Phrase-based finite state models
نویسندگان
چکیده
In the last years, statistical machine translation has already demonstrated its usefulness within a wide variety of translation applications. In this line, phrasebased alignment models have become the reference to follow in order to build competitive systems. Finite state models are always an interesting framework because there are well-known efficient algorithms for their representation and manipulation. This document is a contribution to the evolution of finite state models towards a phrase-based approach. The inference of stochastic transducers that are based on bilingual phrases is carefully analysed from a finite state point of view. Indeed, the algorithmic phenomena that have to be taken into account in order to deal with such phrase-based finite state models when in decoding time are also in-depth detailed.
منابع مشابه
Exploiting morphology in speech translation with phrase-based finite-state transducers
This work implements a novel formulation for phrase-based translation models making use of morpheme-based translation units under a stochastic finite-state framework. This approach has an additional interest for speech translation tasks since it leads to the integration of the acoustic and translation models. As a further contribution, this is the first paper addressing a Basque-to-Spanish spee...
متن کاملFinite-State Approximation of Phrase Structure Grammars
Phrase-structure grammars are effective models for important syntactic and semantic aspects of natural languages, but can be computationally too demanding for use as language models in real-time speech recognition. Therefore, finite-state models are used instead, even though they lack expressive power. To reconcile those two alternatives, we designed an algorithm to compute finite-state approxi...
متن کاملLearning Finite State Transducers Using Bilingual Phrases
Statistical Machine Translation is receiving more and more attention every day due to the success that the phrase-based alignment models are obtaining. However, despite their power, state-of-the-art systems using these models present a series of disadvantages that lessen their effectiveness in working environments where temporal or spacial computational resources are limited. A finite-state fra...
متن کاملIntersecting Hierarchical and Phrase-Based Models of Translation: Formal Aspects and Algorithms
We address the problem of constructing hybrid translation systems by intersecting a Hiero-style hierarchical system with a phrase-based system and present formal techniques for doing so. We model the phrase-based component by introducing a variant of weighted finite-state automata, called σ-automata, provide a self-contained description of a general algorithm for intersecting weighted synchrono...
متن کاملHierarchical phrase-based translation with weighted finite state transducers
This dissertation is focused in the Statistical Machine Translation field (SMT), particularly in hierarchical phrase-based translation frameworks. We first study and redesign hierarchical models using several filtering techniques. Hierarchical search spaces are based on automatically extracted translation rules. As originally defined they are too big to handle directly without filtering. In thi...
متن کامل