Language understanding and subsequential transducer learning

Castellanos, Antonio Javier Martín; Vidal, Enrique; Varó, Miguel Ángel; Oncina, José

doi:10.1006/csla.1998.0045

Cited by 13 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models are known as domain and range language models, respectively. A version of OSTIA called OSTIA-DR (Oncina & Varó, 1996;Castellanos et al, 1998) enforces these restrictions in the learning process. N -grams (Jelinek, 1998), generally trained from the source and target sentences in the given corpus, are usually adopted as domain and range language models for OSTIA-DR.…”

Section: Traditional Syntactic Pattern Recognition Paradigm: Ostiamentioning

confidence: 99%

Learning finite-state models for machine translation

Casacuberta

Vidal

2006

Mach Learn

View full text Add to dashboard Cite

In formal language theory, finite-state transducers are well-know models for simple "input-output" 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 finitestate 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 inputoutput 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.

show abstract

Section: Traditional Syntactic Pattern Recognition Paradigm: Ostiamentioning

confidence: 99%

Learning finite-state models for machine translation

Casacuberta

Vidal

2006

Mach Learn

View full text Add to dashboard Cite

show abstract

“…The algorithm has been also tested with an extension [Castellanos et al, 1998[Castellanos et al, , 1994] of a pseudo-natural task proposed by Feldman et al [Feldman et al, 1990]. The original task consisted of descriptions of simple two-dimensional visual scenes involving a few geometric objects with different shape, shade and size, and located in different relative positions.…”

Section: Feldman Taskmentioning

confidence: 99%

Optimum algorithm to minimize human interactions in sequential Computer Assisted Pattern Recognition

Oncina

2009

Pattern Recognition Letters

View full text Add to dashboard Cite

Given a Pattern Recognition task, Computer Assisted Pattern Recognition can be viewed as a series of solution proposals made by a computer system, followed by corrections made by a user, until an acceptable solution is found. For this kind of systems, the appropriate measure of performance is the expected number of corrections the user has to make.In the present work we study the special case when the solution proposals have a sequential nature. Some examples of this type of tasks are: language translation, speech transcription and handwriting text transcription. In all these cases the output (the solution proposal) is a sequence of symbols. In this framework it is assumed that the user corrects always the first error found in the proposed solution. As a consequence, the prefix of the proposed solution before the last error correction can be assumed error free in the next iteration.Nowadays, all the techniques in the literature relies in proposing, at each step, the most probable suffix given that a prefix of the "correct" output is already known. Usually the computation of the conditional most probable output is an NP-Hard or an undecidable problem (and then we have to apply some approximations) or, in some simple cases, complex dynamic programming techniques should be used (usualy some variant of the Viterbi algorithm).In the present work we show that this strategy is not optimum when we are interested in minimizing the number of human interactions. Moreover we describe the optimum strategy that is simpler (and usually faster) to compute.

show abstract

“…SSTs and OSTIA have been successfully applied to different translation tasks: Roman numerals to their decimal representations, numbers written in English to their Spanish spelling (Oncina, 1991) and Spanish sentences describing simple visual scenes to corresponding English and German sentences (Castellanos et al, 1994). They have also been applied to language understanding tasks (Castellanos et al, 1993;Pieraccini et al, 1993).…”

Section: Learning Subsequential Transducersmentioning

confidence: 99%

“…The comprehension task was studied by Oncina et al (Castellanos et al, 1993). They used English sentences, with a more complex version of the Feldman task domain and more complex semantic representations than we use.…”

Section: Languages #States #Edgesmentioning

confidence: 99%

Experiments using Ostia for a language production task

Angluin

Becerra-Bonache

2009

Proceedings of the EACL 2009 Workshop on Computational Linguistic Aspects of Grammatical Inference - CLAGI '09

View full text Add to dashboard Cite

The phenomenon of meaning-preserving corrections given by an adult to a child involves several aspects: (1) the child produces an incorrect utterance, which the adult nevertheless understands, (2) the adult produces a correct utterance with the same meaning and (3) the child recognizes the adult utterance as having the same meaning as its previous utterance, and takes that as a signal that its previous utterance is not correct according to the adult grammar. An adequate model of this phenomenon must incorporate utterances and meanings, account for how the child and adult can understand each other's meanings, and model how meaning-preserving corrections interact with the child's increasing mastery of language production. In this paper we are concerned with how a learner who has learned to comprehend utterances might go about learning to produce them. We consider a model of language comprehension and production based on finite sequential and subsequential transducers. Utterances are modeled as finite sequences of words and meanings as finite sequences of predicates. Comprehension is interpreted as a mapping of utterances to meanings and production as a mapping of meanings to utterances. Previous work (Castellanos et al., 1993; Pieraccini et al., 1993) has applied subsequential transducers and the OSTIA algorithm to the problem of learning to comprehend language; here we apply them to the problem of learning to produce language. For ten natural languages and a limited domain of geometric shapes and their properties and relations we define sequential transducers to produce pairs consisting of an utterance in that language and its meaning. Using this data we empirically explore the properties of the OSTIA and DD-OSTIA algorithms for the tasks of learning comprehension and production in this domain, to assess whether they may provide a basis for a model of meaning-preserving corrections.

show abstract

Language understanding and subsequential transducer learning

Cited by 13 publications

References 25 publications

Learning finite-state models for machine translation

Learning finite-state models for machine translation

Optimum algorithm to minimize human interactions in sequential Computer Assisted Pattern Recognition

Experiments using Ostia for a language production task

Contact Info

Product

Resources

About