Multilingual Neural RST Discourse Parsing

Proceedings of the 28th International Conference on Computational Linguistics, pages 6730–6738 Barcelona, Spain (Online), December 8-13, 2020 6730 Multilingual Neural RST Discourse Parsing Zhengyuan Liu, Ke Shi, Nancy F. Chen Institute for Infocomm Research, A*STAR, Singapore {liu zhengyuan,shi ke,nfychen}@i2r.a-star.edu.sg Abstract Text discourse parsing plays an important role in understanding information flow and argumenta- tive structure in natural language. Previous research under the Rhetorical Structure Theory (RST) has mostly focused on inducing and evaluating models from the English treebank. However, the parsing tasks for other languages such as German, Dutch, and Portuguese are still challenging due to the shortage of annotated data. In this work, we investigate two approaches to establish a neural, cross-lingual discourse parser via: (1) utilizing multilingual vector representations; and (2) adopting segment-level translation of the source content. Experiment results show that both methods are effective even with limited training data, and achieve state-of-the-art performance on cross-lingual, document-level discourse parsing on all sub-tasks. 1 Introduction Rhetorical Structure Theory (RST) (Mann and Thompson, 1988) is one of the most influential theories of discourse analysis, under which a document is represented by a hierarchical discourse tree. As shown in Figure 1a, the leaf nodes of an RST tree are text spans named Elementary Discourse Units (EDUs), and the EDUs are connected by rhetorical relations (e.g., Cause, Contrast) to form larger text spans until the entire document is included. The rhetorical relations are further categorized to Nucleus (core part) and Satellite (subordinate part) based on their relative importance. Thus, document-level discourse pars- ing consists of three sub-tasks: tree construction, nuclearity determination and relation classification. Moreover, downstream natural language processing tasks can benefit from RST-based structure-aware document analysis, such as summarization (Liu and Chen, 2019; Xu et al., 2020) and machine compre- hension (Gao et al., 2020). By utilizing various linguistic characteristics (e.g., N-gram and lexical features, syntactic and organi- zational features), statistical approaches have obtained substantial improvement on the English RST-DT benchmark (Sagae, 2009; Hernault et al., 2010; Joty et al., 2013; Li et al., 2014b; Heilman and Sagae, 2015). Recently, neural networks have been making inroads into discourse analysis frameworks, such as attention-based hierarchical encoding (Li et al., 2016) and integrating neural-based syntactic features into a transition-based parser (Yu et al., 2018). Lin et al. (2019) and their follow-up work (Liu et al., 2019) successfully explored encoder-decoder neural architectures on sentence-level discourse analysis, with a top-down parsing procedure. Although discourse parsing has received much research attention and progress, the models are mainly optimized and evaluated in English. The main challenge is the shortage of annotated data, since manual annotation under the RST framework is labor-intensive and requires specialized linguistic knowledge. For instance, the most popular benchmark English RST-DT corpus (Carlson et al., 2002) only contains 385 samples, which is much smaller than those of other natural language processing tasks. The treebank size of other languages such as German (Stede and Neumann, 2014), Dutch (Redeker et al., 2012) and Basque (Iruskieta et al., 2013) are even more limited. Such limitations make …

Content truncated to 500 words