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.

A technique to infer finite-state transducers is proposed in this work. This technique is based on the formal relations between finite-state transducers and regular grammars. The technique consists of: 1) building a corpus of training strings from the corpus of training pairs; 2) inferring a regular grammar and 3) transforming the grammar into a finite-state transducer.

Nowadays, hidden Markov models (HMMs) and n-grams are the basic components of the most successful speech recognition systems. In such systems, HMMs (the acoustic models) are integrated into a n-gram or a stochastic finite-state grammar (the language model). Similar models can be used for speech translation, and HMMs (the acoustic models) can be integrated into a finite-state transducer (the translation model). Moreover, the translation process can be performed by searching for an optimal path of states in the integrated network. The output of this search process is a target word sequence associated to the optimal path. In speech translation, HMMs can be trained from a source speech corpus, and the translation model can be learned automatically from a parallel training corpus.

In this paper we discuss the use of cascaded finite state transducers for machine translation. A num- ber of small, dedicated transducers is applied to convert sentence pairs from a bilingual corpus into generalized translation patterns. These patterns, together with the trans- ducers are then used as a hierarchi- cal translation memory for fully au- tomatic translation. Results on the German-English VERBMOBIL corpus are given.

EUTRANS system is a telephone speech input translation prototype capable of translating telephone calls from one language to another. It assumes a human to human communication, each one speaking a different language, assisted by a system with translation capabilities. The prototype has been developed as a demonstrator for the European project with the same name. EUTRANS achieves a response time close to real time for speaker-independent, medium complexity tasks (a few thousand words) and offers competitive accuracy. The acoustic, language and translation models are finite-state networks that are automatically learnt form training samples, this makes the system easily adaptable to news tasks. It runs on a standard PC with audio capability and a cheap modem. The system is currently available for two translation tasks: FUB task (Italian-English) and Traveler task (SpanishEnglish) .

translation system

Current statistical machine translation systems are based on phrases heuristically extracted. In this work, a new approach for phrase-based statistical machine translation is proposed which can properly described as a hidden Markov model. The proposed model, its associated forward and backward recurrences, and its EMbased maximum likelihood estimation is detailed. Empirical results are reported on a spanish-english translation task. 1

EuTrans is a telephone speech input translation prototype capable of translating telephone calls from one language to another. It assumes a human to human communication, each one speaking a dierent language, assisted by a system with translation capabilities. The prototype has been developed as a demonstrator for the European project with the same name. EuTrans achieves a response time close to real time for medium complexity tasks (a few thousand words), speaker independent and oers competitive accuracy. It needs a standard PC with audio capability and a cheap modem. The system is currently available for two translation tasks: FUB task (Italian-English) and Traveler task (Spanish-English).

Machine translation can play an important role nowadays, helping communication between people. One of the projects in this field is TransType2 . Its purpose is to develop an innovative, interactive machine translation system. TransType2 aims at facilitating the task of producing high-quality translations, and make the translation task more cost-effective for human translators.

In this work we implement a confidence estimation system based on a Naive Bayes classifier, by using the maximum entropy paradigm. The model takes information from various sources including a set of scores which have proved to be useful in confidence estimation tasks. Two different approaches are modeled. First a basic model which takes advantages of smoothing techniques used in a previous work, and second an optimized model, which is designed to hold a set of very few but essential characteristics of the model, without decrease in the performance. A considerably reduction in the number of parameters is obtained compared to the basic model. Both models are evaluated with two different corpora and compared to a model previously developed. Index Terms — confidence estimation, maximum entropy, confidence measures, speech recognition. 1.