Learning Relational Dependency Networks For Relation Extraction
Document Type
Conference Proceeding
Publication Date
2016
Published In
Inductive Logic Programming
Series Title
Lecture Notes In Computer Science
Abstract
We consider the task of KBP slot filling – extracting relation information from newswire documents for knowledge base construction. We present our pipeline, which employs Relational Dependency Networks (RDNs) to learn linguistic patterns for relation extraction. Additionally, we demonstrate how several components such as weak supervision, word2vec features, joint learning and the use of human advice, can be incorporated in this relational framework. We evaluate the different components in the benchmark KBP 2015 task and show that RDNs effectively model a diverse set of features and perform competitively with current state-of-the-art relation extraction methods.
Published By
Springer
Editor(s)
J. Cussens And A. Russo
Conference
26th International Conference On Inductive Logic Programming
Recommended Citation
Ameet Soni, D. Viswanathan, J. Shavlik, and S. Natarajan.
(2016).
"Learning Relational Dependency Networks For Relation Extraction".
Inductive Logic Programming.
Volume 10326,
81-93.
DOI: 10.1007/978-3-319-63342-8_7
https://works.swarthmore.edu/fac-comp-sci/47
Comments
The presentation slides for this paper can be found on the author's website.
An earlier version of this paper was presented at the Sixth International Workshop On Statistical Relational AI (StarAI 2016), July 11, 2016, in New York, NY. The full text of this version is freely available on arXiv.org at arXiv:1607.00424.