Issar, S., Estimation of Language Models for New Spoken Language Applications, Proc. ICSLP'96, Philadelphia, USA, 869-872, 1996. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Augmenting Words With Linguistic Information For N-Gram.. - Galescu, Ringger (1999) (Correct)
....## = N c c c c w P c c P w P i i N i i t N , 2 1 1 1 , 1 1 where c i is the class associated with the word w i , for all i. Classes can be determined either by automatic clustering (e.g. 3] or they can be domain specific semantic categories (e.g. [10]) or syntactic categories (POS) 11,15] Although the latter approach has the advantage of capturing some linguistic information in the language 2 We also assume the existence of a start symbol, w 0 . model, using POS classes in the above formulation has a major drawback: the POS tags remove ....
Issar, S. (1996), Estimation of Language Models for New Spoken Language Applications. Proceedings ICSLP '96, Philadelphia, PA, pp. 869-872.
An Architecture for a Generic Dialogue Shell - Allen, Byron, Dzikovska.. (2000) (10 citations) (Correct)
....worse performance than not using any language model at all. Therefore, we need to provide a transformation between language models in the remote domain and language models in the target domain. To do this we use a class based approach. The general procedure for generating class based n gram models (Issar 1996) follows three steps: 1) tagging the corpus according to some predefined word class mapping; 2) computing a back o# n gram class model from the tagged text corpus; and (3) converting back to a word model using the word class mappings in the class tag dictionary. We achieve the adaptation by ....
Issar, S. 1996. Estimation of language models for new spoken language applications. In Proceedings of the International Conference on Spoken Language Processing (ICSLP96) , 869--872.
Online Adaptation For Language Models In Spoken - Dialogue Systems Bernd (Correct)
No context found.
Issar, S., Estimation of Language Models for New Spoken Language Applications, Proc. ICSLP'96, Philadelphia, USA, 869-872, 1996.
Initial Language Models For Spoken Dialogue Systems - Andreas Kellner Philips (1998) (1 citation) (Correct)
No context found.
Sunil Issar. Estimation of language models for new spoken language applications. In Proc. ICSLP, volume 2, pages 869-872, Philadelphia, PA, October 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