ACL

Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

Rongzhou Bao, Jiayi Wang, Hai Zhao

Comments Findings of ACL: ACL 2021

Structured Sentiment Analysis as Dependency Graph Parsing

Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid, Erik Velldal

Comments Accepted at ACL-IJCNLP 2021

CLEVE: Contrastive Pre-training for Event Extraction

Ziqi Wang, Xiaozhi Wang, Xu Han, Yankai Lin, Lei Hou, Zhiyuan Liu, Peng Li, Juanzi Li, Jie Zhou

Comments Accepted at ACL 2021

Pre-training Universal Language Representation

Yian Li, Hai Zhao

Comments Accepted by ACL-IJCNLP 2021 main conference

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation

Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao

Comments To appear at ACL 2021 main conference

NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation

Sungdong Kim, Minsuk Chang, Sang-Woo Lee

Comments Accepted to ACL 2021 as a long paper

Constructing Flow Graphs from Procedural Cybersecurity Texts

Kuntal Kumar Pal, Kazuaki Kashihara, Pratyay Banerjee, Swaroop Mishra, Ruoyu Wang, Chitta Baral

Comments 13 pages, 5 pages, accepted in the Findings of ACL 2021

Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

Yanan Wu, Zhiyuan Zeng, Keqing He, Hong Xu, Yuanmeng Yan, Huixing Jiang, Weiran Xu

Comments Accepted by ACL2021

Journal ref ACL2021

Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning

Zhiyuan Zeng, Keqing He, Yuanmeng Yan, Zijun Liu, Yanan Wu, Hong Xu, Huixing Jiang, Weiran Xu

Comments Accepted by ACL2021

Journal ref ACL2021

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

Linzi Xing, Wen Xiao, Giuseppe Carenini

Comments Accepted at ACL-IJCNLP 2021 main conference (short paper)

CoDesc: A Large Code-Description Parallel Dataset

Masum Hasan, Tanveer Muttaqueen, Abdullah Al Ishtiaq, Kazi Sajeed Mehrab, Md. Mahim Anjum Haque, Tahmid Hasan, Wasi Uddin Ahmad, Anindya Iqbal, Rifat Shahriyar

Comments Findings of the Association for Computational Linguistics, ACL 2021 (camera-ready)

Exploiting Position Bias for Robust Aspect Sentiment Classification

Fang Ma, Chen Zhang, Dawei Song

Comments 7 pages, 2 figures, 4 tables, accepted to Findings of ACL 2021. Repo: https://github.com/BD-MF/POS4ASC

Grammatical Error Correction as GAN-like Sequence Labeling

Kevin Parnow, Zuchao Li, Hai Zhao

Comments Accepted by ACL21, Findings

Multi-Label Few-Shot Learning for Aspect Category Detection

Mengting Hu, Shiwan Zhao, Honglei Guo, Chao Xue, Hang Gao, Tiegang Gao, Renhong Cheng, Zhong Su

Comments Accepted by ACL 2021 main conference

Towards More Equitable Question Answering Systems: How Much More Data Do You Need?

Arnab Debnath, Navid Rajabi, Fardina Fathmiul Alam, Antonios Anastasopoulos

Comments Accepted at ACL 2021

Contrastive Fine-tuning Improves Robustness for Neural Rankers

Xiaofei Ma, Cicero Nogueira dos Santos, Andrew O. Arnold

Journal ref Findings of ACL 2021

Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection

Shirong Shen, Tongtong Wu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari, Sheng Bi

Comments Accepted by ACL2021 Findings

Could you give me a hint? Generating inference graphs for defeasible reasoning

Aman Madaan, Dheeraj Rajagopal, Niket Tandon, Yiming Yang, Eduard Hovy

Comments Findings of the Association for Computational Linguistics: ACL 2021

Long-Span Summarization via Local Attention and Content Selection

Potsawee Manakul, Mark J. F. Gales

Comments ACL 2021 (camera-ready)

Dialogue Graph Modeling for Conversational Machine Reading

Siru Ouyang, Zhuosheng Zhang, Hai Zhao

Comments Findings of ACL: ACL 2021

Syntax-Enhanced Pre-trained Model

Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Nan Duan, Daxin Jiang

Comments Accepted by ACL-IJCNLP 2021: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction

Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Comments ACL 2021 main conference, 14 pages, 7 figures. Code will be released at https://github.com/amzn/refuel-open-domain-qa

A Sequence-to-Sequence Approach to Dialogue State Tracking

Yue Feng, Yang Wang, Hang Li

Comments Accepted by ACL 2021

Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments

Sreyan Ghosh, Sonal Kumar

Comments 9 pages, accepted at SemEval-2021 co-located with ACL-IJCNLP 2021

Changing the World by Changing the Data

Anna Rogers

Comments ACL 2021

Language Models Use Monotonicity to Assess NPI Licensing

Jaap Jumelet, Milica Denić, Jakub Szymanik, Dieuwke Hupkes, Shane Steinert-Threlkeld

Comments Published in ACL Findings 2021

How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation

Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi

Comments Accepted in Findings of ACL 2021

OTTers: One-turn Topic Transitions for Open-Domain Dialogue

Karin Sevegnani, David M. Howcroft, Ioannis Konstas, Verena Rieser

Journal ref ACL2021

Domain-Adaptive Pretraining Methods for Dialogue Understanding

Han Wu, Kun Xu, Linfeng Song, Lifeng Jin, Haisong Zhang, Linqi Song

Comments 6 pages, to appear in ACL2021

Data Augmentation for Text Generation Without Any Augmented Data

Wei Bi, Huayang Li, Jiacheng Huang

Comments Accepted into the main conference of ACL 2021