Interactive Language Learning by Question Answering

Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually conc...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Yuan, Xingdi, Marc-Alexandre Cote, Fu, Jie, Lin, Zhouhan, Pal, Christopher, Bengio, Yoshua, Trischler, Adam
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 28.08.2019
Subjects
Machine learning
Pattern matching
Questions
Online AccessGet full text

Cover

More Information
Summary:Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.
ISSN:2331-8422