Work

Online statistics for a unification-based dialogue parser

Year: 2005
Type: conference-paper
Abstract: We describe a method for augmenting unification-based deep parsing with statistical methods. We extend and adapt the Bikel parser, which uses head-driven lexical statistics, to dialogue. We show that our augmented parser produces significantly fewer constituents than the baseline system and achieves comparable bracketing accuracy, even yielding slight improvements for longer sentences.
Language: English
Open Access status: bronze
OpenAlex ID: W2017485105
FWCI: 0.75
Cites: 11
Cited by: 3
Related to: 10