CoRE: A context-aware relation extraction method for relation completion

Abstract
We identify relation completion (RC) as one recurring problem that is central to the success of novel big data applications such as Entity Reconstruction and Data Enrichment. Given a semantic relation {\cal R}, RC attempts at linking entity pairs between two entity lists under the relation {\cal R}. To accomplish the RC goals, we propose to formulate search queries for each query entity \alpha based on some auxiliary information, so that to detect its target entity \beta from the set of retrieved documents. For instance, a pattern-based method (PaRE) uses extracted patterns as the auxiliary information in formulating search queries. However, high-quality patterns may decrease the probability of finding suitable target entities. As an alternative, we propose CoRE method that uses context terms learned surrounding the expression of a relation as the auxiliary information in formulating queries. The experimental results based on several real-world web data collections demonstrate that CoRE reaches a much higher accuracy than PaRE for the purpose of RC. © 1989-2012 IEEE.

Citation
Li, Z., Sharaf, M. A., Sitbon, L., Du, X., & Zhou, X. (2014). CoRE: A Context-Aware Relation Extraction Method for Relation Completion. IEEE Transactions on Knowledge and Data Engineering, 26(4), 836–849. doi:10.1109/tkde.2013.148

Acknowledgements
This research was partially supported by National 863 High-tech Program (Grant No. 2012AA011001) and the Australian Research Council (Grant No. DP120102829). Part of this work has appeared as a short paper in CIKM '11 [18].

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Journal
IEEE Transactions on Knowledge and Data Engineering

DOI
10.1109/TKDE.2013.148

Permanent link to this record