ACL - arXivDaily 期刊&会议

2210.00185 2023-05-24 cs.CL

Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks

Zhenhailong Wang, Xiaoman Pan, Dian Yu, Dong Yu, Jianshu Chen, Heng Ji

Comments Accepted as a conference paper at Findings of ACL 2023

2305.13299 2023-05-23 cs.CL cs.AI cs.LG

Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations

Chenglei Si, Dan Friedman, Nitish Joshi, Shi Feng, Danqi Chen, He He

Comments ACL 2023

2305.13298 2023-05-23 cs.CL

DiffusionNER: Boundary Diffusion for Named Entity Recognition

Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang

Comments Accepted to ACL 2023, submission version

2305.13282 2023-05-23 cs.CL cs.LG

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection

Rheeya Uppaal, Junjie Hu, Yixuan Li

Comments Accepted to ACL 2023

2305.13142 2023-05-23 cs.CL

Better Sampling of Negatives for Distantly Supervised Named Entity Recognition

Lu Xu, Lidong Bing, Wei Lu

Comments Accepted by ACL Findings 2023

2305.13076 2023-05-23 cs.CL

An Abstract Specification of VoxML as an Annotation Language

Kiyong Lee, Nikhil Krishnaswamy, James Pustejovsky

Comments 8 pages, 4 figures, Proceedings of 19th Joint ISO-ACL Workshop on Interoperable Semantic Annotation (ISA 2023)

2305.13002 2023-05-23 cs.CL cs.AI cs.LG

Rethinking Semi-supervised Learning with Language Models

Zhengxiang Shi, Francesco Tonolini, Nikolaos Aletras, Emine Yilmaz, Gabriella Kazai, Yunlong Jiao

Comments Findings of ACL 2023. Code is available at https://github.com/amzn/pretraining-or-self-training

2305.13000 2023-05-23 cs.CL

Bidirectional Transformer Reranker for Grammatical Error Correction

Ying Zhang, Hidetaka Kamigaito, Manabu Okumura

Comments Accepted to the Findings of ACL 2023

2305.12941 2023-05-23 cs.CL cs.NE

On the Correspondence between Compositionality and Imitation in Emergent Neural Communication

Emily Cheng, Mathieu Rita, Thierry Poibeau

Comments Findings of ACL 2023; 5 pages + 8 pages of supplementary materials

2305.12927 2023-05-23 cs.CL cs.SD eess.AS

Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization

Luyao Cheng, Siqi Zheng, Zhang Qinglin, Hui Wang, Yafeng Chen, Qian Chen

Comments Accepted to Findings of ACL 2023

2305.12880 2023-05-23 cs.CV cs.CL

Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive Teachers

Philipp Sadler, Sherzod Hakimov, David Schlangen

Comments 5 pages, Accepted at Findings of ACL 2023

2305.12816 2023-05-23 cs.CL

Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model

Xiao Wang, Weikang Zhou, Qi Zhang, Jie Zhou, Songyang Gao, Junzhe Wang, Menghan Zhang, Xiang Gao, Yunwen Chen, Tao Gui

Comments Accepted by ACL2023

2305.12792 2023-05-23 cs.CL cs.AI

Semantic Structure Enhanced Event Causality Identification

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Comments Accepted at ACL 2023

2305.12782 2023-05-23 cs.CL cs.AI

Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization

Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, Kam-Fai Wong

Comments ACL 2023

2305.12777 2023-05-23 cs.CL

Evaluating Pragmatic Abilities of Image Captioners on A3DS

Polina Tsvilodub, Michael Franke

Comments 5 pages, 2 figures, to appear in the 61st Proceedings of the Association for Computational Linguistics (ACL 2023)

2305.12761 2023-05-23 cs.CL cs.AI

Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer

Shuang Li, Xuming Hu, Aiwei Liu, Yawen Yang, Fukun Ma, Philip S. Yu, Lijie Wen

Comments Accept at ACL2023

2305.12757 2023-05-23 cs.CL

This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models

Seraphina Goldfarb-Tarrant, Eddie Ungless, Esma Balkir, Su Lin Blodgett

Comments Accepted to ACL Findings 2023

2305.12753 2023-05-23 cs.CL cs.AI

Learning to Rank Utterances for Query-Focused Meeting Summarization

Xingxian Liu, Yajing Xu

Comments Accepted by Findings of ACL 2023

2305.12749 2023-05-23 cs.CL

A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches

Zihan Wang, Tianle Wang, Dheeraj Mekala, Jingbo Shang

Comments ACL 2023 Findings

2305.12744 2023-05-23 cs.CL cs.AI

Fact-Checking Complex Claims with Program-Guided Reasoning

Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov

Comments ACL 2023 (main conference, long paper)

2305.12737 2023-05-23 cs.CL cs.AI

The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning

Zhuang Li, Lizhen Qu, Philip R. Cohen, Raj V. Tumuluri, Gholamreza Haffari

Comments ACL 2023

2305.12717 2023-05-23 cs.CL cs.LG

TADA: Efficient Task-Agnostic Domain Adaptation for Transformers

Chia-Chien Hung, Lukas Lange, Jannik Strötgen

Comments ACL-Findings 2023

2305.12692 2023-05-23 cs.CL cs.AI

MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning

Zhenrui Yue, Huimin Zeng, Yang Zhang, Lanyu Shang, Dong Wang

Comments Accepted to ACL 2023

2305.12628 2023-05-23 cs.CL cs.LG cs.SD eess.AS

Duplex Diffusion Models Improve Speech-to-Speech Translation

Xianchao Wu

Comments 11 pages, 3 figures. Accepted by ACL 2023 findings

2305.12627 2023-05-23 cs.CL cs.AI

MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction

Zhibin Gou, Qingyan Guo, Yujiu Yang

Comments Accepted to ACL 2023 Main Conference

2305.12376 2023-05-23 cs.CL cs.CY cs.LG

Measuring Intersectional Biases in Historical Documents

Nadav Borenstein, Karolina Stańczak, Thea Rolskov, Natália da Silva Perez, Natacha Klein Käfer, Isabelle Augenstein

Comments Accepted to Findings of ACL2023

2305.09210 2023-05-23 cs.CL

Towards Speech Dialogue Translation Mediating Speakers of Different Languages

Shuichiro Shimizu, Chenhui Chu, Sheng Li, Sadao Kurohashi

Comments 11 pages, 4 figures. Accepted to ACL 2023 Findings. Dataset: https://github.com/ku-nlp/speechBSD

2305.03117 2023-05-23 cs.CL

Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations

Bingsheng Yao, Prithviraj Sen, Lucian Popa, James Hendler, Dakuo Wang

Comments Accepted to ACL2023

2212.06711 2023-05-23 cs.CL cs.CY

On Text-based Personality Computing: Challenges and Future Directions

Qixiang Fang, Anastasia Giachanou, Ayoub Bagheri, Laura Boeschoten, Erik-Jan van Kesteren, Mahdi Shafiee Kamalabad, Daniel L Oberski

Comments Findings of ACL 2023. Long paper

2211.08073 2023-05-23 cs.CL cs.AI cs.LG cs.PF

GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective

Linyi Yang, Shuibai Zhang, Libo Qin, Yafu Li, Yidong Wang, Hanmeng Liu, Jindong Wang, Xing Xie, Yue Zhang

Comments Accepted to ACL-23 Findings