Paper: PARMA: A Predicate Argument Aligner

ACL ID P13-2012
Title PARMA: A Predicate Argument Aligner
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013

We introduce PARMA, a system for cross- document, semantic predicate and argu- ment alignment. Our system combines a number of linguistic resources familiar to researchers in areas such as recognizing textual entailment and question answering, integrating them into a simple discrimina- tive model. PARMA achieves state of the art results on an existing and a new dataset. We suggest that previous efforts have fo- cussed on data that is biased and too easy, and we provide a more difficult dataset based on translation data with a low base- line which we beat by 17% F1.