EMNLP - arXivDaily 期刊&会议

2210.10325 2022-10-20 cs.CL

Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping

Chenghao Yang, Xuezhe Ma

Comments EMNLP 2022 Camera Ready

2210.10320 2022-10-20 cs.CL

Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking

Yinghui Li, Shirong Ma, Qingyu Zhou, Zhongli Li, Li Yangning, Shulin Huang, Ruiyang Liu, Chao Li, Yunbo Cao, Haitao Zheng

Comments Long paper, accepted at the Findings of EMNLP 2022

2210.10293 2022-10-20 cs.CL

Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning

Hongqiu Wu, Ruixue Ding, Hai Zhao, Boli Chen, Pengjun Xie, Fei Huang, Min Zhang

Comments EMNLP 2022 (findings)

2210.10291 2022-10-20 cs.CL

Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation

Mengting Hu, Yike Wu, Hang Gao, Yinhao Bai, Shiwan Zhao

Comments EMNLP 2022

2210.10227 2022-10-20 cs.LG cs.AI cs.CL

Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling

Kalpa Gunaratna, Vijay Srinivasan, Akhila Yerukola, Hongxia Jin

Comments EMNLP 2022

2210.10163 2022-10-20 cs.CV cs.CL

MedCLIP: Contrastive Learning from Unpaired Medical Images and Text

Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, Jimeng Sun

Comments EMNLP 2022

2210.10041 2022-10-20 cs.CL cs.AI cs.LG

Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning

Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du, Qing Qu, Hongyuan Mei

Comments EMNLP 2022 camera-ready

2210.09803 2022-10-20 cs.CL

Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis

Shuai Fan, Chen Lin, Haonan Li, Zhenghao Lin, Jinsong Su, Hang Zhang, Yeyun Gong, Jian Guo, Nan Duan

Comments Accepted to EMNLP 2022

2210.08713 2022-10-20 cs.AI

Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation

Xiaohui Song, Longtao Huang, Hui Xue, Songlin Hu

Comments Accepted by EMNLP 2022

2210.06694 2022-10-20 cs.CL cs.AI

SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See

Comments Accepted to the main conference of EMNLP 2022

2210.05499 2022-10-20 cs.CL

Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network

Yuxiang Nie, Heyan Huang, Wei Wei, Xian-Ling Mao

Comments Accepted to the main conference of EMNLP 2022

2204.13692 2022-10-20 cs.CL

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures

Jannis Vamvas, Rico Sennrich

Comments Findings of EMNLP 2022

2202.07280 2022-10-20 cs.CL

Saving Dense Retriever from Shortcut Dependency in Conversational Search

Sungdong Kim, Gangwoo Kim

Comments Accepted to EMNLP 2022 main conference

2202.06671 2022-10-20 cs.CL

Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings

Malte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp, Georg Rehm

Comments Accepted to EMNLP 2022

2201.12093 2022-10-20 cs.CL

PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings

Qiyu Wu, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, Daxin Jiang

Comments To appear at EMNLP 2022

2112.04195 2022-10-20 cs.CL

VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction

Dan Li, Yang Yang, Hongyin Tang, Jingang Wang, Tong Xu, Wei Wu, Enhong Chen

Comments Accepted by EMNLP 2022

2111.10962 2022-10-20 cs.CL cs.AI

Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples

Linlin Liu, Xin Li, Ruidan He, Lidong Bing, Shafiq Joty, Luo Si

Comments Accepted by EMNLP 2022

2110.08247 2022-10-20 cs.CR cs.AI cs.CL

Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks

Yangyi Chen, Fanchao Qi, Hongcheng Gao, Zhiyuan Liu, Maosong Sun

Comments Accepted to EMNLP 2022, main conference

2210.10045 2022-10-19 cs.CL cs.AI

SafeText: A Benchmark for Exploring Physical Safety in Language Models

Sharon Levy, Emily Allaway, Melanie Subbiah, Lydia Chilton, Desmond Patton, Kathleen McKeown, William Yang Wang

Comments Accepted to EMNLP 2022

2210.10020 2022-10-19 cs.CV cs.CL

ULN: Towards Underspecified Vision-and-Language Navigation

Weixi Feng, Tsu-Jui Fu, Yujie Lu, William Yang Wang

Comments EMNLP 2022

2210.09926 2022-10-19 cs.CL cs.AI cs.LG

RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction

Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie

Comments 9 pages, accepted by EMNLP 2022

2210.09708 2022-10-19 cs.AI

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

Comments Full paper of EMNLP 2022 Findings

2210.09658 2022-10-19 cs.CL

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models

Lan Jiang, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Rui Jiang

Comments Accepted to EMNLP 2022. Code is available at https://github.com/jiangllan/ROSE

2210.09588 2022-10-19 cs.CL

Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks

Jaehoon Oh, Jongwoo Ko, Se-Young Yun

Comments The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2210.09587 2022-10-19 cs.CL

Summary Workbench: Unifying Application and Evaluation of Text Summarization Models

Shahbaz Syed, Dominik Schwabe, Martin Potthast

Comments Accepted as system demonstration at EMNLP 2022

2210.09556 2022-10-19 cs.CL cs.SD eess.AS

Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation

Chen Wang, Yuchen Liu, Boxing Chen, Jiajun Zhang, Wei Luo, Zhongqiang Huang, Chengqing Zong

Comments Accepted by the main conference of EMNLP 2022

2210.09545 2022-10-19 cs.CL cs.CR cs.LG

Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

Zhiyuan Zhang, Lingjuan Lyu, Xingjun Ma, Chenguang Wang, Xu Sun

Comments Accepted by Findings of EMNLP 2022

2210.09492 2022-10-19 cs.CL

Systematicity in GPT-3's Interpretation of Novel English Noun Compounds

Siyan Li, Riley Carlson, Christopher Potts

Comments Findings of EMNLP 2022

2210.09396 2022-10-19 cs.CL cs.AI cs.CY cs.SD eess.AS

Affective Idiosyncratic Responses to Music

Sky CH-Wang, Evan Li, Oliver Li, Smaranda Muresan, Zhou Yu

Comments EMNLP 2022 Main Conference; see Github https://github.com/skychwang/music-emotions

2210.09345 2022-10-19 cs.CL

CrossRE: A Cross-Domain Dataset for Relation Extraction

Elisa Bassignana, Barbara Plank

Comments Accepted in Findings of the Association for Computational Linguistics: EMNLP 2022