Multi-hop Evidence Retrieval for Cross-document Relation Extraction

• Published in: arXiv.org
• Main Authors: Lu, Keming, I-Hung, Hsu, Zhou, Wenxuan, Ma, Mingyu Derek, Chen, Muhao
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 05.06.2023
• Subjects: Computer Science - Computation and Language; Computer Science - Information Retrieval; Computer Science - Learning; Documents; Reasoning; Retrieval
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2212.10786

Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations, along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose MR.COD (Multi-hop evidence retrieval for Cross-document relation extraction), which is a multi-hop evidence retrieval method based on evidence path mining and ranking. We explore multiple variants of retrievers to show evidence retrieval is essential in cross-document RE. We also propose a contextual dense retriever for this setting. Experiments on CodRED show that evidence retrieval with MR.COD effectively acquires crossdocument evidence and boosts end-to-end RE performance in both closed and open settings.