Finite-state transducers are models that are being used in different areas of pattern recognition and computational linguistics. One of these areas is machine translation, in which the approaches that are based on building models automatically from training examples are becoming more and more attractive. Finite-state transducers are veryadequate for use in constrained tasks in which training samples of pairs of sentences are available. A technique for inferring finite-state transducers is proposed in this article. This technique is based on formalrelations between finite-state transducers and rational grammars. Given a training corpus of source-target pairs of sentences, the proposed approach uses statistical alignment methods to produce a set of conventional strings from which a stochastic rational grammar (e.g., an n-gram) is inferred. This grammar is finally converted into a finite-state transducer. The proposed methods are assessed through a series of machine translation experiments within the framework of the EuTrans project.

Probabilistic finite-state machines are used today in a variety of areas in pattern recognition, or in fields to which pattern recognition is linked: computational linguistics, machine learning, time series analysis, circuit testing, computational biology, speech recognition and machine translation are some of them. In part I of this paper we survey these generative objects and study their definitions and properties. In part II, we will study the relation of probabilistic finite-state automata with other well known devices that generate strings as hidden Markov models and n-grams, and provide theorems, algorithms and properties that represent a current state of the art of these objects.

translation system

The dialogue system is a new application of speech recognition and understanding systems, with clear implications for linguistic knowledge. This knowledge is expressed in labels that point out the intention and semantic of the dialog turn of the user and the system. Determining this knowledge can be viewed as a pattern recognition problem: assigning the adequate labels to the turn. The labelling work is a complex task, so, in this work, we present a method for semiautomatic labelling of a dialog based on Finite-State Transducers which are learnt from correctly labeled dialogs. We will show that this tool provides high quality dialog labelling, that makes the labelling task easier for a human expert.