A finite-state framework for log-linear models in machine translation
نویسندگان
چکیده
Log-linear models represent nowadays the state-of-the-art in statistical machine translation. There, several models are combined altogether into a whole statistical approach. Finite-state transducers constitute a special type of statistical translation model whose interest has been proved in different translation tasks. The goal of this work is to introduce a finite-state framework for a log-linear modelling approach in statistical machine translation. Results for a French-English technical translation task show the convenience of the proposed methods.
منابع مشابه
A Finite-State Approach to Phrase-Based Statistical Machine Translation
This paper presents a finite-state approach to phrase-based statistical machine translation where a log-linear modelling framework is implemented by means of an on-the-fly composition of weighted finite-state transducers. Moses, a well-known state-of-the-art system, is used as a machine translation reference in order to validate our results by comparison. Experiments on the TED corpus achieve a...
متن کاملA WFST-based log-linear framework for speaking-style transformation
●Objective: Transform spoken-style language (V) into written style language (W) for the creation of transcripts ●Approach: Statistical machine translation to “translate” from verbatim text to written text ●Innovations: ●Log-linear modeling for improved accuracy ●Introduction of features to handle common phenomena in speaking-style transformation ●WFST-based implementation for integration with W...
متن کاملDiscriminative Models and Training Methods For Statistical Machine Translation
Statistical Machine Translation (SMT) has been the dominant avor of Machine Translation (MT) over the last decade. Traditional SMT systems have a pipeline structure in which di erent kinds of Machine Learning models are employed in di erent stages. For the translation modeling, most state of the art systems use hybrid models that combine a handful of generative models in a discriminative framew...
متن کاملOnline optimisation of log-linear weights in interactive machine translation
Whenever the quality provided by a machine translation system is not enough, a human expert is required to correct the sentences provided by the machine translation system. In such a setup, it is crucial that the system is able to learn from the errors that have already been corrected. In this paper, we analyse the applicability of discriminative ridge regression for learning the log-linear wei...
متن کاملLinear Transduction Grammars and Zipper Finite-State Transducers
We examine how the recently explored class of linear transductions relates to finite-state models. Linear transductions have been neglected historically, but gainined recent interest in statistical machine translation modeling, due to empirical studies demonstrating that their attractive balance of generative capacity and complexity characteristics lead to improved accuracy and speed in learnin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008