Towards a top-down approach for an automatic discourse analysis for Basque: Segmentation and Central Unit detection tool

Abstract

Lately, discourse structure has received considerable attention due to the benefits its application offers in several NLP tasks such as opinion mining, summarization, question answering, text simplification, among others. When automatically analyzing texts, discourse parsers typically perform two different tasks: i ) identification of basic discourse units (text segmentation) ii ) linking discourse units by means of discourse relations, building structures such as trees or graphs. The resulting discourse structures are, in general terms, accurate at intra-sentence discourse-level relations, however they fail to capture the correct inter-sentence relations. Detecting the main discourse unit (the Central Unit) is helpful for discourse analyzers (and also for manual annotation) in improving their results in rhetorical labeling. Bearing this in mind, we set out to build the first two steps of a discourse parser following a top-down strategy: i ) to find discourse units, ii ) to detect the Central Unit. The final step, i.e. assigning rhetorical relations, remains to be worked on in the immediate future. In accordance with this strategy, our paper presents a tool consisting of a discourse segmenter and an automatic Central Unit detector.

MultiAzterTest: a Multilingual Analyzer on Multiple Levels of Language for Readability Assessment

“…the CEFR word list since the complex word identification is getting attention in the NLP community (Yimam et al, 2018). Moreover, we would like to keep on adding more features: more morphological features and discourse based features based on a multilingual discourse parser (Atutxa et al, 2019). Applying MultiAzterTest in other text classification tasks is also one of our future aims.…”

RST Discourse Parser for Russian: An Experimental Study of Deep Learning Models

“…RST parsers have been created for several languages, including English [29,32], Chinese [12], Basque [1], Spanish, Portuguese, German, and Dutch [3,21]. The architecture of most of the existing RST-style parsers contains two modules: for discourse segmentation and for DT construction.…”

“…Examples of segmentation mistakes are given in Table 3 in Appendix. The first issue is related to the fact that some EDUs in the corpus contain multiple sentences or multiple paragraphs (1). It often occurs in the "Blogs" subsection with image-replacement tags and image captions, as well as with lists manually annotated as a single EDU, because such text fragments are usually treated by the system as separate paragraphs.…”