Hard constraints for grammatical function labelling
- For languages with (semi-) free word order (such as German), labelling grammatical functions on top of phrase-structural constituent analyses is crucial for making them interpretable. Unfortunately, most statistical classifiers consider only local information for function labelling and fail to capture important restrictions on the distribution of core argument functions such as subject, object etc., namely that there is at most one subject (etc.) per clause. We augment a statistical classifier with an integer linear program imposing hard linguistic constraints on the solution space output by the classifier, capturing global distributional restrictions. We show that this improves labelling quality, in particular for argument grammatical functions, in an intrinsic evaluation, and, importantly, grammar coverage for treebankbased (Lexical-Functional) grammar acquisition and parsing, in an extrinsic evaluation.
Download full text files
Additional Services
Statistics
| Author: | Wolfgang Seeker, Ines Rehbein, Joans Kuhn, Josef van Genabith |
|---|---|
| URN: | urn:nbn:de:bsz:mh39-56059 |
| URL: | http://dl.acm.org/citation.cfm?id=1858681&picked=prox |
| ISBN: | 978-1-932432-66-4 (Vol. 1) |
| ISBN: | 978-1-932432-67-1 (Vol. 2) |
| Parent Title (English): | Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala, Sweden, 11-16 July 2010 |
| Publisher: | Association for Computational Linguistics |
| Place of publication: | Stroudsburg, PA |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of first Publication: | 2010 |
| Date of Publication (online): | 2016/11/21 |
| GND Keyword: | Automatische Sprachanalyse; Phrasenstruktur |
| First Page: | 1087 |
| Last Page: | 1097 |
| DDC classes: | 400 Sprache / 400 Sprache, Linguistik |
| Open Access?: | ja |
| Linguistics-Classification: | Computerlinguistik |
| Licence (German): |  Urheberrechtlich geschützt |