Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
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. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Hop Reading ComprehensionQuestion AnsweringReading ComprehensionSimilar Papers 제목 키워드 기반
Exploiting Explicit Paths for Multi-hop Reading Comprehension
We propose a novel, path-based reasoning approach for the multi-hop reading comprehension task where a system needs to combine facts from multiple passages to answer a question. Although inspired by multi-hop reasoning o…
Implicit RelationsKnowledge GraphsMulti-Hop Reading ComprehensionReading ComprehensionIdentifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, complex Question Answering (QA) typically req…
Multi-hop Question AnsweringQuestion AnsweringReading ComprehensionHKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
Multi-hop RAG poses a data-engineering problem beyond passage matching: under fixed retrieval budgets, a system must organize retrieved text into evidence units that expose answer chains. Dense retrievers score passages …
Lotte and Annette: A Framework for Finding and Exploring Key Passages in Literary Works
We present an approach that leverages expert knowledge contained in scholarly works to automatically identify key passages in literary works. Specifically, we extend a text reuse detection method for finding quotations, …
GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering
Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these systems with knowledge graphs for structured traversal, but this combi…
Multi-hop Question AnsweringPassage RetrievalKnowledge Graphs