Abstract | ||
---|---|---|
We present a method for learning syntax-semantics mappings for verbs from unannotated corpora. We learn linkings, i. e., mappings from the syntactic arguments and adjuncts of a verb to its semantic roles. By learning such linkings, we do not need to model individual semantic roles independently of one another, and we can exploit the relation between different mappings for the same verb, or between mappings for different verbs. We present an evaluation on a standard test set for semantic role labeling. |
Year | Venue | Keywords |
---|---|---|
2012 | *SEM@NAACL-HLT | unsupervised induction,standard test,syntax-semantics lexicon,iterative refinement,syntax-semantics mapping,different mapping,individual semantic role,syntactic argument,unannotated corpus,different verb,semantic role |
Field | DocType | Citations |
Iterative refinement,Verb,Computer science,Exploit,Lexicon,Natural language processing,Artificial intelligence,Syntax,Semantic role labeling,Semantics,Test set | Conference | 4 |
PageRank | References | Authors |
0.43 | 12 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hagen Fürstenau | 1 | 533 | 20.43 |
Owen Rambow | 2 | 2256 | 247.69 |