Paper: Temporally Anchored Relation Extraction

ACL ID P12-1012
Title Temporally Anchored Relation Extraction
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012

Although much work on relation extraction has aimed at obtaining static facts, many of the target relations are actually fluents, as their validity is naturally anchored to a certain time period. This paper proposes a methodologi- cal approach to temporally anchored relation extraction. Our proposal performs distant su- pervised learning to extract a set of relations from a natural language corpus, and anchors each of them to an interval of temporal va- lidity, aggregating evidence from documents supporting the relation. We use a rich graph- based document-level representation to gener- ate novel features for this task. Results show that our implementation for temporal anchor- ing is able to achieve a 69% of the upper bound performance imposed by the relation extraction step. Compared to t...