Papers › Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension...

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

6 Sep 2018arXiv:1809.02040archive 2025-07-28

Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, Daniel Gildea

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Hop Reading ComprehensionQuestion AnsweringReading Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering COMPLEXQUESTIONS MHQA F1 30.1 #2 of 2 Archive leaderboard report
Question Answering WikiHop MHQA Test 65.4 #6 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections