Cunha towards discourse parsing in Spanish

texts can be analysed from different perspectives. one of the most difficult phenomena to process is discourse structure (hovy 2010). in recent years, one of the main challenges in the field of natural language processing (nlp) has been discourse parsing. research on this topic has been done for several languages, such as Japanese (Sumita et al. 1992), english (marcu 2000) and portuguese (pardo 2008), among others. also, for english, the conll-2015 Shared task focused on Shallow discourse parsing.9 discourse annotated corpora have been created too, for example for english (carlson et al. 2002), German (Stede 2004), portuguese (pardo 2008) and french (afantenos 2012). discourse parsing tools and resources are used to develop nlp applications; for example, automatic summarization, information extraction, text generation, machine translation and sentiment analysis (taboada & mann 2004). The aim of this paper is to present the advances in discourse parsing for Spanish. Specifically, after explaining our theoretical framework, we will detail the tools we have developed for the automatic annotation of discourse information in texts in Spanish and the discourse annotated resources we have created.