Discourse Relation Parsing and Treebanking (DISRPT)

Study of coherence relations in frameworks such as RST (Mann & Thompson 1988), SDRT (Asher & Lascarides 2003) and PDTB (Miltsakaki et al. 2004), has experienced a revival in the last few years, in English and many other languages (Matthiessen & Teruya 2015; Maziero et al. 2015; da Cunha 2016; Iruskieta et al. 2016; Zeldes 2016, 2017). Multiple sites are now actively engaged in the development of discourse parsers (Feng and Hirst 2014; Joty et al. 2015; Surdeanu et al. 2015; Xue 2016; Braud et al. 2017), as a goal in itself, but also for applications such as sentiment analysis, argumentation mining, summarization, question answering, or machine translation evaluation (Benamara et al., 2017; Gerani et al. to appear; Durrett et al. 2016; Peldszus & Stede 2016; Scarton et al. 2016; Schouten & Frasincar 2016; among many others). At the same time, evaluation of results in discourse parsing has proven complicated (see Morey et al. 2017), and progress in integrating results across discourse treebanking frameworks has been slow. DISRPT 2019 follows a series of biennial events on discourse relation studies, which were initially focused especially on RST, first in Brazil (2007, 2009, 2011, 2013) as part of Brazilian NLP conferences, and then in Spain in 2015 and in 2017, as part of the Spanish NLP conference (https://sites.google.com/site/workshoprst2015/) and INLG 2017 (https://sites.google.com/site/workshoprst2017/). The 2019 workshop aims to broaden the scope of discussion to include participants and program committee members from different discourse theories (especially, but not limited to, RST, SDRT and PDTB). We are interested in applied papers with a computational orientation, resource papers and work on discourse parsing, as well as papers that advance the field with novel theoretical contributions and promote cross-framework fertilization. A major theme and a related shared task on discourse unit segmentation across formalisms (see below) will aim to promote convergence of resources and a joint evaluation of discourse parsing approaches. We invite submissions on the following and related topics, handling any language(s), and especially under-represented ones: Discourse relations (issues in segmentation, relation inventory, cognitive status of relations) Discourse parsing in any formalism, including shallow and deep discourse parsing Relation signaling (connectives and any other signals) and annotation Applications of coherence relations in NLP