@article{S.2002,
title = {Stochastic Finite-State Models for Spoken Language Machine Translation},
author = {Bangalore S. and Riccardi G.},
url = {https://sisl.disi.unitn.it/wp-content/uploads/2014/11/mt_journal_special-02.pdf},
year = {2002},
date = {2002-01-01},
journal = {Machine Translation , vol 17, n. 3, pp. 165-184, 2002 (Invited paper)},
abstract = {Abstract. The problem of machine translation can be viewed as consisting of two subproblems (a) lexical selection and (b) lexical reordering. In this paper, we propose stochastic finite-state models for these two subproblems. Stochastic finite-state models are efficiently learnable from data, effective for decoding and are associated with a calculus for composing models which allows for tight integration of constraints from various levels of language processing. We present a method for learning stochastic finite-state models for lexical selection and lexical reordering that are trained automatically from pairs of source and target utterances. We use this method to develop models for English–Japanese and English–Spanish translation and present the performance of these models for translation on speech and text. We also evaluate the efficacy of such a translation model in the context of a call routing task of unconstrained speech utterances.},
keywords = {Statistical Machine Translation}
}
Abstract. The problem of machine translation can be viewed as consisting of two subproblems (a) lexical selection and (b) lexical reordering. In this paper, we propose stochastic finite-state models for these two subproblems. Stochastic finite-state models are efficiently learnable from data, effective for decoding and are associated with a calculus for composing models which allows for tight integration of constraints from various levels of language processing. We present a method for learning stochastic finite-state models for lexical selection and lexical reordering that are trained automatically from pairs of source and target utterances. We use this method to develop models for English–Japanese and English–Spanish translation and present the performance of these models for translation on speech and text. We also evaluate the efficacy of such a translation model in the context of a call routing task of unconstrained speech utterances.