In the present paper I describe the conceptual level of representation of a database, currently in development, which aims at fulfilling the Functional-Lexematic model. I will concentrate on the semantic component, as it is central for the theory of Functional…

In this paper, a supervised learning system of word sense disambiguation is presented. It is based on conditional maximum entropy models. This system acquires the linguistic knowledge from an annotated corpus and this knowledge is represented in the form of…

En este artículo se presenta el trabajo que se está realizando para la llamada
ontologización superficial de WordNet, una estructura orientada a superar muchos de los
problemas estructurales de la popular base de conocimiento léxico. El resultado esperado es un

En este trabajo se investigan nuevas distancias entre fonemas y entre palabras que se
han usado para predecir si dos palabras del vocabulario de un sistema de reconocimiento del
habla se van a confundir o no. La distancia entre palabras…

This paper presents the main
characteristics of an Agent-based Architecture
for the design and implementation
of a Spoken Dialogue System. From
a theoretical point of view, the system is
based on the Information State Update
approach, in particular, the system…

This paper presents an algorithm for identifying noun phrase antecedents of third person personal
pronouns, demonstrative pronouns, reflexive pronouns, and omitted pronouns (zero pronouns)
in unrestricted Spanish texts. We define a list of constraints and preferences for different types
of…

Novelty is a concept of great importance in the writing of a research paper, given that the author has to persuade the audience of the news value of the reported research, which makes it worth publishing. In this paper I…

Apart from speculating about a series of issues open to debate, such as the dark side of progress and globalization or the conflict between science and morality,
Margaret Atwood's Oryx and Crake (2003) offers a feasible insight into the state…

The ability of building robust semantic space representations of environments is crucial for the development of truly autonomous robots. This task, inherently connected with cognition, is traditionally achieved by training the robot with a supervised learning phase. We argue that…

The exponential increase of subjective, user-generated content since the birth of the Social Web, has led to the necessity of developing automatic text processing systems able to extract, process and present relevant knowledge. In this paper, we tackle the Opinion…