# Question Answering by Reasoning Across Documents with Graph Convolutional Networks Source: [Question Answering by Reasoning Across Documents with Graph Convolutional Networks]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:55.415Z Authors: Nicola De Cao, Wilker Aziz, Ivan Titov Published: 2018-08-29T16:44:51.000Z ## Abstract Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentions of entities are nodes of this graph while edges encode relations between different mentions (e.g., within- and cross-document co-reference). Graph convolutional networks (GCNs) are applied to these graphs and trained to perform multi-step reasoning. Our Entity-GCN method is scalable and compact, and it achieves state-of-the-art results on a multi-document question answering dataset, WikiHop (Welbl et al., 2018). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-hop Reading Comprehension on WikiHop unmasked (dev)](): Multi-hop Reading Comprehension; WikiHop unmasked (dev); Accuracy: 64.8. - [Multi-hop Reading Comprehension on WikiHop unmasked (test)](): Multi-hop Reading Comprehension; WikiHop unmasked (test); Accuracy: 67.6. - [Multi-hop Question Answering on WikiHop masked (dev)](): Multi-hop Question Answering; WikiHop masked (dev); Accuracy: 70.5. ## Original sources and implementation [Original paper]() [PDF]()