Interactive Machine Comprehension with Information Seeking Agents
arXiv:1908.10449
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.
arXiv commentACL2020
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Prioritized Experience Replay
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Noisy Networks for Exploration
- Highway Networks
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Language Understanding for Text-based Games Using Deep Reinforcement Learning
- Neural Speed Reading via Skim-RNN
- What Makes Reading Comprehension Questions Easier?
- Interactive Language Learning by Question Answering
- Towards Information-Seeking Agents
- Learning to Search in Long Documents Using Document Structure
- Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data