NoiseQA: Challenge Set Evaluation for User-Centric Question Answering

Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard Hovy, Alan W Black


Abstract
When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into a search engine, or even translating questions to languages supported by the QA system. While there has been significant community attention devoted to identifying correct answers in passages assuming a perfectly formed question, we show that components in the pipeline that precede an answering engine can introduce varied and considerable sources of error, and performance can degrade substantially based on these upstream noise sources even for powerful pre-trained QA models. We conclude that there is substantial room for progress before QA systems can be effectively deployed, highlight the need for QA evaluation to expand to consider real-world use, and hope that our findings will spur greater community interest in the issues that arise when our systems actually need to be of utility to humans.
Anthology ID:
2021.eacl-main.259
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2976–2992
Language:
URL:
https://aclanthology.org/2021.eacl-main.259
DOI:
10.18653/v1/2021.eacl-main.259
Bibkey:
Cite (ACL):
Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard Hovy, and Alan W Black. 2021. NoiseQA: Challenge Set Evaluation for User-Centric Question Answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2976–2992, Online. Association for Computational Linguistics.
Cite (Informal):
NoiseQA: Challenge Set Evaluation for User-Centric Question Answering (Ravichander et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.259.pdf
Dataset:
 2021.eacl-main.259.Dataset.zip
Code
 additional community code
Data
SQuADXQuAD