Salvador Climent

The top-down strategy for building EuroWordNet: vocabulary coverage, base concepts and top ontology

This paper describes two fundamental aspects in the process of building of the EuroWordNet database. In EuroWordNet we have chosen for a flexible design in which local wordnets are built relatively independently as language-specific structures, which are linked to an Inter-Lingual-Index (ILI). To ensure compatibility between the wordnets, a core set of common concepts has been defined that has to be covered by every language. Furthermore, these concepts have been classified via the ILI in terms of a Top Ontology of 63 fundamental semantic distinctions used in various semantic theories and paradigms. This paper first discusses the process leading to the definition of the set of Base Concepts, and the structure and the rationale of the Top Ontology.

Bilingual Newsgroups in Catalonia: A Challenge for Machine Translation

This paper presents a linguistic analysis of a corpus of messages written in Catalan and Spanish, which come from several informal newsgroups on the Universitat Oberta de Catalunya (Open University of Catalonia; henceforth, UOC) Virtual Campus. The surrounding environment is one of extensive bilingualism and contact between Spanish and Catalan. The study was carried out as part of the INTERLINGUA project conducted by the UOCs Internet Interdisciplinary Institute (IN3). Its main goal is to ascertain the linguistic characteristics of the e-mail register in the newsgroups in order to assess their implications for the creation of an online machine translation environment. The results shed empirical light on the relevance of characteristics of the e-mail register, the impact of language contact and interference, and their implications for the use of machine translation for CMC data in order to facilitate cross-linguistic communication on the Internet.

Parallel corpora for wordnet construction: machine translation vs. automatic sense tagging

In this paper we present a methodology for WordNet construction based on the exploitation of parallel corpora with semantic annotation of the English source text. We are using this methodology for the enlargement of the Spanish and Catalan versions of WordNet 3.0, but the methodology can also be used for other languages. As big parallel corpora with semantic annotation are not usually available, we explore two strategies to overcome this problem: to use monolingual sense tagged corpora and machine translation, on the one hand; and to use parallel corpora and automatic sense tagging on the source text, on the other. With these resources, the problem of acquiring a WordNet from parallel corpora can be seen as a word alignment task. Fortunately, this task is well known, and some aligning algorithms are freely available.

An Answering System for Questions Asked by Students in an e-Learning Context

In this article, we present a system that helps tutors to answer questions asked by their students at an online university: the Open University of Catalonia (UOC). Communication between UOC students and their tutors is fully online; students ask questions and tutors answer them by e-mail. The system, which is currently being developed at the UOC’s Office of Learning Technologies (OLT), aims to find multilingual contexts with useful information to enable tutors to give fast, appropriate answers to students. These contexts are extracted from course learning materials, from previous messages posted on subject discussion boards, and also from articles and other sources of information available on the Internet. Apart from helping tutors to find better answers, the system is also useful for updating their knowledge and contributing to their lifelong learning.ResumenEn este artículo presentamos un sistema que ayuda a los docentes a responder las preguntas de sus alumnos en una universidad virtual, concretamente la Universitat Oberta de Catalunya (UOC). La comunicación entre alumno y docente se realiza de forma totalmente virtual: las preguntas y las respuestas se formulan y contestan mediante correo electrónico. El sistema, que se está desarrollando en el Área de Tecnología Educativa de la UOC, tiene como principal objetivo encontrar contextos multilingües con información útil para responder al estudiante de forma rápida y adecuada. Los contextos se extraen de los materiales del curso, los foros de participación de la asignatura, artículos y otras fuentes de información disponibles en internet. Además de ayudar a los docentes a encontrar mejores respuestas, el sistema también es útil para actualizar sus conocimientos y desarrollar su aprendizaje permanente.

Ús de la Viquipèdia per al desenvolupament de recursos lingüístics: el WordNet 3.0 català i castellà

Digithum, no. 14 (May, 2012) | ISSN 1575-2275 A scientific e-journal published by the Arts and Humanities Department Abstract We describe the state of the art in the use of Wikipedia for natural language processing tasks and also describe three applications of our own that enrich a powerful language resource: WordNet version 3.0 in Catalan and Spanish. Researchers have for many years sought applications that would take account of world knowledge in a more or less structured way, as this kind of knowledge has proven to be crucial to satisfactorily solving certain language processing tasks. Wikipedia may be the answer to the provision of this kind of information, as it is constantly updated and access is free.

Constitución de un corpus de semántica verbal del español: Metodología de anotación de núcleos argumentales

El presente articulo detalla la metodologia y el desarrollo del proyecto de desambiguacion semantica de los nucleos argumentales de SenSem, un corpus equilibrado constituido por 100 oraciones para cada uno de los 250 verbos mas frecuentes del espanol. El resultado, unido a desarrollos anteriores del proyecto, es un corpus ricamente etiquetado con informacion sintactica y semantica, conectado a una base de datos que recoge la informacion pertinente para cada sentido verbal, por lo que el recurso resultante es adecuado para estudios empiricos centrados en el verbo. Como resultado del proceso se presenta asimismo un analisis critico de WordNet 1.6 del espanol como recurso de anotacion lexico-semantica de corpus y una guia de criterios de anotacion, ambos de utilidad para tareas similares de etiquetado con WordNet.

MOMENT: Metáforas del trastorno mental grave. Análisis del discurso de personas afectadas y profesionales de la salud mental

El proyecto MOMENT pretende contribuir a mejorar la comprension del trastorno mental grave a partir del analisis del discurso de los dos grandes colectivos implicados, personas diagnosticadas y profesionales de la salud mental, aplicando como metodo de analisis la Teoria de la Metafora Conceptual y la linguistica de corpus. En este marco, se constituira un corpus anotado manualmente de testimonios en primera persona de ambos colectivos, que a su vez pueda servir como banco de experimentacion en deteccion automatica de metaforas. De esta manera, se pretende avanzar tanto en la deteccion y anotacion manual de metaforas, como en la deteccion computacional. Desde un punto de vista social, el objetivo del proyecto es identificar y sistematizar las concepciones y asunciones dominantes sobre el trastorno mental grave, asi como promover el cambio de posibles discursos que nieguen la capacidad agentiva de las personas diagnosticadas.

Semantics of portions and partitive nouns for NLP

This paper describes a system of representation of nouns denoting portions, segments and relative quantities of entities, in order to account for this case of part-whole relationship. The semantics of both constructions denoting portions and nouns used to build them are discussed and eventually formalised in a unification-based formalism (LKB-LRL) in terms of Pustejovskys Theory of Qualia and Jackendoffs Conceptual Semantics.