Scielo RSS <![CDATA[Polibits]]> http://www.scielo.org.mx/rss.php?pid=1870-904420100001&lang=es vol. num. 41 lang. es <![CDATA[SciELO Logo]]> http://www.scielo.org.mx/img/en/fbpelogp.gif http://www.scielo.org.mx <![CDATA[<b>Editorial</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100001&lng=es&nrm=iso&tlng=es <![CDATA[<b>Spoken to Spoken vs. Spoken to Written</b>: <b>Corpus Approach to Exploring Interpreting and Subtitling</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100002&lng=es&nrm=iso&tlng=es The need for corpora of interpreting discourse in translation studies is gradually increasing. The research of AV translation is another rapidly developing sphere, thus corpora of subtitling and dubbing would also be quite useful. The main reason of the lack in such resources is the difficulty of obtaining data and the inevitability of manual data input. An interpreting corpus would be a collection of transcripts of speech in two or more languages with part of the transcripts aligned. The subtitling and dubbing corpora can be designed using the same principles. The structure of the corpus should reflect the polyphonic nature of the data. Thus, markup becomes extremely important in these types of corpora. The research presented in this paper deals with corpora of Finnish-Russian interpreting discourse and subtitling. The software package developed for processing of the corpora includes routines specially written for studying speech transcripts rather than written text. For example, speaker statistics function calculates number of words, number of pauses, their duration, average speech tempo of a certain speaker. <![CDATA[<b>Semi-Automatic Parallel Corpora Extraction from Comparable News Corpora</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100003&lng=es&nrm=iso&tlng=es The parallel corpus is a necessary resource in many multi/cross lingual natural language processing applications that include Machine Translation and Cross Lingual Information Retreival. Preparation of large scale parallel corpus takes time and also demands the linguistics skill. In the present work, a technique has been developed that extracts parallel corpus between Manipuri, a morphologically rich and resource constrained Indian language and English from a comparable news corpora collected from the web. A medium sized Manipuri-English bilingual lexicon and another list of Manipuri-English transliterated entities have been developed and used in the present work. Using morphological information for the agglutinative and inflective Manipuri language, the alignment quality based on similarity measure is further improved. A high level of performance is desirable since errors in sentence alignment cause further errors in systems that use the aligned text. The system has been evaluated and error analysis has also been carried out. The technique shows its effectiveness in Manipuri-English language pair and is extendable to other resource constrained, agglutinative and inflective Indian languages. <![CDATA[<b>A Natural Language Dialogue System for Impression-based Music Retrieval</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100004&lng=es&nrm=iso&tlng=es Impression-based music retrieval is the best way to find pieces of music that suit the preferences, senses, or mental states of users. A natural language interface (NLI) is more useful and effective than a graphical user interface for impression-based music retrieval since an NLI interprets users' spontaneous input sentences to represent musical impressions and generates query vectors for music retrieval. Existing impression-based music retrieval systems, however, have no dialogue capabilities for modifying the most recently used query vector. We evaluated a natural language dialogue system we developed that deals not only with 164 impression words but also with 14 comparative expressions, such as "a little more" and "more and more," and, if necessary, modifies the most recently used query vector through a dialogue. We also evaluated performance using 35 participants to determine the effectiveness of our dialogue system. <![CDATA[<b>Retrieving Lexical Semantics from Multilingual Corpora</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100005&lng=es&nrm=iso&tlng=es This paper presents a technique to build a lexical resource used for annotation of parallel corpora where the tags can be seen as multilingual 'synsets'. The approach can be extended to add relationships between these synsets that are akin to WordNet relationships of synonymy and hypernymy. The paper also discusses how the success of this approach can be measured. The reported results are for English, German, French, and Greek using the Europarl parallel corpus. <![CDATA[<b>Análisis de Opiniones con Ontologías</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100006&lng=es&nrm=iso&tlng=es En este artículo presentamos un trabajo sobre análisis de opiniones llevado a cabo gracias a un enfoque innovador basado en fusión de ontologías. El objetivo de este trabajo es permitir que dos empresas puedan intercambiar y compartir los resultados de los análisis de las opiniones de sus productos y servicios.