EMNLP - arXivDaily 期刊&会议

2205.11416 2022-10-25 cs.CL

The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains

Haoran Xu, Philipp Koehn, Kenton Murray

Comments Accepted at EMNLP 2022

2205.11277 2022-10-25 cs.CL

When does Parameter-Efficient Transfer Learning Work for Machine Translation?

Ahmet Üstün, Asa Cooper Stickland

Comments Accepted at EMNLP 2022 (Main Conference)

2205.11024 2022-10-25 cs.CL

Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding

Rishabh Bhardwaj, Amrita Saha, Steven C. H. Hoi, Soujanya Poria

Comments EMNLP 2022

2205.10964 2022-10-25 cs.CL

The Geometry of Multilingual Language Model Representations

Tyler A. Chang, Zhuowen Tu, Benjamin K. Bergen

Comments Accepted to EMNLP 2022

2205.08232 2022-10-25 cs.AI cs.CL

LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning

Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Liang Lin, Xiaodan Liang

Journal ref Findings of EMNLP 2022

2205.03284 2022-10-25 cs.IR

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Xiaohua Li

Comments Accepted by EMNLP 2022

2204.14017 2022-10-25 cs.LG cs.AI cs.CL

Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling

KiYoon Yoo, Nojun Kwak

Comments Accepted to EMNLP 2022, 9 pages and Appendix

2204.13221 2022-10-25 cs.AI cs.LG

TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction

Yizhi Li, Wei Fan, Chao Liu, Chenghua Lin, Jiang Qian

Comments EMNLP 2022. v2 updated for EMNLP camera-ready

2204.13074 2022-10-25 cs.CL cs.AI

Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement

Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Clark

Comments accepted at EMNLP 2022

2204.07705 2022-10-25 cs.CL cs.AI

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi

Comments Accepted to EMNLP 2022, 25 pages

2204.05158 2022-10-25 cs.CL

Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems

Ella Rabinovich, Matan Vetzler, David Boaz, Vineet Kumar, Gaurav Pandey, Ateret Anaby-Tavor

Comments Accepted at EMNLP 2022 (industry track), 8 pages

2204.04058 2022-10-25 cs.CL

Improving Tokenisation by Alternative Treatment of Spaces

Edward Gow-Smith, Harish Tayyar Madabushi, Carolina Scarton, Aline Villavicencio

Comments EMNLP 2022

2203.08597 2022-10-25 cs.CL cs.AI cs.LG

Less is More: Summary of Long Instructions is Better for Program Synthesis

Kirby Kuznia, Swaroop Mishra, Mihir Parmar, Chitta Baral

Comments EMNLP 2022

2203.08383 2022-10-25 cs.CL

Iteratively Prompt Pre-trained Language Models for Chain of Thought

Boshi Wang, Xiang Deng, Huan Sun

Comments EMNLP-2022 Camera-Ready. Code will be available at https://github.com/sunlab-osu/IterPrompt

2203.08118 2022-10-25 cs.CL

Representation Learning for Resource-Constrained Keyphrase Generation

Di Wu, Wasi Uddin Ahmad, Sunipa Dev, Kai-Wei Chang

Comments EMNLP 2022 (Findings)

2203.04212 2022-10-25 cs.CL

Measuring the Mixing of Contextual Information in the Transformer

Javier Ferrando, Gerard I. Gállego, Marta R. Costa-jussà

Comments EMNLP 2022

2203.02700 2022-10-25 cs.SE cs.AI cs.LG

RACE: Retrieval-Augmented Commit Message Generation

Ensheng Shi, Yanlin Wang, Wei Tao, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, Hongbin Sun

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

2202.07962 2022-10-25 cs.CL

Revisiting Parameter-Efficient Tuning: Are We Really There Yet?

Guanzheng Chen, Fangyu Liu, Zaiqiao Meng, Shangsong Liang

Comments EMNLP 2022 main conference

2202.07922 2022-10-25 cs.CL cs.AI

ZeroGen: Efficient Zero-shot Learning via Dataset Generation

Jiacheng Ye, Jiahui Gao, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, Lingpeng Kong

Comments Accepted by EMNLP 2022 (Main Conference)

2201.11473 2022-10-25 cs.CL cs.AI cs.SC

Reasoning Like Program Executors

Xinyu Pi, Qian Liu, Bei Chen, Morteza Ziyadi, Zeqi Lin, Qiang Fu, Yan Gao, Jian-Guang Lou, Weizhu Chen

Comments To appear in EMNLP 2022 main conference. The first two authors contributed equally

2201.08193 2022-10-25 cs.CL cs.LG

TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack

Zhen Yu, Xiaosen Wang, Wanxiang Che, Kun He

Comments Accepted by EMNLP 2022 Findings, Code is available at https://github.com/JHL-HUST/TextHacker

2201.08081 2022-10-25 cs.CL

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training

Qi Shi, Qian Liu, Bei Chen, Yu Zhang, Ting Liu, Jian-Guang Lou

Comments EMNLP 2022 Findings

2201.05899 2022-10-25 cs.CL

Unobserved Local Structures Make Compositional Generalization Hard

Ben Bogin, Shivanshu Gupta, Jonathan Berant

Comments EMNLP 2022

2112.06204 2022-10-25 cs.CL

Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup

Yordan Yordanov, Vid Kocijan, Thomas Lukasiewicz, Oana-Maria Camburu

Comments Accepted to the EMNLP Findings 2022

2112.01476 2022-10-25 cs.CL

KPDrop: Improving Absent Keyphrase Generation

Jishnu Ray Chowdhury, Seoyeon Park, Tuhin Kundu, Cornelia Caragea

Comments Accepted in EMNLP Findings 2022

2012.15375 2022-10-25 cs.CL cs.AI

Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

Weiyan Shi, Yu Li, Saurav Sahay, Zhou Yu

Comments EMNLP 2021 Findings

2210.12112 2022-10-24 cs.CV cs.AI cs.CL

Describing Sets of Images with Textual-PCA

Oded Hupert, Idan Schwartz, Lior Wolf

Comments Accepted to Findings of EMNLP'22

2210.12079 2022-10-24 cs.CL cs.CV

Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?

Mitja Nikolaus, Emmanuelle Salin, Stephane Ayache, Abdellah Fourtassi, Benoit Favre

Comments To appear at EMNLP 2022

2210.12050 2022-10-24 cs.CL

Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards

Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Comments EMNLP 2022 (Findings)

2210.11933 2022-10-24 cs.CV

Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding

Yuechen Wang, Wengang Zhou, Houqiang Li

Comments 11 pages, 4 figures, accepted by Findings of EMNLP 2021