TY - GEN
T1 - Distant Supervision for Relation Extraction with an Incomplete Knowledge Base
AU - Min, Bonan
AU - Grishman, Ralph
AU - Wan, Li
AU - Wang, Chang
AU - Gondek, David
N1 - Funding Information:
Supported in part by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center contract number D11PC20154. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA, DoI/NBC, or the U.S. Government.
Publisher Copyright:
© 2013 Association for Computational Linguistics
PY - 2013
Y1 - 2013
N2 - Distant supervision, heuristically labeling a corpus using a knowledge base, has emerged as a popular choice for training relation extractors. In this paper, we show that a significant number of “negative“examples generated by the labeling process are false negatives because the knowledge base is incomplete. Therefore the heuristic for generating negative examples has a serious flaw. Building on a state-of-the-art distantly-supervised extraction algorithm, we proposed an algorithm that learns from only positive and unlabeled labels at the pair-of-entity level. Experimental results demonstrate its advantage over existing algorithms.
AB - Distant supervision, heuristically labeling a corpus using a knowledge base, has emerged as a popular choice for training relation extractors. In this paper, we show that a significant number of “negative“examples generated by the labeling process are false negatives because the knowledge base is incomplete. Therefore the heuristic for generating negative examples has a serious flaw. Building on a state-of-the-art distantly-supervised extraction algorithm, we proposed an algorithm that learns from only positive and unlabeled labels at the pair-of-entity level. Experimental results demonstrate its advantage over existing algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85121685878&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121685878&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85121685878
T3 - Proceedings of the 2nd Workshop on Computational Linguistics for Literature, CLfL 2013 at the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2013
SP - 777
EP - 782
BT - Proceedings of the 2nd Workshop on Computational Linguistics for Literature, CLfL 2013 at the 2013 Conference of the North American Chapter of the Association for Computational Linguistics
A2 - Elson, David
A2 - Kazantseva, Anna
A2 - Szpakowicz, Stan
PB - Association for Computational Linguistics (ACL)
T2 - 2nd Workshop on Computational Linguistics for Literature, CLfL 2013 at the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2013
Y2 - 14 June 2013
ER -