Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

About

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.

Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma, Muhao Chen• 2022

Related benchmarks

TaskDatasetResultRank
Document-level Relation ExtractionCodRED Closed (test)
F1 Score62.53
8
Document-level Relation ExtractionCodRED Closed (dev)
F1 Score0.612
8
Document-level Relation ExtractionCodRED Open (test)
F1 Score57.88
7
Document-level Relation ExtractionCodRED Open (dev)
F1 Score53.06
7
Showing 4 of 4 rows

Other info

Follow for update