-10 cs.CL

Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization

Ansong Ni, Matt Gardner, Pradeep Dasigi

Comments Accepted to EMNLP 2021 (main conference)

2010.12758 2021-09-10 cs.CL

NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions

Zhiyu Chen, Honglei Liu, Hu Xu, Seungwhan Moon, Hao Zhou, Bing Liu

Comments Findings of EMNLP 2021

2010.11818 2021-09-10 cs.CL

Compositional Generalization via Semantic Tagging

Hao Zheng, Mirella Lapata

Comments EMNLP 2021, Findings

2010.06196 2021-09-10 cs.CL cs.AI

Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations

Tianqiao Liu, Qiang Fang, Wenbiao Ding, Hang Li, Zhongqin Wu, Zitao Liu

Comments EMNLP'21: The 2021 Conference on Empirical Methods in Natural Language Processing, 2021

2009.09363 2021-09-10 cs.CL

Understanding Mention Detector-Linker Interaction in Neural Coreference Resolution

Zhaofeng Wu, Matt Gardner

Comments CRAC @ EMNLP 2021

2109.03808 2021-09-09 cs.CL

Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation

Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, Iryna Gurevych

Comments Accepted as a conference paper to EMNLP 2021

2109.03792 2021-09-09 cs.CL cs.AI stat.ML

Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Nicola De Cao, Wilker Aziz, Ivan Titov

Comments Accepted at EMNLP2021 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Code at https://github.com/nicola-decao/efficient-autoregressive-EL . 8 pages, 1 figure, 3 tables

2109.03764 2021-09-09 cs.CL cs.AI cs.LG

Active Learning by Acquiring Contrastive Examples

Katerina Margatina, Giorgos Vernikos, Loïc Barrault, Nikolaos Aletras

Comments Accepted at EMNLP 2021

2109.03731 2021-09-09 cs.CL

Cross-Policy Compliance Detection via Question Answering

Marzieh Saeidi, Majid Yazdani, Andreas Vlachos

Journal ref EMNLP 2021

2109.03695 2021-09-09 cs.CL cs.AI

Continuous Entailment Patterns for Lexical Inference in Context

Martin Schmitt, Hinrich Schütze

Comments Accepted as a short paper at EMNLP 2021. Code available at https://github.com/mnschmit/conan

2108.13990 2021-09-09 cs.CL cs.AI cs.LG

Effective Sequence-to-Sequence Dialogue State Tracking

Jeffrey Zhao, Mahdis Mahdieh, Ye Zhang, Yuan Cao, Yonghui Wu

Comments Accepted at EMNLP 2021

2104.04670 2021-09-09 cs.CL cs.AI

Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections

Ruiqi Zhong, Kristy Lee, Zheng Zhang, Dan Klein

Comments EMNLP 2021, Findings

2103.09120 2021-09-09 cs.CL

Structural Adapters in Pretrained Language Models for AMR-to-text Generation

Leonardo F. R. Ribeiro, Yue Zhang, Iryna Gurevych

Comments Accepted as a long conference paper to EMNLP 2021

2109.03646 2021-09-09 cs.CL

Sustainable Modular Debiasing of Language Models

Anne Lauscher, Tobias Lüken, Goran Glavaš

Comments Accepted for EMNLP-Findings 2021

2109.03645 2021-09-09 cs.CL

Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach

Víctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez

Comments To be published as long paper in EMNLP 2021

2109.03630 2021-09-09 cs.CL

Discrete and Soft Prompting for Multilingual Models

Mengjie Zhao, Hinrich Schütze

Comments EMNLP 2021

2109.03502 2021-09-09 cs.CL cs.IR cs.LG

R2-D2: A Modular Baseline for Open-Domain Question Answering

Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz

Comments Accepted to Findings of EMNLP'21. arXiv admin note: substantial text overlap with arXiv:2102.10697

2109.03415 2021-09-09 cs.CL

Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models

Jiaoda Li, Duygu Ataman, Rico Sennrich

Comments EMNLP 2021

2109.03334 2021-09-09 cs.CL cs.AI

On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings

Peter Jansen, Kelly Smith, Dan Moreno, Huitzilin Ortiz

Comments Accepted to EMNLP 2021

2109.02377 2021-09-09 cs.CL cs.LG

PermuteFormer: Efficient Relative Position Encoding for Long Sequences

Peng Chen

Comments Accepted by EMNLP 2021

2108.13134 2021-09-09 cs.CL

Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation

Yuexiang Xie, Fei Sun, Yang Deng, Yaliang Li, Bolin Ding

Comments Accepted by EMNLP-21