| Jean-Pierre Chanod and Pasi Tapanainen. A non-deterministic tokeniser for finitestate parsing. In Proceedings of the Workshop on Extended finite state models of language (ECAI'96), Budapest, Hungary, 1996. |
....and preprocessed. tivist approach, based on constraints progressively added during the parsing, Abney, 1991] Joshi, 1996] Grefenstette, 1996] as well as a reductionist approach, in which restrictions are applied to eliminate potential analysis already provided ( Karlsson et al. 1995] [Chanod and Tapanainen, 1996]) The applications for shallow parsing are useful for large scale texts. These applications include knowledge extraction, information retrieval as in the FASTUS system ( Appelt et al. 1993] word sense disambiguation ( Dini et al. 1999] translation memory and multilingual comprehension ....
Chanod, J.-P. and Tapanainen, P. (1996). A Nondeterministic Tokeniser for Finite-State Parsing. In ECAI'96 workshop on Extended finite state models of language, Budapest.
....both the two token sequence bien followed by que and a single token bien que, where the lexicon contains all three, crucially with the last listed as a conjunction. It is left to the grammar to sort out which tokenization succeeds. Such a non deterministic tokenizer has been built for French MWEs [CT96] and could be used as another module within the general parsing architecture. This mechanism does not in itself reduce ambiguity 5 but merely recognizes existing ambiguity. However, moving this recognition to the tokenizer simplifies the grammar, and may in fact reduce spurious ambiguity, ....
Chanod, Jean-Pierre and Tapanainen Pasi. 1996. A Non-Deterministic Tokeniser for Finite-State Parsing. ECAI '96 workshop on Extended Finite State Models of Language, Budapest, 1996.
....on the Workshop on Robust Parsing, pages 16 25. Prague, Czech, 1996 other approaches to robust parsing, especially the TOSCA, ANLT, FIDDITCH or PLNLP systems, can be found in [13, 8, 10, 9] 1. 1 Tokenisation The tokenisation uses a tokenising automaton and a multiword expression lexicon [6, 7] 1 , allowing for non deterministic output, i.e. a same string may be analysed as one or more tokens. For example, the word sequence de meme is analysed as a single token (an adverbial meaning similarly) but also, a two word sequence (preposition adjective meaning of same as in of same ....
Jean-Pierre Chanod and Pasi Tapanainen, `A non-deterministic tokeniser for finite-state parsing', in ECAI '96 workshop on Extended finite state models of language, Budapest, (1996).
No context found.
Jean-Pierre Chanod and Pasi Tapanainen. A non-deterministic tokeniser for finitestate parsing. In Proceedings of the Workshop on Extended finite state models of language (ECAI'96), Budapest, Hungary, 1996.
No context found.
J.-P. Chanod and P. Tapanainen. A non-deterministic tokeniser for finite-state parsing. In Proceedings of the Workshop on Extended finite state models of language (ECAI'96), Budapest, Hungary, 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC