Learning to identify reduced passive verb phrases with a shallow parser
Sean Igo, Ellen Riloff · 2008
Our research is motivated by the observation that NLP sys-tems 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 im-pact thematic role recognition and NLP applications that de-pend on it. We present a learned classifier that can accurately identify reduced passive voice constructions in shallow pars-ing environments.