Name
Abstract | ||
|---|---|---|
The sense of a preposition is related to the semantics of its dominating prepositional phrase. Knowing the sense of a preposition could help to correctly classify the semantic role of the dominating prepositional phrase and vice versa. In this paper, we propose a joint probabilistic model for word sense disambiguation of prepositions and semantic role labeling of prepositional phrases. Our experiments on the PropBank corpus show that jointly learning the word sense and the semantic role leads to an improvement over state-of-the-art individual classifier models on the two tasks. |
Year | Venue | Keywords |
|---|---|---|
2009 | EMNLP | preposition sense,joint probabilistic model,word sense disambiguation,propbank corpus show,state-of-the-art individual classifier model,word sense,prepositional phrase,joint learning,dominating prepositional phrase,semantic role,probabilistic model,semantic role labeling |
Field | DocType | Volume |
SemEval,Computer science,Phrase,PropBank,Natural language processing,Statistical model,Artificial intelligence,Classifier (linguistics),Linguistics,Semantic role labeling,Semantics,Word-sense disambiguation | Conference | D09-1 |
Citations | PageRank | References |
16 | 0.72 | 15 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Dahlmeier | 1 | 460 | 29.67 |
| Hwee Tou Ng | 2 | 4092 | 300.40 |
| T. Schultz | 3 | 2423 | 252.72 |