Catálogo de publicaciones - libros

A preliminary experimental result is reported on language identification tasks by Recurrent Self-Organization Maps (RSOM) with a context map layer, using English part-of-speech strings of variable length. With subsymbolic processing, RSOM suprasymbolically sublimed syntactic rules into a topological configuration.

In this paper we will present opportunities for applying graph based linguistic formalisms for computer automatic understanding of meaning of wrist medical images. Thanks to the proposed method we can understand the merit content of the image even if the form of the image is very different from any known pattern. It seems that in the near future such technique may become one of the effective tools for semantic interpreting, and computer perception of visual medical data.

We propose a new methodology for ethology in terms of automata induction. Recent studies on Bengalese finch reported unique features of its songs. As opposed to most other songbirds, the songs of the Bengalese finch are neither monotonous nor random; they can be represented by a finite automaton, which we call song syntax [3]. Juvenile finches learn songs from their fathers during a critical period. The song learning has a similarity to the grammatical inference from positive samples, which is known as Angluin’s algorithm [1]. This is an induction algorithm for inferring certain subclasses of regular languages, which are known as k -reversible languages, from positive samples, where k = 0,1,2,.... A regular language is k -reversible under the following condition: whenever two prefixes whose last k words match have a tail in common, then these prefixes have all tails in common. For each k , Angluin’s algorithm provides a finite automaton that accepts the smallest k -reversible language, including the given finite positive sample within polynomial time.

k -reversible languages are regular ones that offer interesting properties under the point of view of identification of formal languages in the limit. Different methods have been proposed to identify k -reversible languages in the limit from positive samples. Non-regular language classes have been reduced to regular reversible languages in order to solve their associated learning problems. In this work, we present a hierarchy of reversible languages which can be characterized by some properties related to the set of terminal segments of the automata ( terminal distinguishability ). Terminal distinguishability is a property that has been previously used to characterize other language families which can be identified in the limit from positive data. In the present work we combine reversibility and terminal distinguishability in order to define a new hierarchy of regular languages which is highly related to the k -reversible hierarchy. We will provide an efficient method to identify any given language in the hierarchy from only positive examples.

In this article we present a syntax-based translation system, called TABL (Translation using Alignment-Based Learning). It translates natural language sentences by mapping grammar rules (which are induced by the Alignment-Based Learning grammatical inference framework) of the source language to those of the target language. By parsing a sentence in the source language, the grammar rules in the derivation are translated using the mapping and subsequently, a derivation in the target language is generated. The initial results are encouraging, illustrating that this is a valid machine translation approach.