English

Question Answering by Reasoning Across Documents with Graph Convolutional Networks

Computation and Language 2022-09-28 v4 Machine Learning

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).

Keywords

Cite

@article{arxiv.1808.09920,
  title  = {Question Answering by Reasoning Across Documents with Graph Convolutional Networks},
  author = {Nicola De Cao and Wilker Aziz and Ivan Titov},
  journal= {arXiv preprint arXiv:1808.09920},
  year   = {2022}
}
R2 v1 2026-06-23T03:48:12.765Z