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.
@article{arxiv.2212.10786,
title = {Multi-hop Evidence Retrieval for Cross-document Relation Extraction},
author = {Keming Lu and I-Hung Hsu and Wenxuan Zhou and Mingyu Derek Ma and Muhao Chen},
journal= {arXiv preprint arXiv:2212.10786},
year = {2023}
}