Robust stochastic parsing using optimal maximum coverage

Investor logo

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

KADLEC Vladimír AILOMAA Marita CHAPPELIER Jean-Cédric RAJMAN Martin

Year of publication 2005
Type Article in Proceedings
Conference Proceedings of The International Conference Recent Advances In Natural Language Processing (RANLP) 2005
MU Faculty or unit

Faculty of Informatics

Citation
Field Informatics
Keywords robust; parsing; coverage; NLP
Description This paper presents a robust syntactic parser that is able to return a ``correct'' derivation tree even if the grammar cannot generate the input sentence. The following two steps solution is proposed: the corresponding most probable optimal maximum coverage is generated first, then the trees from this coverage are glued into one resulting tree. The technique was tested on the ATIS and Susanne corpora and experimental results, as well as conclusions on performance, are provided.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.