NAACL

Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach

Yue Yu, Simiao Zuo, Haoming Jiang, Wendi Ren, Tuo Zhao, Chao Zhang

Comments NAACL-HLT 2021. Code: \url{https://github.com/yueyu1030/COSINE}

Journal ref NAACL-HLT 2021

Industry Scale Semi-Supervised Learning for Natural Language Understanding

Luoxin Chen, Francisco Garcia, Varun Kumar, He Xie, Jianhua Lu

Comments NAACL 2021 Industry track

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

Wenkai Yang, Lei Li, Zhiyuan Zhang, Xuancheng Ren, Xu Sun, Bin He

Comments NAACL-HLT 2021, Long Paper

Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks

Minh Van Nguyen, Viet Dac Lai, Thien Huu Nguyen

Comments Accepted at NAACL-HLT 2021

NL-EDIT: Correcting semantic parse errors through natural language interaction

Ahmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Hassan Awadallah

Comments NAACL 2021

Mask Attention Networks: Rethinking and Strengthen Transformer

Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang

Comments Accepted as a long paper to NAACL 2021

Controlling Dialogue Generation with Semantic Exemplars

Prakhar Gupta, Jeffrey P. Bigham, Yulia Tsvetkov, Amy Pavel

Comments Accepted at NAACL 2021

Representing Numbers in NLP: a Survey and a Vision

Avijit Thawani, Jay Pujara, Pedro A. Szekely, Filip Ilievski

Comments Accepted at NAACL 2021

Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases

Ilias Chalkidis, Manos Fergadiotis, Dimitrios Tsarapatsanis, Nikolaos Aletras, Ion Androutsopoulos, Prodromos Malakasiotis

Comments 9 pages, long paper at NAACL 2021 proceedings

Modeling the Severity of Complaints in Social Media

Mali Jin, Nikolaos Aletras

Comments Accepted at NAACL 2021

A Frustratingly Easy Approach for Entity and Relation Extraction

Zexuan Zhong, Danqi Chen

Comments NAACL 2021. Our code and models are available at https://github.com/princeton-nlp/PURE

Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification

Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, Bowen Zhou

Comments Accepted by NAACL 2021

Non-Autoregressive Translation by Learning Target Categorical Codes

Yu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen

Comments 11 pages, 3 figures, 7 tables. Accepted by NAACL-2021

Self-Supervised Test-Time Learning for Reading Comprehension

Pratyay Banerjee, Tejas Gokhale, Chitta Baral

Comments Accepted to NAACL 2021

TextEssence: A Tool for Interactive Analysis of Semantic Shifts Between Corpora

Denis Newman-Griffis, Venkatesh Sivaraman, Adam Perer, Eric Fosler-Lussier, Harry Hochheiser

Comments Accepted as a Systems Demonstration at NAACL-HLT 2021. Video demonstration at https://youtu.be/1xEEfsMwL0k

Masked Conditional Random Fields for Sequence Labeling

Tianwen Wei, Jianwei Qi, Shenghuan He, Songtao Sun

Comments accepted by NAACL 2021

Smoothing and Shrinking the Sparse Seq2Seq Search Space

Ben Peters, André F. T. Martins

Comments NAACL 2021

Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA

Yonatan Bitton, Gabriel Stanovsky, Roy Schwartz, Michael Elhadad

Comments Accepted to NAACL 2021

Towards Few-Shot Fact-Checking via Perplexity

Nayeon Lee, Yejin Bang, Andrea Madotto, Madian Khabsa, Pascale Fung

Comments Accpeted to NAACL'21

Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence

Tal Schuster, Adam Fisch, Regina Barzilay

Comments NAACL 2021

ReinforceBug: A Framework to Generate Adversarial Textual Examples

Bushra Sabir, M. Ali Babar, Raj Gaire

Comments Accepted in NAACL-HLT 2021

Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training

Oshin Agarwal, Heming Ge, Siamak Shakeri, Rami Al-Rfou

Comments Accepted at NAACL 2021

Pre-training with Meta Learning for Chinese Word Segmentation

Zhen Ke, Liang Shi, Songtao Sun, Erli Meng, Bin Wang, Xipeng Qiu

Comments Accepted by NAACL 2021

SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding

Yu-An Chung, Chenguang Zhu, Michael Zeng

Journal ref North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2021. North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2021

Contextualized Perturbation for Textual Adversarial Attack

Dianqi Li, Yizhe Zhang, Hao Peng, Liqun Chen, Chris Brockett, Ming-Ting Sun, Bill Dolan

Comments Accepted by NAACL 2021, long paper

Enhancing Factual Consistency of Abstractive Summarization

Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang

Comments Prediction results available at: https://github.com/zcgzcgzcg1/FASum/

Journal ref North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2021

Human vs Automatic Metrics: on the Importance of Correlation Design

Anastasia Shimorina

Comments accepted for the WiNLP workshop at NAACL 2018; 3 pages

MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization

Chenguang Zhu, Yang Liu, Jie Mei, Michael Zeng

Comments Dataset: https://github.com/zcgzcgzcg1/MediaSum/

Journal ref North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2021

Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages

Xavier Garcia, Aditya Siddhant, Orhan Firat, Ankur P. Parikh

Comments Accepted to NAACL 2021

Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution

Xavier Garcia, Noah Constant, Ankur P. Parikh, Orhan Firat

Comments Accepted at NAACL 2021