ACL - arXivDaily 期刊&会议

2212.10503 2023-07-06 cs.CL cs.LG

Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training

Kelly Marchisio, Patrick Lewis, Yihong Chen, Mikel Artetxe

Comments Findings of ACL 2023 Camera Ready

2210.10329 2023-07-06 cs.CL cs.AI

Language Detoxification with Attribute-Discriminative Latent Space

Jin Myung Kwak, Minseon Kim, Sung Ju Hwang

Comments ACL 2023; *Equal contribution. Author ordering determined by coin flip

2210.10209 2023-07-06 cs.CV cs.AI cs.CL cs.LG

Exclusive Supermask Subnetwork Training for Continual Learning

Prateek Yadav, Mohit Bansal

Comments ACL Findings 2023 (17 pages, 7 figures)

2201.12926 2023-07-06 cs.CL cs.CV cs.LG

Compositionality as Lexical Symmetry

Ekin Akyürek, Jacob Andreas

Comments ACL2023 Final Version

2307.01709 2023-07-06 cs.CL

Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting

Chen Chen, Yufei Wang, Aixin Sun, Bing Li, Kwok-Yan Lam

Comments Accepted by ACL 2023 Findings, Long Paper

2307.01640 2023-07-06 cs.CL

Chain of Thought Prompting Elicits Knowledge Augmentation

Dingjun Wu, Jing Zhang, Xinmei Huang

Comments Accepted by Findings of ACL 2023

2307.01595 2023-07-06 cs.CL cs.AI

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

Yingji Li, Mengnan Du, Xin Wang, Ying Wang

Comments has been accepted as ACL2023 main conference long paper

2307.01542 2023-07-06 cs.CL

Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation

Jian Guan, Minlie Huang

Comments ACL 2023 Short Findings

2307.01503 2023-07-06 cs.CL

On Evaluating and Mitigating Gender Biases in Multilingual Settings

Aniket Vashishtha, Kabir Ahuja, Sunayana Sitaram

Comments Accepted in ACL 2023 Findings

2307.01453 2023-07-06 cs.CL

Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking

Brendan King, Jeffrey Flanigan

Comments 14 pages, 2 figures, to appear in Findings of the ACL 2023

2307.01448 2023-07-06 cs.CL

ReactIE: Enhancing Chemical Reaction Extraction with Weak Supervision

Ming Zhong, Siru Ouyang, Minhao Jiang, Vivian Hu, Yizhu Jiao, Xuan Wang, Jiawei Han

Comments Findings of ACL 2023, Short Paper

2307.01381 2023-07-06 cs.CL cs.LG

Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation

Matthew Raffel, Lizhong Chen

Comments Accepted at Findings of ACL 2023

2307.01209 2023-07-06 cs.CL cs.LG cs.SI

Multi-Dialectal Representation Learning of Sinitic Phonology

Zhibai Jia

Comments Accepted by ACL 2023 Student Research Workshop

2306.03361 2023-07-06 cs.CL cs.AI

WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue

Deuksin Kwon, Sunwoo Lee, Ki Hyun Kim, Seojin Lee, Taeyoon Kim, Eric Davis

Comments Accepted in ACL 2023 Industry Track

2212.10549 2023-07-06 cs.CL cs.CV cs.LG

Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment

Rohan Pandey, Rulin Shao, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency

Comments ACL 2023

2305.18326 2023-07-04 cs.CV cs.AI

BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation

Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, Jinsong Su

Comments Accepted to ACL 2023 Findings

2212.10180 2023-07-04 cs.CL

IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages

Ananya B. Sai, Vignesh Nagarajan, Tanay Dixit, Raj Dabre, Anoop Kunchukuttan, Pratyush Kumar, Mitesh M. Khapra

Comments ACL 2023 long paper

2212.09683 2023-07-04 cs.CL

Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments

Ethan Mendes, Yang Chen, Wei Xu, Alan Ritter

Comments Accepted to ACL 2023 (main conference)

2205.00395 2023-07-04 cs.CL

ELQA: A Corpus of Metalinguistic Questions and Answers about English

Shabnam Behzad, Keisuke Sakaguchi, Nathan Schneider, Amir Zeldes

Comments Accepted to ACL 2023

2307.00569 2023-07-04 cs.CL

SSP: Self-Supervised Post-training for Conversational Search

Quan Tu, Shen Gao, Xiaolong Wu, Zhao Cao, Ji-Rong Wen, Rui Yan

Comments Accepted by ACL 2023 Findings, Long Paper

2307.00509 2023-07-04 cs.CL cs.AI cs.IR cs.LG

HeGeL: A Novel Dataset for Geo-Location from Hebrew Text

Tzuf Paz-Argaman, Tal Bauman, Itai Mondshine, Itzhak Omer, Sagi Dalyot, Reut Tsarfaty

Comments Accepted for ACL findings 2023

2307.00374 2023-07-04 cs.CL

Revisiting Sample Size Determination in Natural Language Understanding

Ernie Chang, Muhammad Hassan Rashid, Pin-Jie Lin, Changsheng Zhao, Vera Demberg, Yangyang Shi, Vikas Chandra

Comments Accepted to ACL 2023

2307.00119 2023-07-04 cs.CL

Meta-training with Demonstration Retrieval for Efficient Few-shot Learning

Aaron Mueller, Kanika Narang, Lambert Mathias, Qifan Wang, Hamed Firooz

Comments Accepted to Findings of ACL 2023

2307.00101 2023-07-04 cs.CL cs.AI

Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models

Harnoor Dhingra, Preetiha Jayashanker, Sayali Moghe, Emma Strubell

Comments Accepted to Queer in AI Workshop at ACL 2023

2306.02561 2023-07-04 cs.CL cs.AI cs.LG

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Dongfu Jiang, Xiang Ren, Bill Yuchen Lin

Comments Accepted to ACL 2023 (main conference); Project website: https://yuchenlin.xyz/LLM-Blender/ V3 update: fix a few typos and update a few citations; V2 update: The experiments on summarization, translation, and constrained generation tasks in the prior version have been moved to the appendix

2212.10511 2023-07-04 cs.CL cs.AI cs.LG

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, Hannaneh Hajishirzi

Comments ACL 2023; Code and data available at https://github.com/AlexTMallen/adaptive-retrieval

2205.12650 2023-07-04 cs.CL cs.IR

Few-shot Reranking for Multi-hop QA via Language Model Prompting

Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

Comments ACL 2023 - Camera Ready

2306.17757 2023-07-03 cs.CL

Should you marginalize over possible tokenizations?

Nadezhda Chirkova, Germán Kruszewski, Jos Rozen, Marc Dymetman

Comments Accepted to ACL 2023

2306.17674 2023-07-03 cs.CL

X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents

Mehrad Moradshahi, Tianhao Shen, Kalika Bali, Monojit Choudhury, Gaël de Chalendar, Anmol Goel, Sungkyun Kim, Prashant Kodali, Ponnurangam Kumaraguru, Nasredine Semmar, Sina J. Semnani, Jiwon Seo, Vivek Seshadri, Manish Shrivastava, Michael Sun, Aditya Yadavalli, Chaobin You, Deyi Xiong, Monica S. Lam

Comments Accepted by ACL 2023 Findings

2306.17472 2023-07-03 cs.CL

Knowledge Base Completion for Long-Tail Entities

Lihu Chen, Simon Razniewski, Gerhard Weikum

Comments In ACL23 (MATCHING workshop)