Accuosto, PabloSaggion, Horacio2019-07-022019-07-022019Accuosto P, Saggion H. Discourse-driven argument mining in scientific abstracts. In: Métais E, Meziane F, Vadera S, Sugumaran V, Saraee M, editors. Natural Language Processing and Information Systems. 24th International Conference on Applications of Natural Language to Information Systems; 2019 Jun 26-28; Salford, UK. Heidelberg: Springer; 2019. p. 182-94. (LNCS, no. 11608). DOI: 10.1007/978-3-030-23281-8_15978-3-030-23280-1http://hdl.handle.net/10230/41907Comunicació presentada a: 24th International Conference on Applications of Natural Language to Information Systems (NLDB), celebrat del 26 al 28 de juny de 2019 a Salford, Regne Unit.Argument mining consists in the automatic identification of argumentative structures in texts. In this work we address the open question of whether discourse-level annotations can contribute to facilitate the identification of argumentative components and relations in scientific literature. We conduct a pilot study by enriching a corpus of computational linguistics abstracts that contains discourse annotations with a new argumentative annotation level. The results obtained from preliminary experiments confirm the potential value of the proposed approach.application/pdfeng© Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-030-23281-8_15info:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1007/978-3-030-23281-8_15Argument miningRSTScientific corpusinfo:eu-repo/semantics/openAccess