Untitled

Abstract

Development of discourse parsers to annotate the relational discourse structure of a text is crucial for many downstream tasks. However, most of the existing work focuses on English, assuming a quite large dataset. Discourse data have been annotated for Basque, but training a system on these data is challenging since the corpus is very small. In this paper, we create the first parser based on RST for Basque, and we investigate the use of data in another language to improve the performance of a Basque discourse parser. More precisely, we build a monolingual system using the small set of data available and investigate the use of multilingual word embeddings to train a system for Basque using data annotated for another language. We found that our approach to building a system limited to the small set of data available for Basque allowed us to get an improvement over previous approaches making use of many data annotated in other languages. At best, we get 34.78 in F1 for the full discourse structure. More data annotation is necessary in order to improve the results obtained with these techniques. We also describe which relations match with the gold standard, in order to understand these results.

DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing

“…We compare the proposed framework with several strong RST parsing baselines: Yu et proposed a transition-based neural parser, obtaining competitive results in English. Iruskieta and Braud (2019) introduced a multilingual parser for 3 languages (English, Portuguese, and Spanish). proposed a multilingual parser that utilized cross-lingual representation (Cross Rep.), and adopted segment-level translation (Segment Trans.…”

“…The main challenge of multilingual discourse parsing is the sparsity of annotated data. Braud et al (2017a) conducted a harmonization of discourse treebanks across annotations in different languages, and Iruskieta and Braud (2019) used multilingual word embeddings to train systems on under-resourced languages. Recently, proposed a multilingual RST parser by utilizing cross-lingual language model and EDU segment-level translation, obtaining substantial performance gains.…”