J.-C. Chappelier, M. Rajman, R. Aragues, and A. Rozenknop. Lattice parsing for speech recognition. In 6eme conference sur le Traitement Automatique du Langage Naturel (TALN99),Cagese, France, July 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
ISIS: Interaction through Speech with Information Systems - Ballim, Chappelier.. (2000) Self-citation (Chappelier Rajman) (Correct)
No context found.
J.-C. Chappelier, M. Rajman, R. Aragues, and A. Rozenknop. Lattice parsing for speech recognition. In Proc. of 6#me conf#rence sur le Traitement Automatique du Langage Naturel (TALN'99), pages 95104, July 1999.
Gibbsian Context-Free Grammar for Parsing - Rozenknop (2002) Self-citation (Rozenknop) (Correct)
....show that up to 33 of analysis errors made by a SCFG can be avoided with this model. 1 Motivations Stochastic Context Free Grammars (SCFGs) are far from being up to date models for the desciption of natural languages, but they still remain interesting models for Parsing and Speech Recognition [4], thanks to particularly e cient algorithms they provide for those tasks [6, 11, 2] They can also be used as computational representations of richer grammars, such as Polynomial Tree Substitution Grammars [3] However, their mathematical properties seem somewhat strange and lower the quality of ....
J.-C. Chappelier, M. Rajman, R. Arags, and A. Rozenknop. Lattice parsing for speech recognition. In Proc. of 6me confrence sur le Traitement Automatique du Langage Naturel (TALN99), pages 95104, Cargse (France), jul 1999.
An FPGA-based syntactic parser for real-life.. - Ciressan.. (2001) Self-citation (Chappelier) (Correct)
No context found.
J.-C. Chappelier, et al. (1999) Lattice Parsing for Speech Recognition. Proc. of 6me confrence sur le Traitement Automatique du Langage Naturel (TALN'99), 95--104. Cargse, France.
Monte-Carlo Sampling for NP-Hard Maximization Problems in.. - Chappelier, Rajman (2000) (2 citations) Self-citation (Chappelier Rajman) (Correct)
.... Analysis and Notations In our case, the analysis phase of the parsing consists in a bottom up filling of a parse chart with items that represent all the possible subderivations of all possible substrings of the input, a sentence in the DOP MPP case [9] and a word graph in the SCFG MPS case [10]. More precisely, the parse chart consists of a set of items [X, i, j]eachrepre senting the fact that the substring w i . w j of the input can be derived from the non terminal X (this will be noted X # w i . w j ) In the case of DOP MPP, where the input consists of a single sentence, w i ....
J.-C. Chappelier, M. Rajman, R. Aragues, and A. Rozenknop. Lattice parsing for speech recognition. In Proc.of6eme conference sur le Traitement Automatique du Langage Naturel (TALN'99), pages 95--104, July 1999.
An FPGA-based coprocessor for the parsing of.. - Ciressan, Sanchez.. (2000) (3 citations) Self-citation (Chappelier) (Correct)
....systems is therefore an important goal; e.g. in the case where the output of the speech recognizer is further processed with a syntactic parser to lter out those of the hypotheses (i.e. sentences) that are not syntactically correct. The case of a sequential coupling, presented in [5], is such an example. Due to the real time constraints in such an application, fast parsing is again required. Various low complexity (i.e. polynomial) parsing solutions have been proposed for context free languages, in particular several parallel implementations of the standard O(n 3 ) time ....
.... the sets N i;1 may be initialized during the initialization step, but any of the sets N i;j as with wordlattice representation words may occur anywhere in the CYK table (see gure 3(b) Thus, in order to adapt the CYK algorithm to word lattice parsing, the initialization step needs to be extended [5]. To illustrate this point, let us consider the wordlattice given in gure 2, containing the six sentences a a b b , a b d b , a b b a , b b a a , b c b a and b c d b and the same grammar G as used in the former example. First the lattice nodes are ordered by increasing depth 3 (see gure ....
J.-C. Chappelier et al. Lattice parsing for speech recognition. In Proc. of 6#me conf#rence sur le Traitement Automatique du Langage Naturel (TALN'99), pages 95104, Carg#se (France), July 1999.
Monte-Carlo Sampling for NP-Hard Maximization Problems in.. - Chappelier, Rajman (2000) (2 citations) Self-citation (Chappelier Rajman) (Correct)
.... Analysis and Notations In our case, the analysis phase of the parsing consists in a bottom up filling of a parse chart with items that represent all the possible subderivations of all possible substrings of the input, a sentence in the DOP MPP case [9] and a word graph in the SCFG MPS case [10]. More precisely, the parse chart consists of a set of items [X; i; j] each representing the fact that the substring w i : w j of the input can be derived from the non terminal X (this will be noted X ) w i : w j ) In the case of DOP MPP, where the input consists of a single sentence, w i ....
J.-C. Chappelier, M. Rajman, R. Aragues, and A. Rozenknop. Lattice parsing for speech recognition. In Proc. of 6me confrence sur le Traitement Automatique du Langage Naturel (TALN'99), pages 95--104, July 1999.
Combining Acoustic Confidence Scores with Deep Semantic.. - Gabsdil, Bos (Correct)
No context found.
J.-C. Chappelier, M. Rajman, R. Aragues, and A. Rozenknop. Lattice parsing for speech recognition. In 6eme conference sur le Traitement Automatique du Langage Naturel (TALN99),Cagese, France, July 1999.
Language Modeling Using Efficient Best-First Bottom-Up Parsing - Hall, Johnson (Correct)
No context found.
J. Chappelier, M. Rajman, R. Aragues, and A. Rozenknop, "Lattice parsing for speech recognition," in Proceedings of 6me confrence sur le Traitement Automatique du Langage Naturel (TALN'99), 1999, pp. 95--104.
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