Interactive Machine Comprehension with Information Seeking Agents
This addresses the issue of limited scalability in MRC models for web-level QA scenarios, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of scaling machine reading comprehension (MRC) models to real-world applications like web-level information retrieval and question answering by reframing existing MRC datasets as interactive, partially observable environments, resulting in a method that trains models to seek relevant information through sequential decision making.
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.