Hemos analizado las alineaciones a nivel de oración de dos corpus paralelos de textos originales y sus simplificaciones creados con diferentes objetivos. Hemos clasificado las alineaciones que se observan y diseñado un algoritmo de clasificación capaz de predecir si las…

El presente trabajo muestra la evaluación cuantitativa y cualitativa de un grupo de analizadores de constituyentes y de dependencias con el objetivo de ser usados en el desarrollo de una métrica automática basada en conocimiento para evaluar la salida de…

This work presents the main theories and models formulated with the purpose of offering a global overview on the acquisition of knowledge and skills involved in the initial development of expert competence. Setting from this background, we developed an empirical…

We develop a theory to explain the transition from stagnation to modern growth. We focus on the forces that shaped the evolution of total factor productivity in agriculture and manufacturing across history. More specifically, we build a multisector model of…

The extension to new languages is a well known bottleneck for rule-based systems. Considerable human effort, which typically consists in re-writing from scratch huge amounts of rules, is in fact required to transfer the knowledge available to the system from…

This paper presents the automatic extension to other languages of TERSEO, a knowledge-based system for the recognition and normalization of temporal expressions originally developed for Spanish. TERSEO was first extended to English through the automatic translation of the temporal expressions.…

The Answer Validation Exercise (AVE) is a pilot track within the Cross-Language Evaluation Forum (CLEF) 2006. The AVE competition provides an evaluation frame-
work for answer validations in Question Answering (QA). In our participation in AVE, we propose a system…

Adaptive websites usually change as effect of user navigational actions. Most current web engineering approaches (which consider personalization) allow to detect basic user browsing behaviour (e.g. user click on a link) but don’t consider the definition of (complex) behaviour events…

When training hidden-Markov-model-based part-of-speech (PoS) taggers involved in machine translation systems in an unsupervised manner the use of target-language information has proven to give better results than the standard Baum-Welch algorithm. The target-language-driven training algorithm proceeds by translating every possible…

This paper describes the development of an image retrieval
system that combines probabilistic and ontological information1. The
process is divided in two different stages: indexing and retrieval. Three
information flows have been created with different kind of information
each one:…