Interactive Machine Comprehension with Information Seeking Agents

Xingdi Yuan, Jie Fu, Marc-Alexandre Côté, Yi Tay, Chris Pal, Adam Trischler


Abstract
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA). We argue that this stems from the nature of MRC datasets: most of these are static environments wherein the supporting documents and all necessary information are fully observed. In this paper, we propose a simple method that reframes existing MRC datasets as interactive, partially observable environments. Specifically, we “occlude” the majority of a document’s text and add context-sensitive commands that reveal “glimpses” of the hidden text to a model. We repurpose SQuAD and NewsQA as an initial case study, and then show how the interactive corpora can be used to train a model that seeks relevant information through sequential decision making. We believe that this setting can contribute in scaling models to web-level QA scenarios.
Anthology ID:
2020.acl-main.211
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2325–2338
Language:
URL:
https://aclanthology.org/2020.acl-main.211
DOI:
10.18653/v1/2020.acl-main.211
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.211.pdf
Video:
 http://slideslive.com/38929112
Code
 xingdi-eric-yuan/imrc_public
Data
NewsQA