EMNLP

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack

Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao

Comments Accepted by EMNLP 2022 (long), 9 pages main + 2 pages references + 7 pages appendix

Truncation Sampling as Language Model Desmoothing

John Hewitt, Christopher D. Manning, Percy Liang

Comments Findings of EMNLP, + small fixes

Dictionary-Assisted Supervised Contrastive Learning

Patrick Y. Wu, Richard Bonneau, Joshua A. Tucker, Jonathan Nagler

Comments 6 pages, 5 figures, EMNLP 2022

Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems

Wang Zhu, Jesse Thomason, Robin Jia

Comments Accepted by the Findings of EMNLP 2022

FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning

Suvir Mirchandani, Licheng Yu, Mengjiao Wang, Animesh Sinha, Wenwen Jiang, Tao Xiang, Ning Zhang

Comments 14 pages, 4 figures. To appear at Conference on Empirical Methods in Natural Language Processing (EMNLP) 2022

Robust Domain Adaptation for Pre-trained Multilingual Neural Machine Translation Models

Mathieu Grosso, Pirashanth Ratnamogan, Alexis Mathey, William Vanhuffel, Michael Fotso Fotso

Comments Accepted by EMNLP 2022 MMNLU Workshop

MABEL: Attenuating Gender Bias using Textual Entailment Data

Jacqueline He, Mengzhou Xia, Christiane Fellbaum, Danqi Chen

Comments Accepted to EMNLP 2022. Code and models are publicly available at https://github.com/princeton-nlp/mabel

Language Model Pre-Training with Sparse Latent Typing

Liliang Ren, Zixuan Zhang, Han Wang, Clare R. Voss, Chengxiang Zhai, Heng Ji

Comments EMNLP 2022 (Oral)

Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models

Mengzhou Xia, Mikel Artetxe, Jingfei Du, Danqi Chen, Ves Stoyanov

Comments Accepted to EMNLP 2022; The code is available at https://github.com/facebookresearch/ELECTRA-Fewshot-Learning

Is a Question Decomposition Unit All We Need?

Pruthvi Patel, Swaroop Mishra, Mihir Parmar, Chitta Baral

Comments EMNLP 2022 (17 pages)

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models

Weiyan Shi, Ryan Shea, Si Chen, Chiyuan Zhang, Ruoxi Jia, Zhou Yu

Comments EMNLP 2022

Reproducibility Issues for BERT-based Evaluation Metrics

Yanran Chen, Jonas Belouadi, Steffen Eger

Comments EMNLP 2022 Camera-Ready (captions fixed)

IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages

Aman Kumar, Himani Shrotriya, Prachi Sahu, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Amogh Mishra, Mitesh M. Khapra, Pratyush Kumar

Comments Accepted at EMNLP 2022

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation

Raymond Li, Wen Xiao, Linzi Xing, Lanjun Wang, Gabriel Murray, Giuseppe Carenini

Comments 16 pages, 4 figures, Camera-Ready for EMNLP 2022 (Long Paper)

On the Curious Case of $\ell_2$ norm of Sense Embeddings

Yi Zhou, Danushka Bollegala

Comments Accepted to Findings of EMNLP 2022

BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Mohaddeseh Bastan, Mihai Surdeanu, Niranjan Balasubramanian

Comments Accepted to Findings of EMNLP 2022, Data and evaluation suite available at https://stonybrooknlp.github.io/BioNLI/

Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models

Mozes van de Kar, Mengzhou Xia, Danqi Chen, Mikel Artetxe

Comments EMNLP 2022

Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks

Colin Leong, Joshua Nemecek, Jacob Mansdorfer, Anna Filighera, Abraham Owodunni, Daniel Whitenack

Comments 14 pages, 1 figure, 3 tables, accepted to and presented at EMNLP 2022

Journal ref EMNLP 2022

MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective

Zhe Hu, Hou Pong Chan, Lifu Huang

Comments Accepted at EMNLP 2022

Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator

Qinyuan Cheng, Linyang Li, Guofeng Quan, Feng Gao, Xiaofeng Mou, Xipeng Qiu

Comments Accepted by Findings of EMNLP 2022

Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding

Md Mosharaf Hossain, Eduardo Blanco

Comments To appear at the main conference of EMNLP 2022

Benchmarking Language Models for Code Syntax Understanding

Da Shen, Xinyun Chen, Chenguang Wang, Koushik Sen, Dawn Song

Comments Findings of EMNLP 2022

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning

Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur

Comments To appear in EMNLP 2022. Code is available at https://github.com/ychen-stat-ml/kernel-adapters

ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select

Yuchen Zhuang, Yinghao Li, Jerry Junyang Cheung, Yue Yu, Yingjun Mou, Xiang Chen, Le Song, Chao Zhang

Comments Accepted to EMNLP 2022

Geographic Citation Gaps in NLP Research

Mukund Rungta, Janvijay Singh, Saif M. Mohammad, Diyi Yang

Comments EMNLP 2022 Main Conference

Progressive Sentiment Analysis for Code-Switched Text Data

Sudhanshu Ranjan, Dheeraj Mekala, Jingbo Shang

Comments To appear in Findings of EMNLP 2022

Deploying a Retrieval based Response Model for Task Oriented Dialogues

Lahari Poddar, György Szarvas, Cheng Wang, Jorge Balazs, Pavel Danchenko, Patrick Ernst

Comments Accepted at EMNLP 2022

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport

Kelly Marchisio, Ali Saad-Eldin, Kevin Duh, Carey Priebe, Philipp Koehn

Comments EMNLP 2022 Camera-Ready

Differentially Private Language Models for Secure Data Sharing

Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schoelkopf, Mrinmaya Sachan

Comments Accepted at EMNLP 2022

Multilingual Relation Classification via Efficient and Effective Prompting

Yuxuan Chen, David Harbecke, Leonhard Hennig

Comments EMNLP 2022