Author： Fujita Sanae
Publisher： Springer Publishing Company
ISSN： 1570-7075
Source： Research on Language and Computation, Vol.8, Iss.1, 2010-03, pp. : 1-22
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
In this article, we investigate the use of semantic information in parse selection. We show that fully disambiguated sense-based semantic features smoothed using ontological information are effective for parse selection. Training and testing was undertaken using definition and example sentences taken from a Japanese dictionary corpus (Hinoki), which is manually annotated with senses. A model employing both syntactic and semantic information provides better parse selection accuracy than a model using only syntactic features.
Related content
Access to resources
Recommend
Is HPSG Featureless Or Unprincipled?
By Moshier M.A.
Linguistics and Philosophy, Vol. 20, Iss. 6, 1997-12 ,pp. :