Inference of k-testable languages in the strict sense and application to syntactic pattern recognition

Garcia, Pedro Castillo; Vidal, Enrique

doi:10.1109/34.57687

Cited by 153 publications

(118 citation statements)

References 27 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…The transcriptions of this partition were used for the perfect decoding experiment, and the results from the speech recognition experiment were used for the speech decoding experiment. In the speech recognition experiment, the training data was used to obtain acoustic models (Hidden Markov Models trained with the recorded speech signal) and the language model (a k-TTS automaton (García and Vidal (1990)) inferred from the preprocessed transcriptions without punctuation marks). The WER for this test partition was about 20%.…”

Section: Decoding Resultsmentioning

confidence: 99%

Statistical framework for a Spanish spoken dialogue corpus

Martínez-Hinarejos

Benedí

Granell

2008

Speech Communication

View full text Add to dashboard Cite

Section: Decoding Resultsmentioning

confidence: 99%

Statistical framework for a Spanish spoken dialogue corpus

Martínez-Hinarejos

Benedí

Granell

2008

Speech Communication

View full text Add to dashboard Cite

“…We promote the use of ktestable in the strict sense (k-TSS) grammars, which are a subset of regular grammars. Hence, the corresponding k-TSS stochastic finite-state automaton (SFSA) can be automatically learnt from positive samples making use of efficient algorithms based on a maximum likelihood approach (García and Vidal, 1990). k-TSS language models are considered to be the syntactic approach of the well known n-gram models.…”

Section: Learningmentioning

confidence: 99%

Joining linguistic and statistical methods for Spanish-to-Basque speech translation

Pérez

Torres

Casacuberta

2008

Speech Communication

View full text Add to dashboard Cite

To cite this version:Alicia Pérez, M. Inés Torres, Francisco Casacuberta. Joining linguistic and statistical methods for Spanish-to-Basque speech translation. Speech Communication, Elsevier : North-Holland, 2008, 50 (11-12) AbstractThe goal of this work is to develop a text and speech translation system from Spanish to Basque. This pair of languages shows quite odd characteristics as they differ extraordinarily in both morphology and syntax, thus, attractive challenges in machine translation are involved. Nevertheless, since both languages share official status in the Basque Country, the underlying motivation is not only academic but also practical.Finite-state transducers were adopted as basic translation models. The main contribution of this work involves the study of several techniques to improve probabilistic finite-state transducers by means of additional linguistic knowledge. Two methods to cope with both linguistics and statistics were proposed. The first one performed a morphological analysis in an attempt to benefit from atomic meaningful units when it comes to rendering the meaning from one language to the other. The second approach aimed at clustering words according to their syntactic role and used such phrases as translation unit. From the latter approach phrase-based finite-state transducers arose as a natural extension of classical ones.The models were assessed under a restricted domain task, very repetitive and with a small vocabulary. Experimental results shown that both morphological and syntactical approaches outperformed the baseline under different test sets and architectures for speech translation.

show abstract

“…The same holds for total subsequential functions (Oncina et al, 1993). Algorithms provided in these papers have been implemented to deal with practical problems in the fields of speech , pattern recognition (García & Vidal, 1990) and Automatic Translation (Castellanos et al, 1994). On the other hand no hardness results have been proven within this model, leaving open the question of the triviality of the model.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Untitled

Higuera

1997

Machine Learning

View full text Add to dashboard Cite

Abstract. When concerned about efficient grammatical inference two issues are relevant: the first one is to determine the quality of the result, and the second is to try to use polynomial time and space. A typical idea to deal with the first point is to say that an algorithm performs well if it infers in the limit the correct language. The second point has led to debate about how to define polynomial time: the main definitions of polynomial inference have been proposed by Pitt and Angluin. We return in this paper to a definition proposed by Gold that requires a characteristic set of strings to exist for each grammar, and this set to be polynomial in the size of the grammar or automaton that is to be learned, where the size of the sample is the sum of the lengths of all strings it includes. The learning algorithm must also infer correctly as soon as the characteristic set is included in the data. We first show that this definition corresponds to a notion of teachability as defined by Goldman and Mathias. By adapting their teacher/learner model to grammatical inference we prove that languages given by context-free grammars, simple deterministic grammars, linear grammars and nondeterministic finite automata are not identifiable in the limit from polynomial time and data.

show abstract

Inference of k-testable languages in the strict sense and application to syntactic pattern recognition

Cited by 153 publications

References 27 publications

Statistical framework for a Spanish spoken dialogue corpus

Statistical framework for a Spanish spoken dialogue corpus

Joining linguistic and statistical methods for Spanish-to-Basque speech translation

Untitled

Contact Info

Product

Resources

About