EMNLP - arXivDaily 期刊&会议

2109.01935 2021-09-07 cs.CL

Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case

Jingqing Zhang, Luis Bolanos, Tong Li, Ashwani Tanwar, Guilherme Freire, Xian Yang, Julia Ive, Vibhor Gupta, Yike Guo

Comments EMNLP 2021 long paper accepted

2109.01819 2021-09-07 cs.CL cs.AI cs.LG

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling

Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras

Comments Accepted at EMNLP 2021

2109.01758 2021-09-07 cs.CL

Data Augmentation for Cross-Domain Named Entity Recognition

Shuguang Chen, Gustavo Aguilar, Leonardo Neves, Thamar Solorio

Comments To appear at EMNLP 2021 main conference

2108.13875 2021-09-07 cs.CL cs.AI cs.IR

When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions

Zixian Huang, Ao Wu, Yulin Shen, Gong Cheng, Yuzhong Qu

Comments 10 pages, accepted to Findings of EMNLP 2021

2104.06129 2021-09-07 cs.CL

What's in your Head? Emergent Behaviour in Multi-Task Transformer Models

Mor Geva, Uri Katz, Aviv Ben-Arie, Jonathan Berant

Comments EMNLP 2021

2012.14913 2021-09-07 cs.CL

Transformer Feed-Forward Layers Are Key-Value Memories

Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy

Comments EMNLP 2021

2109.01583 2021-09-06 cs.CL cs.AI

Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding

Yingmei Guo, Linjun Shou, Jian Pei, Ming Gong, Mingxing Xu, Zhiyong Wu, Daxin Jiang

Comments Long paper at EMNLP 2021

2109.01484 2021-09-06 cs.CL cs.LG

Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation

Haoran Yang, Wai Lam, Piji Li

Comments Findings of EMNLP 2021

2109.01396 2021-09-06 cs.CL

Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT

Elena Voita, Rico Sennrich, Ivan Titov

Comments EMNLP 2021

2109.01330 2021-09-06 cs.CL

Detecting Speaker Personas from Conversational Texts

Jia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu, Zhigang Chen, Xiaodan Zhu

Comments Accepted by EMNLP 2021

2109.01238 2021-09-06 cs.CL cs.AI

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction

Samuel Mensah, Kai Sun, Nikolaos Aletras

Comments Accepted at EMNLP 2021

2104.08724 2021-09-06 cs.CL

Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation

Yuning Mao, Wenchang Ma, Deren Lei, Jiawei Han, Xiang Ren

Comments EMNLP 2021

2101.00406 2021-09-06 cs.CL

CDLM: Cross-Document Language Modeling

Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew E. Peters, Arie Cattan, Ido Dagan

Comments EMNLP 2021, findings

2012.14682 2021-09-06 cs.CL

CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade

Lei Li, Yankai Lin, Deli Chen, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun

Comments Findings of EMNLP 2021

2011.08277 2021-09-06 cs.CV cs.CL

Where Are You? Localization from Embodied Dialog

Meera Hahn, Jacob Krantz, Dhruv Batra, Devi Parikh, James M. Rehg, Stefan Lee, Peter Anderson

Journal ref EMNLP 2020

2010.10333 2021-09-06 cs.CL cs.IR

CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation

Wenchang Ma, Ryuichi Takanobu, Minlie Huang

Comments EMNLP 2021 long paper

1905.10617 2021-09-06 cs.LG cs.CL stat.ML

Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?

Tianxing He, Jingzhao Zhang, Zhiming Zhou, James Glass

Journal ref EMNLP 2021

2109.01100 2021-09-03 cs.CL

How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?

Chantal Amrhein, Rico Sennrich

Comments Findings of EMNLP 2021

2109.01078 2021-09-03 cs.CL

Skim-Attention: Learning to Focus via Document Layout

Laura Nguyen, Thomas Scialom, Jacopo Staiano, Benjamin Piwowarski

Comments 15 pages, 6 figures, to be published in EMNLP 2021 Findings

2109.00859 2021-09-03 cs.CL cs.PL

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

Yue Wang, Weishi Wang, Shafiq Joty, Steven C. H. Hoi

Comments Accepted to EMNLP 2021. 13 pages

2104.08691 2021-09-03 cs.CL

The Power of Scale for Parameter-Efficient Prompt Tuning

Brian Lester, Rami Al-Rfou, Noah Constant

Comments Accepted to EMNLP 2021

2109.00668 2021-09-03 cs.CL

Towards Making the Most of Dialogue Characteristics for Neural Chat Translation

Yunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu, Yufeng Chen, Jinsong Su, Jie Zhou

Comments Accepted as a long paper at EMNLP 2021 main conference. The first two authors contributed equally. Code: https://github.com/XL2248/CSA-NCT

2109.00602 2021-09-03 cs.CL

Point-of-Interest Type Prediction using Text and Images

Danae Sánchez Villegas, Nikolaos Aletras

Comments Accepted at EMNLP 2021

2109.00591 2021-09-03 cs.CL cs.AI

Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech

Tomer Wullach, Amir Adler, Einat Minkov

Comments Accepted to Findings of ACL: EMNLP 2021

2109.00523 2021-09-03 cs.CL cs.LG

Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification

Shuhuai Ren, Jinchao Zhang, Lei Li, Xu Sun, Jie Zhou

Comments Accepted by EMNLP 2021 main conference (Long Paper)

2109.00521 2021-09-03 cs.LG cs.CL

Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques

Hossein Amirkhani, Mohammad Taher Pilehvar

Comments Findings of EMNLP, 2021

2108.12599 2021-09-03 cs.CL cs.AI cs.HC cs.IR

Smoothing Dialogue States for Open Conversational Machine Reading

Zhuosheng Zhang, Siru Ouyang, Hai Zhao, Masao Utiyama, Eiichiro Sumita

Comments Accepted by EMNLP 2021 Main Conference

2103.01834 2021-09-03 cs.CL cs.AI

A Data-Centric Framework for Composable NLP Workflows

Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Haoying Zhang, Xiaodan Liang, Teruko Mitamura, Eric P. Xing, Zhiting Hu

Comments 8 pages, 4 figures, EMNLP 2020

2010.07620 2021-09-03 cs.AI cs.CL

GMH: A General Multi-hop Reasoning Model for KG Completion

Yao Zhang, Hongru Liang, Adam Jatowt, Wenqiang Lei, Xin Wei, Ning Jiang, Zhenglu Yang

Comments Accepted to EMNLP 2021; 10 pages, 5 figures, 4 tables

2004.01935 2021-09-03 cs.CL

An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis

Yunlong Liang, Fandong Meng, Jinchao Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

Comments Accepted to Findings of EMNLP 2021. arXiv admin note: substantial text overlap with: arXiv:2004.01935