The 3rd Workshop on Machine Reading for Question Answering

Workshop at EMNLP 2021
Date: November 10, 2021
Format: Hybrid (Online + "Bavaro 2"")

Accepted Papers

Following papers are accepted to MRQA 2021. Multilingual, Interpretability and Research track papers appear in the proceedings of the workshop, while non-archival papers are not be included (but are given opportunity to present in the workshop). Papers from EMNLP Findings presented in MRQA are also below.

Multilingual Track

GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval
Timo Möller, Julian Risch and Malte Pietsch

Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer
Ziqing Yang, Wentao Ma, Yiming Cui, Jiani Ye, Wanxiang Che and Shijin Wang

ParaShoot: A Hebrew Question Answering Dataset
Omri Keren and Omer Levy

Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering
Fahim Faisal and Antonios Anastasopoulos

MFAQ: a Multilingual FAQ Dataset
Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann and Walter Daelemans

Interpretability Track

Eliciting Bias in Question Answering Models through Ambiguity
Andrew Mao, Naveen J. Raman, Matthew Shu, Eric Li, Franklin Yang and Jordan Boyd-Graber

What Would it Take to get Biomedical QA Systems into Practice?
Gregory Kell, Iain Marshall, Byron Wallace and Andre Jaun

Research Track

Rethinking the Objectives of Extractive Question Answering
Martin Fajcik, Josef Jon and Pavel Smrz

Zero-Shot Clinical Questionnaire Filling From Human-Machine Interactions
Farnaz Ghassemi Toudeshki, Philippe Jolivet, Alexandre Durand-Salmon and Anna Liednikova

Can Question Generation Debias Question Answering Models? A Case Study on Question–Context Lexical Overlap
Kazutoshi Shinoda, Saku Sugawara and Akiko Aizawa

What Can a Generative Language Model Answer About a Passage?
Douglas Summers-Stay, Claire Bonial and Clare Voss

Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models
Bogdan Kostić, Julian Risch and Timo Möller

Unsupervised Multiple Choices Question Answering: Start Learning from Basic Knowledge
Chi-Liang Liu and Hung-yi Lee

GANDALF: a General Character Name Description Dataset for Long Fiction
Fredrik Carlsson, Magnus Sahlgren, Fredrik Olsson and Amaru Cuba Gyllensten

Semantic Answer Similarity for Evaluating Question Answering Models
Julian Risch, Timo Möller, Julian Gutsch and Malte Pietsch

Simple and Efficient ways to Improve REALM
Vidhisha Balachandran, Ashish Vaswani, Yulia Tsvetkov and Niki Parmar

Non-Archival Track

Synthetic Target Domain Supervision for Open Retrieval QA
Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan, Rong Zhang, Avirup Sil, Vittorio Castelli, Radu Florian and Salim Roukos
Published at SIGIR 2021

Entity-based Knowledge Conflicts in Question Answering
Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris Dubois and Sameer Singh
Published at EMNLP 2021

Mitigating False-Negative Contexts in Multi-Document Question Answering with Retrieval Marginalization
Ansong Ni, Matt Gardner and Pradeep Dasigi
Published at EMNLP 2021

Generative Context Pair Selection for Multi-hop Question Answering
Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner and Sameer Singh
Published at EMNLP 2021

Learning with Instance Bundles for Reading Comprehension
Dheeru Dua, Pradeep Dasigi, Sameer Singh and Matt Gardner
Published at EMNLP 2021

Knowing More About Questions Can Help: Improving Calibration in Question Answering
Shujian Zhang, Chengyue Gong and Eunsol Choi
Published at ACL 2021 Findings

RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu and Haifeng Wang
Published at NAACL 2021

Weakly Supervised Pre-Training for Multi-Hop Retriever
Yeon Seonwoo, Sang-Woo Lee, Ji-Hoon Kim, Jung-Woo Ha and Alice Oh
Published at ACL 2021 Findings

ReasonBert: Pre-trained to Reason with Distant Supervision
Xiang Deng, Yu Su, Alyssa Lees, You Wu, Cong Yu and Huan Sun
Published at ACL 2021

EMNLP Findings

Can NLI Models Verify QA Systems’ Predictions?
Jifan Chen, Eunsol Choi and Greg Durrett
Published at EMNLP 2021 Findings

Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework
Abhilash Nandy, Soumya Sharma, Shubham Maddhashiya, Kapil Sachdeva, Pawan Goyal and NIloy Ganguly
Published at EMNLP 2021 Findings

Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0
Elior Sulem, Jamaal Hay and Dan Roth
Published at EMNLP 2021 Findings

Relation-Guided Pre-Training for Open-Domain Question Answering
Ziniu Hu, Yizhou Sun and Kai-Wei Chang
Published at EMNLP 2021 Findings

Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization
Akhil Kedia, Sai Chetan Chinthakindi and Wonho Ryu
Published at EMNLP 2021 Findings

SD-QA: Spoken Dialectal Question Answering for the Real World
Fahim Faisal, Sharlina Keshava, Md Mahfuz Ibn Alam and Antonios Anastasopoulos
Published at EMNLP 2021 Findings

When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions
ZiXian Huang, Ao Wu, Yulin Shen, Gong Cheng and Yuzhong Qu
Published at EMNLP 2021 Findings

Winnowing Knowledge for Multi-choice Question Answering
Yeqiu Li, Bowei Zou, Zhifeng Li, Ai Ti Aw, Yu Hong and Qiaoming Zhu
Published at EMNLP 2021 Findings

Extract, Integrate, Compete: Towards Verification Style Reading Comprehension
Chen Zhang, Yuxuan Lai, Yansong Feng and Dongyan Zhao
Published at EMNLP 2021 Findings

Reference-based Weak Supervision for Answer Sentence Selection using Web Data
Vivek Krishnamurthy, Thuy Vu and Alessandro Moschitti
Published at EMNLP 2021 Findings

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
Qiyuan Zhang, Lei Wang, SICHENG YU, Shuohang Wang, Yang Wang, Jing Jiang and Ee-Peng Lim
Published at EMNLP 2021 Findings

Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text
Xiao-Yu Guo, Yuan-Fang Li and Gholamreza Haffari
Published at EMNLP 2021 Findings

R2-D2: A Modular Baseline for Open-Domain Question Answering
Martin Fajcik, Martin Docekal, Karel Ondrej and Pavel Smrz
Published at EMNLP 2021 Findings

AutoEQA: Auto-Encoding Questions for Extractive Question Answering
Stalin Varanasi, Saadullah Amin and Guenter Neumann
Published at EMNLP 2021 Findings