Natural language processing techniques for document retrieval in the biomedical domain

Document Retrieval in the biomedical domain has been broadening through time, as a consequence of the growth of the available biomedical literature. Therefore, there is an increasing number of researches made in this knowledge field especially focused on this Natural Language Processing application. Having such a big amount of data turns out to be beneficial for decision-making in this domain, but a sufficiently accurate document retrieval system is required. A large number of NLP techniques and models have been proposed for text matching, but few of them have been able to consider the variations of language and the relationship between distant words in texts. This work is focused on formulating a method based on graph structures for building up a Document Retrieval system for the biomedical domain, and comparing the obtained results with traditional Document Retrieval techniques. The graph-based methods were selected to prove the importance of analyzing the semantic, syntactic, and long-distant word relationships in texts. It will be demonstrated that through the graph's topology the system is capable of extracting the structural information of documents, which solves relevant issues that are faced in this research area.

• Autores: Zuluaga Cajiao, Adelaida
• Fecha de publicación: 2021
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: spa
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/53581
• Acceso en línea: http://hdl.handle.net/1992/53581
• Palabra clave: Recuperación de información; Procesamiento de lenguaje natural (Computación); Motores de búsqueda; Literatura científica; Ordenación jerárquica y selección (Estadística); Ingeniería
• Rights: openAccess
• License: https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf