Multilingual Neural RST Discourse Parsing

TL;DR

This paper introduces neural cross-lingual discourse parsing methods that leverage multilingual embeddings and translation, achieving state-of-the-art results across multiple languages with limited data.

Contribution

It proposes two novel approaches for multilingual discourse parsing using neural models, addressing data scarcity in non-English languages.

Findings

Both methods outperform previous models in cross-lingual discourse parsing.

Effective even with limited training data.

Achieved state-of-the-art performance across all sub-tasks.

Abstract

Text discourse parsing plays an important role in understanding information flow and argumentative 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.