| AILOMAA, Marita, Vladimír KADLEC, Jean-Cédric CHAPPELIER a Martin RAJMAN. Robust stochastic parsing: comparing two approaches for processing extra-grammatical sentences. In Proceedings of the 15th Nordic Conference of Computational Linguistics (NODALIDA) 2005. 2005. vyd. Finland: University of Joensuu, 2005, s. 21-29, 8 s. |
Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{571729,
author = {Ailomaa, Marita and Kadlec, Vladimír and Chappelier, JeanandCédric and Rajman, Martin},
address = {Finland},
booktitle = {Proceedings of the 15th Nordic Conference of Computational Linguistics (NODALIDA) 2005},
edition = {2005},
keywords = {robust; parsing; NLP},
language = {eng},
location = {Finland},
pages = {21-29},
publisher = {University of Joensuu},
title = {Robust stochastic parsing: comparing two approaches for processing extra-grammatical sentences},
year = {2005}
}
TY - JOUR
ID - 571729
AU - Ailomaa, Marita - Kadlec, Vladimír - Chappelier, Jean-Cédric - Rajman, Martin
PY - 2005
TI - Robust stochastic parsing: comparing two approaches for processing extra-grammatical sentences
PB - University of Joensuu
CY - Finland
KW - robust
KW - parsing
KW - NLP
N2 - 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.
ER -
AILOMAA, Marita, Vladimír KADLEC, Jean-Cédric CHAPPELIER a Martin RAJMAN. Robust stochastic parsing: comparing two approaches for processing extra-grammatical sentences. In \textit{Proceedings of the 15th Nordic Conference of Computational Linguistics (NODALIDA) 2005}. 2005. vyd. Finland: University of Joensuu, 2005, s.~21-29, 8 s.
|
