BeFree : a text mining system for the extraction of biomedical information from literature
Current biomedical research needs to leverage the large amount of information reported in scientific publications. Automated text processing, commonly known as text mining, has become an indispensable tool to identify, extract, organize and analyze the relevant biomedical information from the litera...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis doctoral |
| Estado: | Versión publicada |
| Fecha de publicación: | 2016 |
| País: | España |
| Institución: | CBUC, CESCA |
| Repositorio: | TDR. Tesis Doctorales en Red |
| OAI Identifier: | oai:www.tdx.cat:10803/398300 |
| Acceso en línea: | http://hdl.handle.net/10803/398300 |
| Access Level: | acceso abierto |
| Palabra clave: | Text mining Natural language processing Named entity recognition Relation extraction Information extraction Mineria de text Processament de llenguatge natural Reconeixement d'entitats Extracció de relacions Extracció d'informació 573 |
| Sumario: | Current biomedical research needs to leverage the large amount of information reported in scientific publications. Automated text processing, commonly known as text mining, has become an indispensable tool to identify, extract, organize and analyze the relevant biomedical information from the literature. This thesis presents the BeFree system, a text mining tool for the extraction of biomedical information to support research in the genetic basis of disease and drug toxicity. BeFree can identify entities such as genes and diseases from a vast repository of biomedical text sources. Furthermore, by exploiting shallow and deep syntactic information of text, BeFree detects relationships between genes, diseases and drugs with a performance comparable to the state-of-the-art. As a result, BeFree has been used in various applications in the biomedical field, with the aim to provide structured biomedical information for the development of knowledge and corpora resources. Furthermore, these resources are available to the scientific community for the development of novel text mining tools |
|---|