Learning Script Participants from Unlabeled Data
- We introduce a system that learns the participants of arbitrary given scripts. This system processes data from web experiments, in which each participant can be realized with different expressions. It computes participants by encoding semantic similarity and global structural information into an Integer Linear Program. An evaluation against a gold standard shows that we significantly outperform two informed baselines.
Download full text files
Additional Services
Statistics
| Author: | Michaela Regneri, Alexander Koller, Josef RuppenhoferGND, Manfred Pinkal |
|---|---|
| URN: | urn:nbn:de:bsz:mh39-52718 |
| URL: | http://www.aclweb.org/anthology/R/R11/ |
| ISSN: | 1313-8502 |
| Parent Title (English): | Proceedings of Recent Advances in Natural Language Processing |
| Publisher: | ICOMANIA Ltd. |
| Place of publication: | Shoumen |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of first Publication: | 2011 |
| Date of Publication (online): | 2016/09/16 |
| Publicationstate: | Veröffentlichungsversion |
| Reviewstate: | Peer-Review |
| Tag: | Integer Linear Program; arbitrary scripts; global structural information; semantic similarity |
| GND Keyword: | Automatische Sprachanalyse; Nominalphrase; Semantische Analyse |
| First Page: | 463 |
| Last Page: | 470 |
| DDC classes: | 400 Sprache / 410 Linguistik |
| Open Access?: | ja |
| Linguistics-Classification: | Computerlinguistik |
| Licence (German): |  Urheberrechtlich geschützt |