Name
Abstract | ||
|---|---|---|
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 treebank-based (Lexical-Functional) grammar acquisition and parsing, in an extrinsic evaluation. |
Year | Venue | Keywords |
|---|---|---|
2010 | ACL | grammatical function,core argument function,extrinsic evaluation,grammatical function labelling,statistical classifier,function labelling,intrinsic evaluation,hard constraint,object etc.,grammar coverage,argument grammatical function,grammar acquisition,computational linguistics |
Field | DocType | Volume |
Integer,Word order,Computer science,Computational linguistics,Grammar,Natural language processing,Linear programming,Treebank,Artificial intelligence,Parsing,Classifier (linguistics),Machine learning | Conference | P10-1 |
Citations | PageRank | References |
6 | 0.47 | 18 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| wolfgang seeker | 1 | 121 | 10.56 |
| Ines Rehbein | 2 | 142 | 19.21 |
| Jonas Kuhn | 3 | 115 | 13.05 |
| Josef van Genabith | 4 | 1037 | 105.64 |