Isabel Galiano

Application of OSTIA to Machine Translation Tasks

A new application of the Onward Subsequential Transducer Inference Algorithm (OSTIA) is presented. Limited-domain Machine Translation tasks have been defined from a conceptually constrained task which was recently proposed within the field of Cognitive Science. Large corpora of English-to-Spanish and English-to-German translations have been generated, and exhaustive experiments have been carried out to test the ability of OSTIA to learn these translations. The success of the results show the usefulness of formal learning techniques in limited-domain Machine Translation tasks.

ON THE USE OF THE MORPHIC GENERATOR GRAMMATICAL INFERENCE (MGGI) METHODOLOGY IN AUTOMATIC SPEECH RECOGNITION

Recently, a new methodology, referred to as “Morphic Generator Grammatical Inference” (MGGI), has been introduced as a step towards a general methodology for the inference of regular languages. In this paper we consider the application of this methodology to a real problem of automatic speech recognition, thus allowing (and also requiring) the proposed problem to be properly formulated within the canonical framework of syntactic pattern recognition. The results show both the viability and appropriateness of the application of MGGI to the problem considered.

Applying Dialogue Constraints to the Understanding Process in a Dialogue System

In this paper, we present an approach to the estimation of a dialogue- dependent understanding component of a dialogue system. This work is developed in the framework of the Basurde Spanish dialogue system, which answers queries about train timetables by telephone in Spanish. A modelization which is specific to each dialogue state is proposed to improve the behaviour of the understanding process. Some experimental results are presented.

ACOUSTIC-PHONETIC DECODING OF SPANISH CONTINUOUS SPEECH

The design of current acoustic-phonetic decoders for a specific language involves the selection of an adequate set of sublexical units, and a choice of the mathematical framework for modelling the corresponding units. In this work, the baseline chosen for continuous Spanish speech consists of 23 sublexical units that roughly correspond to the 24 Spanish phonemes. The process of selection of such a baseline was based on language phonetic criteria and some experiments with an available speech corpora. On the other hand, two types of models were chosen for this work, conventional Hidden Markov Models and Inferred Stochastic Regular Grammars. With these two choices we could compare classical Hidden Markov modelling where the structure of a unit-model is deductively supplied, with Grammatical Inference modelling where the baseforms of model-units are automatically generated from training samples. The best speaker-independent phone recognition rate was 64% for the first type of modelling, and 66% for the second type.

Learning structural models of subword units through grammatical inference techniques

The authors propose obtaining the structure of phonetic units from training samples of speech automatically by using two specific grammatical inference (GI) algorithms: the error correcting GI algorithm and the morphic generator GI (MGGI) methodology. They describe the adequacy of the properties and capabilities of both methods for the modeling of subword units of speech (such as phonemes). They also report preliminary results obtained in their application to a continuous speech recognition, task. The results obtained with the semicontinuous MGGI methodology are shown to be very encouraging and can be improved with the use of some phonological grammar.<<ETX>>

Multi-speaker experiments with the morphic generator grammatical inference methodology

Grammatical Inference (GI) is the learning or model estimation phase required by any Syntactic approach to Pattern Recognition (PR). Some fundamental results on GI have been known since the 60’s through the works by Gold (1967) and Feldman (1972), which stablished that the decidability of any (even regular) GI problem depends largely upon the avaibility of both an adequate positive sample R+ of strings known to have been generated by the unknown Grammar, and an equally adequate negative sample R- of strings not generated by that Grammar. Despite these results being commonly recognized, taking into account negative samples, lead, in general to intractable GI problems (see /Angluin,78/) and, consequently, most recent works on GI only use positive samples, an aim just at giving practical solutions to specific PR problems (see eg. /Angluin,83/ /Fu,75/). Clearly, this paradigm is not a very appealing one, and some general methodology seems to be strongly required.

A hybrid approach to the development of dialogue systems directed by semantics

In this work we present an approach to the development of the BASURDE1 dialogue system, which answers telephone queries about railway timetables in Spanish. We will focus on the understanding and dialogue components which are modeled under a stochastic framework. The preliminary results from semantic and dialogue interpretations of user dialogue turns are also included in this work.

Modelling Phone-Context in Spanish by Using SCMGGI Models

The incorporation of context modelling to a Spanish Inferred Stochastic Regular Grammar -based continuous acoustic phonetic decoder, lead to a Speaker-Independent recognition phone accuracy of 75% and 72% for the Vocabulary Dependent and the Vocabulary Independent tests, respectively. The major novelty of this work is the modelling approach chosen in order to tackle the general problem of context-modelling: stochastic regular grammars inferred automatically from speech samples via the Semi-Continuous Morphic Generator Grammatical Inference methodology.