EMNLP - arXivDaily 期刊&会议

2205.06262 2022-10-17 cs.CL

FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue

Alon Albalak, Yi-Lin Tuan, Pegah Jandaghi, Connor Pryor, Luke Yoffe, Deepak Ramachandran, Lise Getoor, Jay Pujara, William Yang Wang

Comments EMNLP 2022. benchmark available at https://alon-albalak.github.io/feta-website

2110.04093 2022-10-17 cs.CL

How to Do Things without Words: Modeling Semantic Drift of Emoji

Eyal Arviv, Oren Tsur

Comments To be published at EMNLP 2022

2109.13563 2022-10-17 cs.CL cs.AI cs.CY

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement

Elisa Leonardelli, Stefano Menini, Alessio Palmero Aprosio, Marco Guerini, Sara Tonelli

Comments To appear at EMNLP 2021 (long paper)

2210.07197 2022-10-14 cs.CL

Towards a Unified Multi-Dimensional Evaluator for Text Generation

Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

Comments EMNLP 2022

2210.05197 2022-10-14 cs.CL cs.AI cs.IR

Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA

Junjie Huang, Wanjun Zhong, Qian Liu, Ming Gong, Daxin Jiang, Nan Duan

Comments Accepted to Findings of EMNLP 2022

2210.06895 2022-10-14 cs.LG

GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization

Zhiyuan Zhang, Ruixuan Luo, Qi Su, Xu Sun

Comments Accepted by EMNLP 2022

2210.06894 2022-10-14 cs.LG cs.CR

Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation

Zhiyuan Zhang, Qi Su, Xu Sun

Comments Accepted by Findings of EMNLP 2022

2210.06881 2022-10-14 cs.CV cs.AI

RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval

Xing Wu, Chaochen Gao, Zijia Lin, Zhongyuan Wang, Jizhong Han, Songlin Hu

Comments EMNLP 2022

2210.06716 2022-10-14 cs.CL

Low-resource Neural Machine Translation with Cross-modal Alignment

Zhe Yang, Qingkai Fang, Yang Feng

Comments Accepted to EMNLP 2022

2210.06656 2022-10-14 cs.CL

Knowledge-grounded Dialog State Tracking

Dian Yu, Mingqiu Wang, Yuan Cao, Izhak Shafran, Laurent El Shafey, Hagen Soltau

Comments EMNLP 2022 Findings

2210.03304 2022-10-14 cs.CL

Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding

Zhichao Yang, Shufan Wang, Bhanu Pratap Singh Rawat, Avijit Mitra, Hong Yu

Comments Accepted by Findings of EMNLP 2022, code is available at https://github.com/whaleloops/KEPT

2204.12130 2022-10-14 cs.CL

LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models

Mor Geva, Avi Caciularu, Guy Dar, Paul Roit, Shoval Sadde, Micah Shlain, Bar Tamir, Yoav Goldberg

Comments EMNLP 2022 System Demonstrations

2203.14680 2022-10-14 cs.CL

Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Mor Geva, Avi Caciularu, Kevin Ro Wang, Yoav Goldberg

Comments EMNLP 2022

2201.04337 2022-10-14 cs.CL

PromptBERT: Improving BERT Sentence Embeddings with Prompts

Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang

Comments EMNLP 2022

2109.12053 2022-10-14 cs.CL

Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus

Daniela Trotta, Raffaele Guarasci, Elisa Leonardelli, Sara Tonelli

Comments Findings of EMNLP 2021. Dataset available at https://github.com/dhfbk/ItaCoLA-dataset

2210.06350 2022-10-13 cs.LG cs.AI cs.NE

CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations

Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

Comments Accepted to EMNLP 2022

2210.06277 2022-10-13 cs.CL cs.AI cs.IR cs.LG

Task Compass: Scaling Multi-task Pre-training with Task Prefix

Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng

Comments Findings of EMNLP 2022

2210.05875 2022-10-13 cs.CL

MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score

Sunjae Kwon, Zonghai Yao, Harmon S. Jordan, David A. Levy, Brian Corner, Hong Yu

Comments Accepted to EMNLP 22

2210.05839 2022-10-13 cs.CL cs.HC

SEAL : Interactive Tool for Systematic Error Analysis and Labeling

Nazneen Rajani, Weixin Liang, Lingjiao Chen, Meg Mitchell, James Zou

Comments Accepted at EMNLP 2022 demo track

2210.05287 2022-10-13 cs.CL

Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training

Taolin Zhang, Junwei Dong, Jianing Wang, Chengyu Wang, Ang Wang, Yinghui Liu, Jun Huang, Yong Li, Xiaofeng He

Comments EMNLP 2022 industry track

2210.04443 2022-10-13 cs.LG cs.AI cs.CL

Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue

So Yeon Min, Hao Zhu, Ruslan Salakhutdinov, Yonatan Bisk

Comments To Appear in the Proceedings of EMNLP 2022

2209.15565 2022-10-13 cs.CL cs.AI

Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions

Rindranirina Ramamonjison, Haley Li, Timothy T. Yu, Shiqi He, Vishnu Rengan, Amin Banitalebi-Dehkordi, Zirui Zhou, Yong Zhang

Comments Accepted for presentation at the EMNLP 2022 Conference (industry track)

2204.10290 2022-10-13 cs.CL

Learning to Revise References for Faithful Summarization

Griffin Adams, Han-Chin Shing, Qing Sun, Christopher Winestock, Kathleen McKeown, Noémie Elhadad

Comments Findings of EMNLP 2022

2201.03533 2022-10-13 cs.CL cs.AI cs.LG stat.ML

SCROLLS: Standardized CompaRison Over Long Language Sequences

Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, Omer Levy

Comments EMNLP 2022

2108.12637 2022-10-13 cs.CL

Oh My Mistake!: Toward Realistic Dialogue State Tracking including Turnback Utterances

Takyoung Kim, Yukyung Lee, Hoonsang Yoon, Pilsung Kang, Junseong Bang, Misuk Kim

Comments SereTOD Workshop at EMNLP 2022

2108.10949 2022-10-13 cs.CL

Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowing

Vera Provatorova, Svitlana Vakulenko, Samarth Bhargav, Evangelos Kanoulas

Journal ref Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021) 10501-10510

2210.05549 2022-10-12 cs.CL cs.AI cs.LG cs.NE

Continual Training of Language Models for Few-Shot Learning

Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, Bing Liu

Journal ref EMNLP 2022

2210.05528 2022-10-12 cs.CL cs.AI

Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems

Neeraj Varshney, Chitta Baral

Comments EMNLP 2022

2210.05497 2022-10-12 cs.CL

Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models

Qihuang Zhong, Liang Ding, Li Shen, Peng Mi, Juhua Liu, Bo Du, Dacheng Tao

Comments Accepted by EMNLP 2022 (Findings)

2210.05471 2022-10-12 cs.CL cs.AI

Instance Regularization for Discriminative Language Model Pre-training

Zhuosheng Zhang, Hai Zhao, Ming Zhou

Comments Accepted to EMNLP 2022