caa a22 4500 463207203 CHVBK 20180405153129.0 cr unu---uuuuu 170326e20071201xx s 000 0 eng 10.1007/s10462-009-9104-y doi (NATIONALLICENCE)springer-10.1007/s10462-009-9104-y Araujo Lourdes Dpto. de Lenguajes y Sistemas Informáticos, Universidad Nacional de Educación a Distancia (UNED), C/ Juan del Rosal, 16, 28040, Madrid, Spain aut How evolutionary algorithms are applied to statistical natural language processing [Elektronische Daten] [Lourdes Araujo] Statistical natural language processing (NLP) and evolutionary algorithms (EAs) are two very active areas of research which have been combined many times. In general, statistical models applied to deal with NLP tasks require designing specific algorithms to be trained and applied to process new texts. The development of such algorithms may be hard. This makes EAs attractive since they offer a general design, yet providing a high performance in particular conditions of application. In this article, we present a survey of many works which apply EAs to different NLP problems, including syntactic and semantic analysis, grammar induction, summaries and text generation, document clustering and machine translation. This review finishes extracting conclusions about which are the best suited problems or particular aspects within those problems to be solved with an evolutionary algorithm. Springer Science+Business Media B.V., 2009 Evolutionary algorithms nationallicence Statistical natural language processing nationallicence Artificial Intelligence Review Springer Netherlands 28/4(2007-12-01), 275-303 0269-2821 28:4<275 2007 28 10462 https://doi.org/10.1007/s10462-009-9104-y text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s10462-009-9104-y text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Araujo Lourdes Dpto. de Lenguajes y Sistemas Informáticos, Universidad Nacional de Educación a Distancia (UNED), C/ Juan del Rosal, 16, 28040, Madrid, Spain aut NATIONALLICENCE 773 0- Artificial Intelligence Review Springer Netherlands 28/4(2007-12-01), 275-303 0269-2821 28:4<275 2007 28 10462 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer