Sean Igo, Ellen Riloff
Our research is motivated by the observation that NLP systems frequently mislabel passive voice verb phrases as being in the active voice when there is no auxiliary verb (e.g., "The man arrested had a long record"). These errors directly impact thematic role recognition and NLP applications that depend on it. We present a learned classifier that can accurately identify reduced passive voice constructions in shallow parsing environments.
Subjects: 13. Natural Language Processing; 13.3 Syntax
Submitted: Apr 15, 2008