EMNLP - arXivDaily 期刊&会议

2109.15207 2021-10-01 cs.CV cs.CL cs.RO

Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments

Sonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang

Comments EMNLP 2021

2109.15000 2021-10-01 cs.CL

A surprisal--duration trade-off across and within the world's languages

Tiago Pimentel, Clara Meister, Elizabeth Salesky, Simone Teufel, Damián Blasi, Ryan Cotterell

Comments Accepted for publication in EMNLP 2021. Code available in https://github.com/rycolab/surprisal-duration-tradeoff

2109.14723 2021-10-01 cs.CL

BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief

Nora Kassner, Oyvind Tafjord, Hinrich Schütze, Peter Clark

Comments EMNLP 2021 Camera Ready. arXiv admin note: substantial text overlap with arXiv:2104.08401

2109.12212 2021-10-01 cs.CL cs.CV cs.CY

An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog

Xingyao Wang, David Jurgens

Comments Findings of EMNLP 2021; 30 pages

2106.11096 2021-10-01 cs.CL cs.IR

Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation

Yang Deng, Wenxuan Zhang, Wai Lam

Comments Accepted by W-NUT@EMNLP 2021

2104.08758 2021-10-01 cs.CL cs.AI

Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus

Jesse Dodge, Maarten Sap, Ana Marasović, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Margaret Mitchell, Matt Gardner

Comments EMNLP 2021 accepted paper camera ready version

1912.00147 2021-10-01 cs.CL cs.AI

Integrating Graph Contextualized Knowledge into Pre-trained Language Models

Bin He, Di Zhou, Jinghui Xiao, Xin jiang, Qun Liu, Nicholas Jing Yuan, Tong Xu

Comments Findings of EMNLP 2020

2109.14401 2021-09-30 cs.CL

BiQUE: Biquaternionic Embeddings of Knowledge Graphs

Jia Guo, Stanley Kok

Comments EMNLP 2021 (Main Conference)

2109.13984 2021-09-30 cs.CL cs.IR

Text Simplification for Comprehension-based Question-Answering

Tanvi Dadu, Kartikey Pant, Seema Nagar, Ferdous Ahmed Barbhuiya, Kuntal Dey

Comments Accepted at W-NUT Workshop to be held at EMNLP 2021 as a long paper. Also presented at DeMAL Workshop held at the Web Conference (WWW) 2021

2109.13032 2021-09-30 cs.CL

Patterns of Lexical Ambiguity in Contextualised Language Models

Janosch Haber, Massimo Poesio

Comments Accepted at Findings of EMNLP 2021. Data available at https://github.com/dali-ambiguity/Patterns-of-Lexical-Ambiguity . 9 pages, 4 figure, 4 tables. Includes appendix with 3 figures

2010.05740 2021-09-30 cs.CL

Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems

Yanjie Gou, Yinjie Lei, Lingqiao Liu, Yong Dai, Chunxu Shen

Comments EMNLP-2021

2109.13880 2021-09-29 cs.CL

Single-dataset Experts for Multi-dataset Question Answering

Dan Friedman, Ben Dodge, Danqi Chen

Comments EMNLP 2021. The code is available at https://github.com/princeton-nlp/MADE

2109.13770 2021-09-29 cs.CL

Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health

Andrew Lee, Jonathan K. Kummerfeld, Lawrence C. An, Rada Mihalcea

Comments To appear in Findings of EMNLP 2021

2109.13766 2021-09-29 cs.CL

On Homophony and Rényi Entropy

Tiago Pimentel, Clara Meister, Simone Teufel, Ryan Cotterell

Comments Accepted for publication in EMNLP 2021. Code available in https://github.com/rycolab/homophony-as-renyi-entropy

2109.13620 2021-09-29 cs.CL

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

Nikita Moghe, Mark Steedman, Alexandra Birch

Comments EMNLP 2021 Camera Ready

2109.13449 2021-09-29 cs.LG cs.CL cs.CV

When in Doubt: Improving Classification Performance with Alternating Normalization

