@inproceedings{424e4303b7c641f69e13f1c514707838,
title = "Event extraction using distant supervision",
abstract = "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.",
keywords = "Distant-supervision, Event-extraction, Searn",
author = "Kevin Reschke and Martin Jankowiak and Mihai Surdeanu and Manning, {Christopher D.} and Daniel Jurafsky",
year = "2014",
language = "English (US)",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "4527--4531",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
note = "9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
}