This paper describes a new finite-state shallow parser. It merges constructive and reductionist approaches within a highly modular architecture. Syntactic information is added at the sentence level in an incremental way, depending on the contextual information available at a given stage. This approach overcomes the inefficiency of previous fully reductionist constraint-based systems, while maintaining broad coverage and linguistic granularity. The implementation relies on a sequence of networks built with the replace operator. Given the high level of modularity, the core grammar is easily augmented with corpus-specific sub-grammars. The current system is implemented for French and is being expanded to new languages.
%0 Conference Paper
%1 Ait:1997
%A A\"ıt-Mokhtar, Salah
%A Chanod, Jean-Pierre
%B Proc. Applied Natural Language Processing
%C Washington
%D 1997
%K shallow_parsing robust_parsing
%T Incremental Finite-State Parsing
%X This paper describes a new finite-state shallow parser. It merges constructive and reductionist approaches within a highly modular architecture. Syntactic information is added at the sentence level in an incremental way, depending on the contextual information available at a given stage. This approach overcomes the inefficiency of previous fully reductionist constraint-based systems, while maintaining broad coverage and linguistic granularity. The implementation relies on a sequence of networks built with the replace operator. Given the high level of modularity, the core grammar is easily augmented with corpus-specific sub-grammars. The current system is implemented for French and is being expanded to new languages.
@inproceedings{Ait:1997,
abstract = {This paper describes a new finite-state shallow parser. It merges constructive and reductionist approaches within a highly modular architecture. Syntactic information is added at the sentence level in an incremental way, depending on the contextual information available at a given stage. This approach overcomes the inefficiency of previous fully reductionist constraint-based systems, while maintaining broad coverage and linguistic granularity. The implementation relies on a sequence of networks built with the replace operator. Given the high level of modularity, the core grammar is easily augmented with corpus-specific sub-grammars. The current system is implemented for French and is being expanded to new languages.},
added-at = {2007-12-14T02:35:39.000+0100},
address = {Washington},
author = {A{\"\i}t-Mokhtar, Salah and Chanod, Jean-Pierre},
biburl = {https://www.bibsonomy.org/bibtex/2fceef20ad1ff90c4b63e51b3d20cd07e/diego_ma},
booktitle = {Proc. Applied Natural Language Processing},
interhash = {b1bae85df1c5cb859bbbafbc70875c12},
intrahash = {fceef20ad1ff90c4b63e51b3d20cd07e},
keywords = {shallow_parsing robust_parsing},
timestamp = {2007-12-14T02:35:39.000+0100},
title = {Incremental Finite-State Parsing},
year = 1997
}