No abstract

The study we report in this article addresses the results of comparing the rhetorical trees from two different languages carried out by two annotators starting from the Rhetorical Structure Theory (RST). Furthermore, we investigate the methodology for a suitable evaluation, both quantitative and qualitative, of these trees. Our corpus contains abstracts of medical research articles written both in Spanish and Basque, and extracted from Gaceta Médica de Bilbao ('Medical Journal of Bilbao'). The results demonstrate that almost half of the annotator disagreement is due to the use of translation strategies that notably affect rhetorical structures.

This article presents a discourse annotation methodology based on Rhetorical Structure Theory and an empirical study of annotating a corpus of specialized medical texts in Basque. The annotation process includes two phases: segmentation and annotation of rhetorical relations. Phase one entails an initial study which leads to establishing linguistic criteria for sentence-based segmentation; a second phase focuses on annotation of rhetorical relations. After establishing discourse segments and rhetorical relations, the annotation process is analyzed and evaluated by means of the method commonly used in RST (Marcu 2000). Inconsistencies detected in the evaluation method lead the authors to redefine some criteria of the evaluation method. As a result of this work, a small annotated Basque-language corpus is provided to scientific community.

In 2021, we organized the second iteration of a shared task dedicated to the underlying units used in discourse parsing across formalisms: the DISRPT Shared Task (Discourse Relation Parsing and Treebanking). Adding to the 2019 tasks on Elementary Discourse Unit Segmentation and Connective Detection, this iteration of the Shared Task included for the first time a track on discourse relation classification across three formalisms: RST, SDRT, and PDTB. In this paper we review the data included in the Shared Task, which covers nearly 3 million manually annotated tokens from 16 datasets in 11 languages, survey and compare submitted systems and report on system performance on each task for both annotated and plain-tokenized versions of the data.

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.

No abstract

Systems for opinion and sentiment analysis rely on different resources: a lexicon, annotated corpora and constraints (morphological, syntactic or discursive), depending on the nature of the language or text type. In this respect, Basque is a language with fewer linguistic resources and tools than other languages, like English or Spanish. The aim of this work is to study whether some kinds of discourse structures based on nuclearity are sufficient to correctly assign positive and negative polarity with a lexicon-based approach for sentiment analysis. The evaluation is performed in two phases: i) Text extraction following some constraints on discourse structure from manually annotated trees. ii) Automatic annotation of semantic orientation (or polarity). Results show that the method is useful to detect all positive cases, but fails with the negative ones. An error analysis shows that negative cases have to be addressed in a different way. The immediate results of this work include an evaluation on how discourse structure can be exploited in Basque. In the future, we will also publish a manually created Basque dictionary to use in sentiment analysis tasks.

The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F 1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter.