dc.creatorDias, Márcio de Souza
dc.creatorPardo, Thiago Alexandre Salgueiro
dc.date.accessioned2016-01-06T18:24:16Z
dc.date.accessioned2018-07-04T17:06:38Z
dc.date.available2016-01-06T18:24:16Z
dc.date.available2018-07-04T17:06:38Z
dc.date.created2016-01-06T18:24:16Z
dc.date.issued2015-09
dc.identifierAnnual Meeting of the Special Interest Group on Discourse and Dialogue, 16th, 2015, Prague.
dc.identifier9781941643754
dc.identifierhttp://www.producao.usp.br/handle/BDPI/49418
dc.identifierhttp://www.aclweb.org/anthology/W/W15/W15-4608.pdf
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1644788
dc.description.abstractMulti-document summarization is a very important area of Natural Language Processing (NLP) nowadays because of the huge amount of data in the web. People want more and more information and this information must be coherently organized and summarized. The main focus of this paper is to deal with the coherence of multi-document summaries. Therefore, a model that uses discursive information to automatically evaluate local coherence in multi-document summaries has been developed. This model obtains 92.69% of accuracy in distinguishing coherent from incoherent summaries, outperforming the state of the art in the area.
dc.languageeng
dc.publisherAssociation for Computational Linguistics - ACL
dc.publisherPrague
dc.relationAnnual Meeting of the Special Interest Group on Discourse and Dialogue, 16th
dc.rightsCopyright Association for Computational Linguistics
dc.rightsopenAccess
dc.titleA discursive grid approach to model local coherence in multi-document summaries
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución