ACL - arXivDaily 期刊&会议

2306.05083 2023-06-14 cs.CL

Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS

Cheng-Han Chiang, Yung-Sung Chuang, James Glass, Hung-yi Lee

Comments ACL 2023 repl4nlp (representation learning for NLP) workshop poster paper. Dataset at https://huggingface.co/datasets/dcml0714/Heros

2306.04551 2023-06-14 cs.CL cs.LG

Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning

Brihat Sharma, Yanjun Gao, Timothy Miller, Matthew M. Churpek, Majid Afshar, Dmitriy Dligach

Comments Accepted to the Proceedings of the 5th Clinical NLP Workshop at ACL

2305.14839 2023-06-14 cs.CL cs.CV

PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts

Yunshui Li, Binyuan Hui, ZhiChao Yin, Min Yang, Fei Huang, Yongbin Li

Comments ACL 2023

2305.02549 2023-06-14 cs.CL cs.CV cs.LG

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

Chen-Yu Lee, Chun-Liang Li, Hao Zhang, Timothy Dozat, Vincent Perot, Guolong Su, Xiang Zhang, Kihyuk Sohn, Nikolai Glushnev, Renshen Wang, Joshua Ainslie, Shangbang Long, Siyang Qin, Yasuhisa Fujii, Nan Hua, Tomas Pfister

Comments Accepted to ACL 2023

2304.02721 2023-06-14 cs.CL cs.AI

To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency

Daniel Campos, ChengXiang Zhai

Comments SustaiNLP2023 @ ACL 2023,9 pages, 6 figures, 33 tables

2212.10071 2023-06-14 cs.CL cs.AI cs.LG

Large Language Models Are Reasoning Teachers

Namgyu Ho, Laura Schmid, Se-Young Yun

Comments ACL 2023 camera-ready

2211.13892 2023-06-14 cs.CL

Complementary Explanations for Effective In-Context Learning

Xi Ye, Srinivasan Iyer, Asli Celikyilmaz, Ves Stoyanov, Greg Durrett, Ramakanth Pasunuru

Comments ACL Findings 2023 Camera-Ready

2210.16494 2023-06-14 cs.SE cs.AI cs.HC cs.PL

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu, Saleema Amershi

Comments Accepted at ACL 2023 (Findings)

2208.08232 2023-06-14 cs.CL cs.AI cs.CV cs.HC cs.LG

HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models

Swaroop Mishra, Elnaz Nouri

Comments ACL 2023 Findings

2110.01176 2023-06-14 cs.CL

Contextualized Semantic Distance between Highly Overlapped Texts

Letian Peng, Zuchao Li, Hai Zhao

Comments Accepted to ACL 2023 (findings)

2104.05596 2023-06-14 cs.CL

Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages

Gowtham Ramesh, Sumanth Doddapaneni, Aravinth Bheemaraj, Mayank Jobanputra, Raghavan AK, Ajitesh Sharma, Sujit Sahoo, Harshita Diddee, Mahalakshmi J, Divyanshu Kakwani, Navneet Kumar, Aswin Pradeep, Srihari Nagaraj, Kumar Deepak, Vivek Raghavan, Anoop Kunchukuttan, Pratyush Kumar, Mitesh Shantadevi Khapra

Comments Accepted to the Transactions of the Association for Computational Linguistics (TACL)

2306.07111 2023-06-13 cs.CL cs.AI cs.LG

Linear Classifier: An Often-Forgotten Baseline for Text Classification

Yu-Chen Lin, Si-An Chen, Jie-Jyun Liu, Chih-Jen Lin

Comments Accepted by ACL 2023

2306.07061 2023-06-13 cs.CL cs.AI cs.LG

Deep Model Compression Also Helps Models Capture Ambiguity

Hancheol Park, Jong C. Park

Comments ACL 2023

2306.07052 2023-06-13 cs.CL cs.AI

Gradient Ascent Post-training Enhances Language Model Generalization

Dongkeun Yoon, Joel Jang, Sungdong Kim, Minjoon Seo

Comments ACL 2023 Main Conference (Short Paper)

2306.06948 2023-06-13 cs.CL cs.AI

Rethinking Translation Memory Augmented Neural Machine Translation

Hongkun Hao, Guoping Huang, Lemao Liu, Zhirui Zhang, Shuming Shi, Rui Wang

Comments 15 pages, 2 figures, accepted by ACL2023 findings

2306.06941 2023-06-13 cs.CL

The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues

Anaïs Tack, Ekaterina Kochmar, Zheng Yuan, Serge Bibauw, Chris Piech

Comments to appear in the Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications, ACL 2023, Toronto, Canada

2306.06891 2023-06-13 cs.CL cs.AI

Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models

Soochan Lee, Gunhee Kim

Comments ACL 2023 (short, findings)

2306.06872 2023-06-13 cs.CL

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling

Hao Sun, Yang Li, Liwei Deng, Bowen Li, Binyuan Hui, Binhua Li, Yunshi Lan, Yan Zhang, Yongbin Li

Comments Accepted to ACL 2023 Main Conference

2305.19512 2023-06-13 cs.CL cs.AI cs.LG

Fine-grained Text Style Transfer with Diffusion-Based Language Models

Yiwei Lyu, Tiange Luo, Jiacheng Shi, Todd C. Hollon, Honglak Lee

Comments Accepted at Repl4NLP workshop at ACL 2023

2305.19344 2023-06-13 cs.CL

infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information

Jaehyung Kim, Yekyung Kim, Karin de Langis, Jinwoo Shin, Dongyeop Kang

Comments 26 pages, accepted at ACL 2023 conference as a full paper

2305.17682 2023-06-13 cs.CL cs.AI

One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning

Guangtao Zeng, Peiyuan Zhang, Wei Lu

Comments Accepted by ACL 2023

2305.17506 2023-06-13 cs.SE cs.AI cs.CL

Backdooring Neural Code Search

Weisong Sun, Yuchen Chen, Guanhong Tao, Chunrong Fang, Xiangyu Zhang, Quanjun Zhang, Bin Luo

Comments Accepted to the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)

2305.13592 2023-06-13 cs.LG cs.AI cs.CL cs.CR cs.SE

Understanding Programs by Exploiting (Fuzzing) Test Cases

Jianyu Zhao, Yuyang Rong, Yiwen Guo, Yifeng He, Hao Chen

Comments Findings of the Association for Computational Linguistics: ACL 2023; fix typos and update results to keep the same settings in all experiments

2212.10563 2023-06-13 cs.CL

BLIND: Bias Removal With No Demographics

Hadas Orgad, Yonatan Belinkov

Comments Accepted to ACL 2023 main conference

2212.09097 2023-06-13 cs.CL

Continual Knowledge Distillation for Neural Machine Translation

Yuanchi Zhang, Peng Li, Maosong Sun, Yang Liu

Comments Accepted to ACL 2023. The source code is available at https://github.com/THUNLP-MT/CKD

2210.06629 2023-06-13 cs.CL

Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis

Siddharth Varia, Shuai Wang, Kishaloy Halder, Robert Vacareanu, Miguel Ballesteros, Yassine Benajiba, Neha Anna John, Rishita Anubhai, Smaranda Muresan, Dan Roth

Comments Camera ready copy for WASSA at ACL 2023

2206.00621 2023-06-13 cs.CL cs.AI cs.CV cs.LG

Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training

Yan Zeng, Wangchunshu Zhou, Ao Luo, Ziming Cheng, Xinsong Zhang

Comments ACL 2023

2306.06779 2023-06-13 cs.CL

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

Hai Ye, Qizhe Xie, Hwee Tou Ng

Comments Main conference of ACL 2023

2306.06629 2023-06-13 cs.CL cs.AI

GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model

Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Yang Yang, Hongyin Tang, Keqing He, Jiahao Liu, Jingang Wang, Shu Zhao, Peng Zhang, Jie Tang

Comments accepted for ACL 2023 industry track

2306.06625 2023-06-13 cs.CL cs.AI

Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method

Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Shu Zhao, Peng Zhang, Jie Tang

Comments Accepted to Findings of ACL2023