EMNLP - arXivDaily 期刊&会议

2109.09105 2021-09-22 cs.CL cs.AI cs.LG eess.AS

What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study

Ayush Kumar, Mukuntha Narayanan Sundararaman, Jithendra Vepa

Comments BlackboxNLP @ EMNLP 2021 (15 pages, includes Appendix)

2109.08828 2021-09-22 cs.CL

Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes

Hyunwoo Kim, Byeongchang Kim, Gunhee Kim

Comments Accepted at EMNLP 2021 main conference. For the code and dataset, see https://github.com/skywalker023/focused-empathy

2109.02550 2021-09-22 cs.CL

You should evaluate your language model on marginal likelihood over tokenisations

Kris Cao, Laura Rimell

Comments accepted at EMNLP 2021

2104.08253 2021-09-22 cs.CL cs.IR

Condenser: a Pre-training Architecture for Dense Retrieval

Luyu Gao, Jamie Callan

Comments EMNLP 2021

2104.03630 2021-09-22 cs.CL cs.LG

A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders

Maarten De Raedt, Fréderic Godin, Pieter Buteneers, Chris Develder, Thomas Demeester

Comments EMNLP 2021 - Short Paper Track

2103.06819 2021-09-22 cs.CR

TAG: Gradient Attack on Transformer-based Language Models

Jieren Deng, Yijue Wang, Ji Li, Chao Shang, Hang Liu, Sanguthevar Rajasekaran, Caiwen Ding

Comments Accepted to Findings of EMNLP 2021

2109.09707 2021-09-21 cs.CL cs.AI

A Plug-and-Play Method for Controlled Text Generation

Damian Pascual, Beni Egressy, Clara Meister, Ryan Cotterell, Roger Wattenhofer

Comments Findings of EMNLP 2021

2109.09700 2021-09-21 cs.CL cs.AI

BERT Cannot Align Characters

Antonis Maronikolakis, Philipp Dufter, Hinrich Schütze

Comments Second Workshop on Insights from Negative Results, EMNLP 2021

2109.09577 2021-09-21 cs.CL cs.AI

MeetDot: Videoconferencing with Live Translation Captions

Arkady Arkhangorodsky, Christopher Chu, Scot Fang, Yiqi Huang, Denglin Jiang, Ajay Nagesh, Boliang Zhang, Kevin Knight

Comments 7 pages, 4 figures, Accepted as EMNLP 2021 demo paper

2109.09366 2021-09-21 cs.CL cs.LG

Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

Gaël Guibon, Matthieu Labeau, Hélène Flamein, Luce Lefeuvre, Chloé Clavel

Journal ref The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), Nov 2021, Punta Cana, Dominican Republic

2109.09234 2021-09-21 cs.CL

Conditional probing: measuring usable information beyond a baseline

John Hewitt, Kawin Ethayarajh, Percy Liang, Christopher D. Manning

Comments EMNLP 2021 + typo fixes

2109.09209 2021-09-21 cs.CL

CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization

Shuyang Cao, Lu Wang

Comments EMNLP 2021

2109.09191 2021-09-21 cs.CL cs.AI

Training Dynamic based data filtering may not work for NLP datasets

Arka Talukdar, Monika Dagar, Prachi Gupta, Varun Menon

Comments EMNLP BlackBoxNLP 2021

2109.09133 2021-09-21 cs.CL

Preventing Author Profiling through Zero-Shot Multilingual Back-Translation

David Ifeoluwa Adelani, Miaoran Zhang, Xiaoyu Shen, Ali Davody, Thomas Kleinbauer, Dietrich Klakow

Comments Accepted to EMNLP 2021 (Main Conference), 9 pages

2109.09057 2021-09-21 cs.CL

Knowledge-Enhanced Evidence Retrieval for Counterargument Generation

Yohan Jo, Haneul Yoo, JinYeong Bak, Alice Oh, Chris Reed, Eduard Hovy

Comments To appear in Findings of EMNLP 2021

2109.08877 2021-09-21 cs.CL cs.AI

DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation

Zeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che

Comments Accepted by EMNLP 2021

2109.08820 2021-09-21 cs.CL cs.AI cs.LG

Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems

Di Jin, Shuyang Gao, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur

Comments To appear at NLP4ConvAI workshop of EMNLP 2021

2109.08805 2021-09-21 cs.CL cs.AI cs.IR cs.LG

BERT-Beta: A Proactive Probabilistic Approach to Text Moderation

Fei Tan, Yifan Hu, Kevin Yen, Changwei Hu

Comments 9 pages, EMNLP'21

2109.08780 2021-09-21 cs.LG cs.SE

Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy

Colin B. Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, Alexey Svyatkovskiy

Comments EMNLP 2021 camera ready

2109.08705 2021-09-21 cs.CL cs.LG

Relating Neural Text Degeneration to Exposure Bias

Ting-Rui Chiang, Yun-Nung Chen

Comments Accepted by BlackBoxNLP at EMNLP 2021

2109.07779 2021-09-21 cs.CL

Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation

Lei Shen, Jinchao Zhang, Jiao Ou, Xiaofang Zhao, Jie Zhou

Comments Accepted by EMNLP 2021 Findings

2109.05696 2021-09-21 cs.CL

How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding

Tianda Li, Ahmad Rashid, Aref Jafari, Pranav Sharma, Ali Ghodsi, Mehdi Rezagholizadeh

Comments Accepted as EMNLP 2021 Findings

2109.00750 2021-09-21 cs.CL

Neural News Recommendation with Collaborative News Encoding and Structural User Encoding

Zhiming Mao, Xingshan Zeng, Kam-Fai Wong

Comments EMNLP 2021 Findings

2104.08639 2021-09-21 cs.CL

AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples

Qianchu Liu, Edoardo M. Ponti, Diana McCarthy, Ivan Vulić, Anna Korhonen

Comments EMNLP 2021 long paper

2104.08445 2021-09-21 cs.CL cs.AI

Joint Passage Ranking for Diverse Multi-Answer Retrieval

Sewon Min, Kenton Lee, Ming-Wei Chang, Kristina Toutanova, Hannaneh Hajishirzi

Comments 13 pages; Published as a conference paper at EMNLP 2021 (long)

2104.07972 2021-09-21 cs.CL cs.LG

Language Models are Few-Shot Butlers

Vincent Micheli, François Fleuret

Comments EMNLP 2021

2104.07846 2021-09-21 cs.CL

Multivalent Entailment Graphs for Question Answering

Nick McKenna, Liane Guillou, Mohammad Javad Hosseini, Sander Bijl de Vroe, Mark Johnson, Mark Steedman

Comments Accepted to EMNLP 2021

2104.00764 2021-09-21 cs.CL

SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis

Pranav Maneriker, Yuntian He, Srinivasan Parthasarathy

Comments EMNLP 2021 camera ready version

2103.13076 2021-09-21 cs.CL

Finetuning Pretrained Transformers into RNNs

Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith

Comments EMNLP 2021

2010.13263 2021-09-21 cs.SI cs.CY

PoliWAM: An Exploration of a Large Scale Corpus of Political Discussions on WhatsApp Messenger

Vivek Srivastava, Mayank Singh

Comments Accepted at W-NUT, EMNLP