Interactive Machine Comprehension with Dynamic Knowledge Graphs
arXiv:2109.00077
Abstract
Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.
arXiv commentAccepted at EMNLP 2021
References in corpus (8)
- Playing Atari with Deep Reinforcement Learning
- Bidirectional Attention Flow for Machine Comprehension
- Agent57: Outperforming the Atari Human Benchmark
- Simple BERT Models for Relation Extraction and Semantic Role Labeling
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Counting to Explore and Generalize in Text-based Games
- Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
- Towards Information-Seeking Agents