Robust stochastic parsing: comparing two approaches for processing extra-grammatical sentences

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

AILOMAA Marita KADLEC Vladimír CHAPPELIER Jean-Cédric RAJMAN Martin

Year of publication 2005
Type Article in Proceedings
Conference Proceedings of the 15th Nordic Conference of Computational Linguistics (NODALIDA) 2005
MU Faculty or unit

Faculty of Informatics

Citation
Field Informatics
Keywords robust; parsing; NLP
Description This paper compares two techniques for robust parsing of extra-grammatical natural language that might be of interest in large scale Textual Data Analysis applications. The first one returns a "correct" derivation for any extra-grammatical sentence by generating the finest corresponding most probable optimal maximum coverage. The second one extends the initial grammar by adding relaxed grammar rules in a controlled manner. Both techniques use a stochastic parser that selects a "best" solution among multiple analyses. The techniques were tested on the ATIS and Susanne corp ora and exp erimental results, as well as conclusions on performance comparison, are provided.
Related projects:

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