Paper: Sentence Simplification for Semantic Role Labeling

ACL ID P08-1040
Title Sentence Simplification for Semantic Role Labeling
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008

Parse-tree paths are commonly used to incor- porate information from syntactic parses into NLP systems. These systems typically treat thepathsasatomic(ornearlyatomic)features; these features are quite sparse due to the im- mense variety of syntactic expression. In this paper, we propose a general method for learn- inghowtoiterativelysimplifyasentence, thus decomposing complicated syntax into small, easy-to-process pieces. Our method applies a series of hand-written transformation rules corresponding to basic syntactic patterns — for example, one rule “depassivizes” a sen- tence. The model is parameterized by learned weights specifying preferences for some rules over others. After applying all possible trans- formations to a sentence, we are left with a set of candidate simplified sen...