Exploiting Parallel News Streams for Unsupervised Event Extraction

Congle Zhang, Stephen Soderland, Daniel S. Weld


Abstract
Most approaches to relation extraction, the task of extracting ground facts from natural language text, are based on machine learning and thus starved by scarce training data. Manual annotation is too expensive to scale to a comprehensive set of relations. Distant supervision, which automatically creates training data, only works with relations that already populate a knowledge base (KB). Unfortunately, KBs such as FreeBase rarely cover event relations (e.g. “person travels to location”). Thus, the problem of extracting a wide range of events — e.g., from news streams — is an important, open challenge. This paper introduces NewsSpike-RE, a novel, unsupervised algorithm that discovers event relations and then learns to extract them. NewsSpike-RE uses a novel probabilistic graphical model to cluster sentences describing similar events from parallel news streams. These clusters then comprise training data for the extractor. Our evaluation shows that NewsSpike-RE generates high quality training sentences and learns extractors that perform much better than rival approaches, more than doubling the area under a precision-recall curve compared to Universal Schemas.
Anthology ID:
Q15-1009
Volume:
Transactions of the Association for Computational Linguistics, Volume 3
Month:
Year:
2015
Address:
Cambridge, MA
Editors:
Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
117–129
Language:
URL:
https://aclanthology.org/Q15-1009
DOI:
10.1162/tacl_a_00127
Bibkey:
Cite (ACL):
Congle Zhang, Stephen Soderland, and Daniel S. Weld. 2015. Exploiting Parallel News Streams for Unsupervised Event Extraction. Transactions of the Association for Computational Linguistics, 3:117–129.
Cite (Informal):
Exploiting Parallel News Streams for Unsupervised Event Extraction (Zhang et al., TACL 2015)
Copy Citation:
PDF:
https://aclanthology.org/Q15-1009.pdf
Data
FIGERNew York Times Annotated Corpus