Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

Understand

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question.

• Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader.
• However, coreference is limited in providing information for rich inference.
• We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs.