Cross-lingual RST Discourse Parsing

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 292–304, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Cross-lingual RST Discourse Parsing Chlo´e Braud1, Maximin Coavoux2 and Anders Søgaard1 1CoAStaL, DIKU, University of Copenhagen, University Park 5, 2100 Copenhagen 2LLF, CNRS, Univ Paris Diderot, Sorbonne Paris Cit´e {braud,soegaard}@di.ku.dk {maximin.coavoux}@etu.univ-paris-diderot.fr Abstract Discourse parsing is an integral part of understanding information flow and argu- mentative structure in documents. Most previous research has focused on inducing and evaluating models from the English RST Discourse Treebank. However, dis- course treebanks for other languages ex- ist, including Spanish, German, Basque, Dutch and Brazilian Portuguese. The tree- banks share the same underlying linguistic theory, but differ slightly in the way doc- uments are annotated. In this paper, we present (a) a new discourse parser which is simpler, yet competitive (significantly bet- ter on 2/3 metrics) to state of the art for English, (b) a harmonization of discourse treebanks across languages, enabling us to present (c) what to the best of our knowl- edge are the first experiments on cross- lingual discourse parsing. 1 Introduction Documents can be analyzed as sequences of hier- archical discourse structures. Discourse structures describe the organization of documents in terms of discourse or rhetorical relations. For instance, the three discourse units below can be represented by the tree in Figure 1, where a relation COMPAR- ISON holds between the segments 1 and 2, and a relation ATTRIBUTION links the segment covering the units 1 and 2, and the segment 3.1 1 Consumer spending in Britain rose 0.1% in the third quarter from the second quarter 2 and was up 3.8% from a year ago, 3 the Central Statistical Office estimated. 1“NS” and “NN” in Figure 1 describe the nuclearity of the segments, see Section 3. 1 2 3 NN-COMPARISON NS-ATTRIBUTION Figure 1: Tree for the structure covering the seg- ments 1 to 3 in document 1384 in the English RST Discourse Treebank. Rhetorical Structure Theory (RST) (Mann and Thompson, 1988) is a prominent linguistic the- ory of discourse structures, in which texts are an- alyzed as constituency trees, such as the one in Figure 1. This theory guided the annotation of the RST Discourse Treebank (RST-DT) (Carlson et al., 2001) for English, from which several text- level discourse parsers have been induced (Her- nault et al., 2010; Joty et al., 2012; Feng and Hirst, 2014; Li et al., 2014; Ji and Eisenstein, 2014). Such parsers have proven to be useful for various downstream applications (Daum´e III and Marcu, 2009; Burstein et al., 2003; Higgins et al., 2004; Thione et al., 2004; Sporleder and Lapata, 2005; Taboada and Mann, 2006; Louis et al., 2010; Bha- tia et al., 2015). There are discourse treebanks for other lan- guages than English, including Spanish, German, Basque, Dutch, and Brazilian Portuguese. How- ever, most research experimenting with these lan- guages has focused on rule-based systems (Pardo and Nunes, 2008; Maziero et al., 2011) or …

Content truncated to 500 words