Stochastic Finite-state Transducers Research Articles

An Investigation into Methodology and Metrics Employed to Evaluate the (Speech-to-Speech) Way in Translation Systems

Speech-to-speech translation is a challenging problem, due to poor sentence planning typically associated with spontaneous speech, as well as errors caused by automatic speech recognition. Based upon a statistically trained speech translation system, in this study, we try to investigate methodologies and metrics employed to assess the (speech-to-speech) way in translation systems. The speech translation is performed incrementally based on generation of partial hypotheses from speech recognition. Speech-input translation can be properly approached as a pattern recognition problem by means of statistical alignment models and stochastic finite-state transducers. Under this general framework, some specific models are presented. One of the features of such models is their capability of automatically learning from training examples. The speech translation system consists of three modules: automatic speech recognition, machine translation and text to speech synthesis. Many procedures for incorporation of speech recognition and machine translation have been projected. In this research, we want explore methodologies and metrics employed to assess the (speech-to-speech) way in translation systems.

Spoken dialog systems based on online generated stochastic finite-state transducers

In this paper, we present an approach for the development of spoken dialog systems based on the statistical modelization of the dialog manager. This work focuses on three points: the modelization of the dialog manager using Stochastic Finite-State Transducers, an unsupervised way to generate training corpora, and a mechanism to address the problem of coverage that is based on the online generation of synthetic dialogs. Our proposal has been developed and applied to a sport facilities booking task at the university. We present experimentation evaluating the system behavior on a set of dialogs that was acquired using the Wizard of Oz technique as well as experimentation with real users. The experimentation shows that the method proposed to increase the coverage of the Dialog System was useful to find new valid paths in the model to achieve the user goals, providing good results with real users.

Discriminative Reranking for Spoken Language Understanding

Spoken language understanding (SLU) is concerned with the extraction of meaning structures from spoken utterances. Recent computational approaches to SLU, e.g., conditional random fields (CRFs), optimize local models by encoding several features, mainly based on simple n-grams. In contrast, recent works have shown that the accuracy of CRF can be significantly improved by modeling long-distance dependency features. In this paper, we propose novel approaches to encode all possible dependencies between features and most importantly among parts of the meaning structure, e.g., concepts and their combination. We rerank hypotheses generated by local models, e.g., stochastic finite state transducers (SFSTs) or CRF, with a global model. The latter encodes a very large number of dependencies (in the form of trees or sequences) by applying kernel methods to the space of all meaning (sub) structures. We performed comparative experiments between SFST, CRF, support vector machines (SVMs), and our proposed discriminative reranking models (DRMs) on representative conversational speech corpora in three different languages: the ATIS (English), the MEDIA (French), and the LUNA (Italian) corpora. These corpora have been collected within three different domain applications of increasing complexity: informational, transactional, and problem-solving tasks, respectively. The results show that our DRMs consistently outperform the state-of-the-art models based on CRF.

GREAT: open source software for statistical machine translation

In this article, the first public release of GREAT as an open-source, statistical machine translation (SMT) software toolkit is described. GREAT is based on a bilingual language modelling approach for SMT, which is so far implemented for n-gram models based on the framework of stochastic finite-state transducers. The use of finite-state models is motivated by their simplicity, their versatility, and the fact that they present a lower computational cost, if compared with other more expressive models. Moreover, if translation is assumed to be a subsequential process, finite-state models are enough for modelling the existing relations between a source and a target language. GREAT includes some characteristics usually present in state-of-the-art SMT, such as phrase-based translation models or a log-linear framework for local features. Experimental results on a well-known corpus such as Europarl are reported in order to validate this software. A competitive translation quality is achieved, yet using both a lower number of model parameters and a lower response time than the widely-used, state-of-the-art SMT system Moses.

Statistical Approaches to Computer-Assisted Translation

Current machine translation (MT) systems are still not perfect. In practice, the output from these systems needs to be edited to correct errors. A way of increasing the productivity of the whole translation process (MT plus human work) is to incorporate the human correction activities within the translation process itself, thereby shifting the MT paradigm to that of computer-assisted translation. This model entails an iterative process in which the human translator activity is included in the loop: In each iteration, a prefix of the translation is validated (accepted or amended) by the human and the system computes its best (or n-best) translation suffix hypothesis to complete this prefix. A successful framework for MT is the so-called statistical (or pattern recognition) framework. Interestingly, within this framework, the adaptation of MT systems to the interactive scenario affects mainly the search process, allowing a great reuse of successful techniques and models. In this article, alignment templates, phrase-based models, and stochastic finite-state transducers are used to develop computer-assisted translation systems. These systems were assessed in a European project (TransType2) in two real tasks: The translation of printer manuals; manuals and the translation of the Bulletin of the European Union. In each task, the following three pairs of languages were involved (in both translation directions): English-Spanish, English-German, and English-French.

Learning finite-state models for machine translation

In formal language theory, finite-state transducers are well-know models for simple mappings between two languages. Even if more powerful, recursive models can be used to account for more complex mappings, it has been argued that the input-output relations underlying most usual natural language pairs can essentially be modeled by finite-state devices. Moreover, the relative simplicity of these mappings has recently led to the development of techniques for learning finite-state transducers from a training set of input-output sentence pairs of the languages considered. In the last years, these techniques have lead to the development of a number of machine translation systems. Under the statistical statement of machine translation, we overview here how modeling, learning and search problems can be solved by using stochastic finite-state transducers. We also review the results achieved by the systems we have developed under this paradigm. As a main conclusion of this review we argue that, as task complexity and training data scarcity increase, those systems which rely more on statistical techniques tend produce the best results.

Machine Translation with Inferred Stochastic Finite-State Transducers

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 very adequate 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 formal relations 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 E u Trans project.

Some approaches to statistical and finite-state speech-to-speech translation

Speech-input translation can be properly approached as a pattern recognition problem by means of statistical alignment models and stochastic finite-state transducers. Under this general framework, some specific models are presented. One of the features of such models is their capability of automatically learning from training examples. Moreover, the stochastic finite-state transducers permit an integrated architecture similar to one used in speech recognition. In this case, the acoustic models (hidden Markov models) are embedded into the finite-state transducers, and the translation of a source utterance is the result of a (Viterbi) search on the integrated network. These approaches have been followed in the framework of the European project E uT rans. Translation experiments have been performed from Spanish to English and from Italian to English in an application involving the interaction of a customer with a receptionist at the frontdesk of a hotel.

Some Statistical-Estimation Methods for Stochastic Finite-State Transducers

Formal translations constitute a suitable framework for dealing with many problems in pattern recognition and computational linguistics. The application of formal transducers to these areas requires a stochastic extension for dealing with noisy, distorted patterns with high variability. In this paper, some estimation criteria are proposed and developed for the parameter estimation of regular syntax-directed translation schemata. These criteria are: maximum likelihood estimation, minimum conditional entropy estimation and conditional maximum likelihood estimation. The last two criteria were proposed in order to deal with situations when training data is sparse. These criteria take into account the possibility of ambiguity in the translations: i.e., there can be different output strings for a single input string. In this case, the final goal of the stochastic framework is to find the highest probability translation of a given input string. These criteria were tested on a translation task which has a high degree of ambiguity.