Extracción automática de terminología multilingüe empleada en la implementación de tecnologías de la información y las comunicaciones, aplicada a castellano e inglés
No Thumbnail Available
Date
2025-04-01
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Pontificia Universidad Católica del Perú
Acceso al texto completo solo para la Comunidad PUCP
Abstract
Actualmente se observa una presión creciente sobre las organizaciones para
implementar herramientas de Inteligencia Artificial y otros tipos de Tecnologías de la
Información y las Comunicaciones –TIC. Sin embargo, la rápida evolución de las
TIC y la carencia de metodologías de implementación actualizadas en varios
idiomas dificultan el avance.
El objetivo del presente trabajo es facilitar la actualización de las metodologías de
implementación. Para esto se elaboran listas de términos, en castellano e inglés,
para la implementación de dos tipos de TIC con la ayuda de varios modelos
especializados en la Extracción Automática de Términos – EAT. Las listas de
términos luego pueden ser usadas para afinar modelos de clasificación de textos,
elaboración de resúmenes y traducción, que a su vez pueden ayudar en la
actualización de las metodologías de implementación.
Las listas de términos fueron elaboradas mediante una metodología incremental,
combinando el uso de modelos y revisiones manuales. Se probaron 5 modelos pre-
entrenados de tipo BERT y uno XLNet con resultados superiores a los de
investigaciones similares, apoyando la posibilidad de hacer EAT en temas e idiomas
para los cuales se cuente con pocos datos de entrenamiento.
Se plantea una forma de medir la similitud entre listas de términos. Se observa que
los corpus en diferentes idiomas sobre un mismo tema pueden tener enfoques
diferentes, sugiriendo que el conocimiento se enriquecería si se tomaran como
insumo juntas publicaciones en varios idiomas.
Una métrica propuesta para evaluar la capacidad de un modelo para identificar
términos no vistos antes estaría mostrando que esta capacidad no dependería
solamente de identificar palabras vistas anteriormente.
Currently, a growing pressure on organizations to implement Artificial Intelligence tools and other types of Information and Communication Technologies (ICT) is observed. However, the rapid evolution of ICTs and the lack of up-to-date implementation methodologies in several languages hinder progress. The goal of this work is to make a contribution to facilitate the updating of implementation methodologies. To this end, lists of terms in Spanish and English are created for the implementation of two types of ICT using several models trained in Automatic Term Extraction (ATE). These lists of terms can later on be used to fine- tune text classification, abstracting, and translation models, which in turn can help updating implementation methodologies. Term lists were created using an incremental methodology, combining the use of models and manual reviews. 5 pre-trained BERT models and one XLNet model were tested with results superior to previous research, providing support to the possibility of doing ATE in topics and languages for which there is little training data. A method to measure the similarity between lists of terms is proposed. Experiments results indicate that corpora in different languages on the same topic could have different approaches, suggesting that knowledge would be enriched if publications in several languages were used together as sources. A metric proposed to evaluate a model's ability to identify previously unseen terms would be showing that this ability would not depend solely on identifying previously viewed words.
Currently, a growing pressure on organizations to implement Artificial Intelligence tools and other types of Information and Communication Technologies (ICT) is observed. However, the rapid evolution of ICTs and the lack of up-to-date implementation methodologies in several languages hinder progress. The goal of this work is to make a contribution to facilitate the updating of implementation methodologies. To this end, lists of terms in Spanish and English are created for the implementation of two types of ICT using several models trained in Automatic Term Extraction (ATE). These lists of terms can later on be used to fine- tune text classification, abstracting, and translation models, which in turn can help updating implementation methodologies. Term lists were created using an incremental methodology, combining the use of models and manual reviews. 5 pre-trained BERT models and one XLNet model were tested with results superior to previous research, providing support to the possibility of doing ATE in topics and languages for which there is little training data. A method to measure the similarity between lists of terms is proposed. Experiments results indicate that corpora in different languages on the same topic could have different approaches, suggesting that knowledge would be enriched if publications in several languages were used together as sources. A metric proposed to evaluate a model's ability to identify previously unseen terms would be showing that this ability would not depend solely on identifying previously viewed words.
Description
Keywords
Procesamiento de lenguaje natural (Computación), Aprendizaje automático (Inteligencia artificial), Tecnología de la información, Minería de textos
Citation
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwised noted, this item's license is described as info:eu-repo/semantics/openAccess