Distant supervision is a successful paradigm that gathers training data for information extraction systems by automatically aligning vast databases of facts with text. Previous work has demonstrated its usefulness for the extraction of binary relations such as a person’s employer or a film’s director. Here, we extend the distant supervision approach to template-based event extraction, focusing on the extraction of passenger counts, aircraft types, and other facts concerning airplane crash events. We present a new publicly available dataset and event extraction task in the plane crash domain based on Wikipedia infoboxes and newswire text. Using this dataset, we conduct a preliminary evaluation of four distantly supervised extraction models which assign named entity mentions in text to entries in the event template. Our results indicate that joint inference over sequences of candidate entity mentions is beneficial. Furthermore, we demonstrate that the Searn algorithm outperforms a linear-chain CRF and strong baselines with local inference.
[1]
Ramesh Nallapati,et al.
Multi-instance Multi-label Learning for Relation Extraction
,
2012,
EMNLP.
[2]
Koby Crammer,et al.
Online Passive-Aggressive Algorithms
,
2003,
J. Mach. Learn. Res..
[3]
Daniel Marcu,et al.
Practical structured learning techniques for natural language processing
,
2006
.
[4]
References
,
1971
.
[5]
Daniel Jurafsky,et al.
Distant supervision for relation extraction without labeled data
,
2009,
ACL.
[6]
Andrew McCallum,et al.
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
,
2001,
ICML.
[7]
Andrew McCallum,et al.
FACTORIE: Probabilistic Programming via Imperatively Defined Factor Graphs
,
2009,
NIPS.
[8]
Andreas Vlachos,et al.
Search-based Structured Prediction applied to Biomedical Event Extraction
,
2011,
CoNLL.
[9]
Valentin I. Spitkovsky,et al.
Stanford's Distantly-Supervised Slot-Filling System
,
2011,
TAC.