Extending Automatic Discourse Segmentation for Texts in Spanish to Catalan

TL;DR

This paper introduces the first discourse segmenter for Catalan, adapting RST-based methods from Spanish and demonstrating promising results on manually segmented texts.

Contribution

It develops the initial discourse segmenter for Catalan by adapting existing Spanish RST-based rules, filling a gap in NLP tools for Catalan.

Findings

System achieves promising results on gold standard corpus

Adapts Spanish discourse rules to Catalan using lexical and syntactic info

First discourse segmenter developed for Catalan texts

Abstract

At present, automatic discourse analysis is a relevant research topic in the field of NLP. However, discourse is one of the phenomena most difficult to process. Although discourse parsers have been already developed for several languages, this tool does not exist for Catalan. In order to implement this kind of parser, the first step is to develop a discourse segmenter. In this article we present the first discourse segmenter for texts in Catalan. This segmenter is based on Rhetorical Structure Theory (RST) for Spanish, and uses lexical and syntactic information to translate rules valid for Spanish into rules for Catalan. We have evaluated the system by using a gold standard corpus including manually segmented texts and results are promising.