Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Lu, Keming, Hsu, I-Hung, Zhou, Wenxuan, Ma, Mingyu Derek, Chen, Muhao
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jun-4-2023
- Country:
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- Canada (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California > Los Angeles County
- Los Angeles (0.14)
- Washington > King County
- Europe
- Sweden > Uppsala County
- Uppsala (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Portugal > Lisbon
- Lisbon (0.04)
- Italy > Tuscany
- Florence (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Sweden > Uppsala County
- Asia
- Genre:
- Research Report (0.64)
- Industry:
- Media > Film (1.00)
- Leisure & Entertainment (1.00)
- Technology: