Name
Abstract | ||
|---|---|---|
Unknown lexical items present a major obstacle to the development of broad-coverage semantic role labeling systems. We address this problem with a semi-supervised learning approach which acquires training instances for unseen verbs from an unlabeled corpus. Our method relies on the hypothesis that unknown lexical items will be structurally and semantically similar to known items for which annotations are available. Accordingly, we represent known and unknown sentences as graphs, formalize the search for the most similar verb as a graph alignment problem and solve the optimization using integer linear programming. Experimental results show that role labeling performance for unknown lexical items improves with training data produced automatically by our method. |
Year | Venue | Keywords |
|---|---|---|
2009 | EMNLP | training data,unknown sentence,known item,broad-coverage semantic role,similar verb,major obstacle,integer linear programming,graph alignment problem,semi-supervised semantic role,unknown lexical item,semantic role labeling,semi supervised learning,linear program,semantic similarity |
Field | DocType | Volume |
Training set,Verb,Graph,Computer science,Lexical item,Integer programming,Natural language processing,Artificial intelligence,Machine learning,Semantic role labeling | Conference | D09-1 |
Citations | PageRank | References |
26 | 0.91 | 13 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hagen Fürstenau | 1 | 533 | 20.43 |
| Mirella Lapata | 2 | 5973 | 369.52 |