Title | ||
---|---|---|
Discriminative approach to predicate-argument structure analysis with zero-anaphora resolution |
Abstract | ||
---|---|---|
This paper presents a predicate-argument structure analysis that simultaneously conducts zero-anaphora resolution. By adding noun phrases as candidate arguments that are not only in the sentence of the target predicate but also outside of the sentence, our analyzer identifies arguments regardless of whether they appear in the sentence or not. Because we adopt discriminative models based on maximum entropy for argument identification, we can easily add new features. We add language model scores as well as contextual features. We also use contextual information to restrict candidate arguments. |
Year | Venue | Keywords |
---|---|---|
2009 | ACL/IJCNLP (Short Papers) | language model score,discriminative model,zero-anaphora resolution,predicate-argument structure analysis,contextual feature,maximum entropy,new feature,argument identification,noun phrase,contextual information,candidate argument,discriminative approach,language model |
Field | DocType | Volume |
Noun phrase,Structure analysis,Computer science,Natural language processing,Artificial intelligence,Principle of maximum entropy,Predicate (grammar),Discriminative model,Sentence,Language model,restrict | Conference | P09-2 |
Citations | PageRank | References |
22 | 1.06 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kenji Imamura | 1 | 42 | 5.60 |
Kuniko Saito | 2 | 75 | 7.12 |
Tomoko Izumi | 3 | 141 | 21.33 |