Alonso, LauraCastellón Masalles, IrenePadró, LluísGibert, Karina2019-03-112019-03-1120021135-5948https://hdl.handle.net/2445/130028In this paper we will show how clustering techniques provide empirical evidence for a characterisation of Discourse Markers (DMs) that helps in overcoming the lack of consensus and reduces the cost of building NLP resources based on DMs. By comparison of classifications from hand-tagged and unsupervised corpora we are capable of grounding a notion of DM prototypicality, from which reliable classifications can be obtained from fully unsupervised corpora.8 p.application/pdfeng(c) Alonso, Laura et al., 2002Tractament del llenguatge natural (Informàtica)Marcadors del discursNatural language processing (Computer science)Discourse markersinfo:eu-repo/semantics/article5145972019-03-11info:eu-repo/semantics/openAccess