Abstract
In this paper, we evaluate five distinct systems of labelled grammatical dependency against the kind of input we require for semantic interpretation, in particular for the deep semantic interpreter underlying a tutorial dialogue system. We focus on the following linguistic phenomena: passive, control and raising, noun modifiers, and meaningful vs. non-meaningful prepositions. We conclude that no one system provides all the features that we require, although each such feature is contained within at least one of the competing systems.
Original language | English |
---|---|
Title of host publication | Coling 2008: Proceedings of the workshop on Cross-Framework and Cross-Domain Parser Evaluation |
Place of Publication | Manchester, UK |
Publisher | ASSOC COMPUTATIONAL LINGUISTICS-ACL |
Pages | 51-58 |
Number of pages | 8 |
ISBN (Print) | 978-1-905593-50-7 |
Publication status | Published - 1 Aug 2008 |