EMNLP - arXivDaily 期刊&会议

2305.13993 2023-10-24 cs.CL

Condensing Multilingual Knowledge with Lightweight Language-Specific Modules

Haoran Xu, Weiting Tan, Shuyue Stella Li, Yunmo Chen, Benjamin Van Durme, Philipp Koehn, Kenton Murray

Comments Accepted at the main conference of EMNLP 2023

2305.13735 2023-10-24 cs.CL cs.AI cs.LG

Aligning Large Language Models through Synthetic Feedback

Sungdong Kim, Sanghwan Bae, Jamin Shin, Soyoung Kang, Donghyun Kwak, Kang Min Yoo, Minjoon Seo

Comments Accepted to EMNLP 2023 main conference

2305.13631 2023-10-24 cs.CL cs.CV cs.IR

EDIS: Entity-Driven Image Search over Multimodal Web Content

Siqi Liu, Weixi Feng, Tsu-jui Fu, Wenhu Chen, William Yang Wang

Comments EMNLP 2023 camera ready version

2305.13477 2023-10-24 cs.CL

Look-back Decoding for Open-Ended Text Generation

Nan Xu, Chunting Zhou, Asli Celikyilmaz, Xuezhe Ma

Comments EMNLP 2023

2305.13469 2023-10-24 cs.CL cs.AI

MAILEX: Email Event and Argument Extraction

Saurabh Srivastava, Gaurav Singh, Shou Matsumoto, Ali Raz, Paulo Costa, Joshua Poore, Ziyu Yao

Comments Accepted at EMNLP 2023

2305.13085 2023-10-24 cs.CL

Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models

Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre, Ai Ti Aw, Nancy F. Chen

Comments EMNLP 2023 (Main, Long paper)

2305.12152 2023-10-24 cs.CL

Revisiting Automated Topic Model Evaluation with Large Language Models

Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan, Elliott Ash

Journal ref Forthcoming in EMNLP 2023

2305.11747 2023-10-24 cs.CL

HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models

Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen

Comments Accepted to EMNLP 2023 Main Conference (Long Paper)

2305.10434 2023-10-24 cs.CL cs.AI cs.LG

Learning the Visualness of Text Using Large Vision-Language Models

Gaurav Verma, Ryan A. Rossi, Christopher Tensmeyer, Jiuxiang Gu, Ani Nenkova

Comments Accepted at EMNLP 2023 (Main, long); 9 pages, 5 figures

2305.07988 2023-10-24 cs.CL

Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts

Haochen Tan, Han Wu, Wei Shao, Xinyun Zhang, Mingjie Zhan, Zhaohui Hou, Ding Liang, Linqi Song

Comments Accepted to EMNLP 2023 main conference

2305.07004 2023-10-24 cs.CL

Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting

Haoyang Huang, Tianyi Tang, Dongdong Zhang, Wayne Xin Zhao, Ting Song, Yan Xia, Furu Wei

Comments Accepted by EMNLP 2023 Findings

2305.06983 2023-10-24 cs.CL cs.LG

Active Retrieval Augmented Generation

Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig

Comments EMNLP 2023

2305.05471 2023-10-24 cs.CL

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good

Fernando Gonzalez, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan, Rada Mihalcea

Comments EMNLP 2023 Findings

2305.03276 2023-10-24 cs.CL

Expository Text Generation: Imitate, Retrieve, Paraphrase

Nishant Balepur, Jie Huang, Kevin Chen-Chuan Chang

Comments Accepted to EMNLP 2023 Main Conference

2305.02606 2023-10-24 cs.CL

Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training

Jiaxin Wen, Hao Zhou, Jian Guan, Minlie Huang

Comments EMNLP 2023 Main Coference

2305.02176 2023-10-24 cs.CL

Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity

Haoran Xu, Maha Elbayad, Kenton Murray, Jean Maillard, Vedanuj Goswami

Comments Accepted at Findings of EMNLP 2023

2305.01498 2023-10-24 cs.CL cs.AI

Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation

Miao Li, Eduard Hovy, Jey Han Lau

Comments Long paper; Accepted to EMNLP 2023; Soundness: 3, 3, 4; Excitement: 3, 4, 4

2305.00118 2023-10-24 cs.CL

Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4

Kent K. Chang, Mackenzie Cramer, Sandeep Soni, David Bamman

Comments EMNLP 2023 camera-ready (16 pages, 4 figures)

2304.11389 2023-10-24 cs.CL

Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens

Byung-Doh Oh, William Schuler

Comments Findings of the Association for Computational Linguistics: EMNLP 2023

2303.12528 2023-10-24 cs.CL

MEGA: Multilingual Evaluation of Generative AI

Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, Prachi Jain, Akshay Nambi, Tanuja Ganu, Sameer Segal, Maxamed Axmed, Kalika Bali, Sunayana Sitaram

Comments EMNLP 2023

2303.11315 2023-10-24 cs.CL

Context-faithful Prompting for Large Language Models

Wenxuan Zhou, Sheng Zhang, Hoifung Poon, Muhao Chen

Comments Accepted at EMNLP 2023 Findings. Code and data are released at https://github.com/wzhouad/context-faithful-llm

2303.01432 2023-10-24 cs.CL

WiCE: Real-World Entailment for Claims in Wikipedia

Ryo Kamoi, Tanya Goyal, Juan Diego Rodriguez, Greg Durrett

Comments EMNLP 2023

2302.06541 2023-10-24 cs.CL

Towards Agile Text Classifiers for Everyone

Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek, Muhamed Kouate, Nithum Thain, Ann Yuan, Tolga Bolukbasi, Lucas Dixon

Comments Findings of EMNLP 2023

2302.04858 2023-10-24 cs.CV cs.AI cs.CL cs.IR cs.LG

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Ming-Yu Liu, Yuke Zhu, Mohammad Shoeybi, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar

Comments Findings of EMNLP 2023

2302.00871 2023-10-24 cs.CL

Using In-Context Learning to Improve Dialogue Safety

Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür

Comments Findings of EMNLP 2023

2212.09702 2023-10-24 cs.CL cs.AI cs.LG

On Event Individuation for Document-Level Information Extraction

William Gantt, Reno Kriz, Yunmo Chen, Siddharth Vashishtha, Aaron Steven White

Comments EMNLP: Findings 2023

2211.11093 2023-10-24 cs.CL cs.AI

VER: Unifying Verbalizing Entities and Relations

Jie Huang, Kevin Chen-Chuan Chang

Comments EMNLP 2023 Findings

2211.08238 2023-10-24 cs.CL cs.AI

Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction

Leilei Gan, Baokui Li, Kun Kuang, Yating Zhang, Lei Wang, Luu Anh Tuan, Yi Yang, Fei Wu

Comments Accepted to Findings of EMNLP 2023

2210.15500 2023-10-24 cs.CL cs.CY cs.IR cs.LG

COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation

Nan Wang, Qifan Wang, Yi-Chia Wang, Maziar Sanjabi, Jingzhou Liu, Hamed Firooz, Hongning Wang, Shaoliang Nie

Comments This is a long paper accepted by the Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

2210.05261 2023-10-24 cs.CL cs.AI

Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling

Yuanhang Yang, Shiyi Qi, Chuanyi Liu, Qifan Wang, Cuiyun Gao, Zenglin Xu

Comments Accepted to EMNLP 2023