Menglin Jia, Austin Reiter, Ser-Nam Lim, Yoav Artzi, Claire Cardie

Comments Findings of EMNLP 2021

2109.13296 2021-09-29 cs.CL

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation

Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, Dongwon Lee

Comments Accepted to Findings of EMNLP 2021

2103.11955 2021-09-29 cs.CL cs.AI cs.LG

Improving and Simplifying Pattern Exploiting Training

Derek Tam, Rakesh R Menon, Mohit Bansal, Shashank Srivastava, Colin Raffel

Comments EMNLP 2021 (12 pages, 2 figures)

2012.04780 2021-09-29 cs.CL cs.AI cs.IR cs.LG

Open Knowledge Graphs Canonicalization using Variational Autoencoders

Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo

Comments Accepted to EMNLP 2021

2109.13222 2021-09-28 cs.CL cs.LG

Using Pause Information for More Accurate Entity Recognition

Sahas Dendukuri, Pooja Chitkara, Joel Ruben Antony Moniz, Xiao Yang, Manos Tsagkias, Stephen Pulman

Comments Accepted at the 3rd Workshop on NLP for Conversational AI (EMNLP 2021)

2109.13070 2021-09-28 cs.CL

Controllable Neural Dialogue Summarization with Personal Named Entity Planning

Zhengyuan Liu, Nancy F. Chen

Comments EMNLP 2021 Main Conference

2109.13067 2021-09-28 cs.CL

Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance

Jan Wira Gotama Putra, Simone Teufel, Takenobu Tokunaga

Comments 9 pages (excluding citations and appendix), 10 figures, 3 tables, the paper has been accepted (peer-reviewed) for publication at the 8th Workshop on Argument Mining (co-located with EMNLP 2021)

2109.13006 2021-09-28 cs.AI cs.CL cs.LG cs.LO cs.NE

RuleBert: Teaching Soft Rules to Pre-trained Language Models

Mohammed Saeed, Naser Ahmadi, Preslav Nakov, Paolo Papotti

Comments Logical reasoning, soft Horn rules, Transformers, pre-trained language models, combining symbolic and probabilistic methods, BERT

Journal ref EMNLP-2021

2109.12969 2021-09-28 cs.CL cs.LG

Challenging the Semi-Supervised VAE Framework for Text Classification

Ghazi Felhi, Joseph Le Roux, Djamé Seddah

Comments Accepted at the EMNLP 2021 Workshop on Insights from Negative Results

2109.12860 2021-09-28 cs.CL cs.LG cs.SI

Classifying Dyads for Militarized Conflict Analysis

Niklas Stoehr, Lucas Torroba Hennigen, Samin Ahbab, Robert West, Ryan Cotterell

Comments Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2109.12781 2021-09-28 cs.CL cs.AI

Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction

Meisin Lee, Lay-Ki Soon, Eu-Gene Siew

Comments Accepted in ECONLP workshop at EMNLP 2021

2109.12776 2021-09-28 cs.CV cs.MM

Joint Multimedia Event Extraction from Video and Article

Brian Chen, Xudong Lin, Christopher Thomas, Manling Li, Shoya Yoshida, Lovish Chum, Heng Ji, Shih-Fu Chang

Comments To be presented at EMNLP 2021 findings

2109.12655 2021-09-28 cs.CL

QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions

Daniela Brook Weiss, Paul Roit, Ayal Klein, Ori Ernst, Ido Dagan

Comments Accepted to EMNLP 2021, Main Conference

2104.06960 2021-09-28 cs.CL

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce

Song Xu, Haoran Li, Peng Yuan, Yujia Wang, Youzheng Wu, Xiaodong He, Ying Liu, Bowen Zhou

Comments Accepted by Findings of EMNLP 2021

2011.14039 2021-09-28 cs.CL

An Investigation of Language Model Interpretability via Sentence Editing

Samuel Stevens, Yu Su

Comments 12 pages, 9 figures. Accepted at EMNLP BlackboxNLP 2021