CLIRLGDec 21, 2022

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

arXiv:2212.10786v2231 citationsh-index: 45
Originality Incremental advance
AI Analysis

This addresses the challenge of extracting relations that span multiple documents, which is incremental as it builds on existing cross-document RE methods.

The paper tackled the problem of efficiently retrieving multi-hop evidence for cross-document relation extraction, proposing MR.COD, which improved end-to-end performance on the CodRED dataset in both closed and open settings.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes