Paper: Appropriately Handled Prosodic Breaks Help PCFG Parsing

ACL ID N10-1005
Title Appropriately Handled Prosodic Breaks Help PCFG Parsing
Venue Human Language Technologies
Session Main Conference
Year 2010

This paper investigates using prosodic infor- mation in the form of ToBI break indexes for parsing spontaneous speech. We revisit two previously studied approaches, one that hurt parsing performance and one that achieved minor improvements, and propose a new method that aims to better integrate prosodic breaks into parsing. Although these ap- proaches can improve the performance of ba- sicprobabilisticcontextfreegrammar(PCFG) parsers, they all fail to produce fine-grained PCFG models with latent annotations (PCFG- LA) (Matsuzaki et al., 2005; Petrov and Klein, 2007)thatperformsignificantlybetterthanthe baseline PCFG-LA model that does not use break indexes, partially due to mis-alignments between automatic prosodic breaks and true phrase boundaries. We propose two alterna- tive ways to res...