The objective of this study is to develop a methodology for the automatic detection of negated findings in radiological reports which takes into account semantic and syntactic descriptions, as well as morphological and syntactic analysis rules. In order to achieve this goal, a series of rules for processing lexical and syntactic information was elaborated. This required development of an electronic dictionary of medical terminology and computerized grammar. Computational framework was carried out with NooJ, a free software developed by Silberztein, which has various utilities for treating natural language. Results show that the detection of negated findings improves if lexical-grammatical information is added. © 2018, Springer International Publishing AG, part of Springer Nature.
Documento: | Artículo |
Título: | Automatic detection of negated findings with nooj: First results |
Autor: | Koza, W.; Muñoz, M.; Rivas, N.; Godoy, N.; Filippo, D.; Cotik, V.; Stricker, V.; Martínez, R.; Meziane F.; Silberztein M.; Atigui F.; Kornyshova E.; Metais E. |
Filiación: | Proyecto FONDECyT 1171033, Pontificia Universidad Católica de Valparaíso, Avenue El Bosque 1290, Viña del Mar, 2530388, Chile Hospital Pediátrico Garrahan, Combate de los Pozos 1881, Buenos Aires, C1245AAM, Argentina Departamento de Computación, FCEN, Pabellón I, Ciudad Universitaria, Buenos Aires, C1428EGA, Argentina Universidad Diego Portales, Vergara 210, Santiago, 8370067, Chile |
Palabras clave: | Negated finding; NooJ; Syntactic rules; Information systems; Information use; Semantics; Syntactics; Terminology; Computational framework; Electronic dictionaries; Grammatical information; Medical terminologies; Negated finding; NooJ; Syntactic information; Syntactic rules; Natural language processing systems |
Año: | 2018 |
Volumen: | 10859 LNCS |
Página de inicio: | 298 |
Página de fin: | 302 |
DOI: | http://dx.doi.org/10.1007/978-3-319-91947-8_30 |
Título revista: | 23rd International Conference on Natural Language and Information Systems, NLDB 2018 |
Título revista abreviado: | Lect. Notes Comput. Sci. |
ISSN: | 03029743 |
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v10859LNCS_n_p298_Koza |