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.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014 |
| Publisher | European Language Resources Association (ELRA) |
| Pages | 4527-4531 |
| Number of pages | 5 |
| ISBN (Electronic) | 9782951740884 |
| State | Published - Jan 1 2014 |
| Event | 9th International Conference on Language Resources and Evaluation, LREC 2014 - Reykjavik, Iceland Duration: May 26 2014 → May 31 2014 |
Other
| Other | 9th International Conference on Language Resources and Evaluation, LREC 2014 |
|---|---|
| Country | Iceland |
| City | Reykjavik |
| Period | 5/26/14 → 5/31/14 |
Fingerprint
Keywords
- Distant-supervision
- Event-extraction
- Searn
ASJC Scopus subject areas
- Linguistics and Language
- Library and Information Sciences
- Education
- Language and Linguistics
Cite this
Event extraction using distant supervision. / Reschke, Kevin; Jankowiak, Martin; Surdeanu, Mihai; Manning, Christopher D.; Jurafsky, Daniel.
Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014. European Language Resources Association (ELRA), 2014. p. 4527-4531.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Event extraction using distant supervision
AU - Reschke, Kevin
AU - Jankowiak, Martin
AU - Surdeanu, Mihai
AU - Manning, Christopher D.
AU - Jurafsky, Daniel
PY - 2014/1/1
Y1 - 2014/1/1
N2 - 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.
AB - 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.
KW - Distant-supervision
KW - Event-extraction
KW - Searn
UR - http://www.scopus.com/inward/record.url?scp=85021736987&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021736987&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85021736987
SP - 4527
EP - 4531
BT - Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014
PB - European Language Resources Association (ELRA)
ER -