<hr/>In this paper we present a work dealing with opinion analysis carried out thanks to an innovative approach based on ontology matching. The aim of this work is to allow two enterprises to share and merge the results of opinion analyses on their own products and services. <![CDATA[<b>Aprendizaje de Reglas Encadenas para la Creación de Grafos Conceptuales</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100007&lng=es&nrm=iso&tlng=es El documento presenta una forma de aprendizaje sobre reglas encadenadas para la generación de nuevas reglas que al aplicarlas deberán permitir la construcción de Grafos Conceptuales. La propuesta se basa en la inclusión de reglas encadenadas y de de un método supervisado. Las reglas son definidas sobre la base de tres elementos: a)La marcación o rol que ocupa la palabra dentro de la oración, b)El estándar de Grafos Conceptuales y c) La definición de un Objeto que funciona como una caja de negra de Grafos. Las pruebas se realizaron sobre algunos de los textos correspondientes a los títulos y comentarios que hacen parte de la colección de imágenes médicas del ImageClefmed del 2008. Para la realización de las marcas se utilizó el metatesauro UMLS y la herramienta MMTx y para los procesos de clasificación se uso el Weka. Como resultado se estiman nuevas reglas. <![CDATA[<b>On a Framework for Complex and ad hoc Event Management over Distributed Systems</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100008&lng=es&nrm=iso&tlng=es Internet-based communications have amazingly evolved in recent years. As a consequence, the number - and complexity - of distributed systems which provide access to services and applications has dramatically increased. As long as these services have been extended to support an increasing number of communication media (voice, audio, video, ...) and systems, ad hoc communication protocols and methodologies have been designed and developed. Given the autonomy of available services and applications, distributed systems generally rely on event-based communications for integrating these resources. However, a general model for the management of event-based communications, suitable for complex and ad hoc event processing as well as for the generic publish/subscribe messaging paradigm, is still missing. This paper presents a general and flexible event detection and processing framework which can be adapted based on specific requirements and situations. Within the framework, the main aspects of event management over distributed systems are treated, such as event definition, detection, production, notification and history management. Other aspects such as event composition, are also discussed. The goal of the paper is to provide a common paradigm for event-based communications, providing at the same time new advantages with respect to the existing standards such as composition, interoperability and dynamic adaptability. <![CDATA[<b>Sistema Informático para Análisis de Cardiopatía Holter</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100009&lng=es&nrm=iso&tlng=es El presente artículo, muestra los avances de desarrollo de una herramienta médica relacionada con los estudios de cardiopatía que esté disponible y al alcance de cualquier hospital, centro médico, o consultorio médico, que sea accesible en el costo, de fácil manejo y comprensible. Como un beneficio para el paciente, este proyecto le permitiría tener un mayor acceso a este tipo de estudios. Este proyecto también permite apoyar al médico profesional en cuanto a obtener en ciertos casos, un posible diagnóstico.<hr/>This paper presents the development of a medical tool related to cardiopathy studies that is available and accessible to any hospital, medical center, or doctor's office, which is accessible at low cost, user friendly and understandable. As a benefit for patients, this project allows major accessibility of the corresponding medical studies. This project also allows to the medical professional obtaining in certain cases a possible diagnosis. <![CDATA[<b>Predicción de Fallos en Redes IP empleando Redes Neuronales Artificiales</b>]]> http://www.scielo.org.mx/scielo.php?script=sci_arttext&pid=S1870-90442010000100010&lng=es&nrm=iso&tlng=es El presente artículo describe la implementación de un sistema de predicción de fallos en redes LAN (fallos de timeout y rechazo en las conexiones), utilizando redes neuronales artificiales Perceptrón Multicapa. Se describe como se implementó el sistema, las pruebas realizadas para la selección de los parámetros propios de la red neuronal, como del algoritmo de entrenamiento y los resultados de evaluación obtenidos.<hr/>The paper presents the implementation of a system for predicting failures in LAN (timeout failure and rejection of connections), using neural networks (multilayer perceptron). It describes the implementation of the system, experiments conducted for the selection of specific parameters of the neural network, training algorithm and evaluation results.