DiSeg 1.0: The first system for Spanish discourse segmentation

Cunha, Iria da; Juan, Eric San; Torres‐Moreno, Juan‐Manuel; Lloberese, Marina; Castellóne, Irene

doi:10.1016/j.eswa.2011.06.058

Cited by 22 publications

(19 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This article adopts the definition of discourse segment put forward by Tofiloski et al (2009: 77): ‘Discourse segmentation is the process of decomposing discourse into elementary discourse units (EDUs), which may be simple sentences or clauses in a complex sentence, and from which discourse trees are constructed’. Specifically, we use the criteria for discourse segmentation most used in Spanish described in da Cunha et al (2012b), da Cunha and Iruskieta (2010) and Iruskieta et al (2015). See, for instance, examples 1 and 2.…”

Section: Methodsmentioning

confidence: 99%

“…First, data were manually extracted for sections, titles and moves (from the textual level). Second, the remaining data were extracted automatically (from the lexical and discourse levels), by using the following automatic Natural Language Processing (NLP) tools: a morphosyntactic analyzer (Freeling; Atserias et al, 2006), and a discourse segmentation system (DiSeg; da Cunha et al, 2012b).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A corpus-based analysis of textual genres in the administration domain

Cunha

Montané

2019

Discourse Studies

Self Cite

View full text Add to dashboard Cite

Laymen occasionally have to write texts in specialized domains, such as when interacting with the public administration. However, in Spanish, most studies related to administrative texts have focused on texts written by the administration for laymen rather than texts that average citizens write to the administration. Against this backdrop, this article aims to carry out the following: (a) a linguistic analysis on a corpus of Spanish-language texts from five textual genres written by laymen and addressed to the public administration (allegation, cover letter, letter of complaint, claim, and application) on the textual, lexical and discourse levels; (b) a contrastive analysis that applies statistical techniques to quantitative data to identify significant differences among these textual genres. The results show a detailed and comprehensive understanding of the characteristics of each genre. Also, the statistical results indicate that there are significant differences among some of the analyzed genres.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

A corpus-based analysis of textual genres in the administration domain

Cunha

Montané

2019

Discourse Studies

Self Cite

View full text Add to dashboard Cite

show abstract

“…This corpus, compared to the one used by [28, 55, 56] for Basque, contains 40 additional texts, as we included 2 new domains (economy and computer science). The size—140 texts—is similar to or larger than others created for similar aims, such as [40] (9 texts) and [44] (20 texts) for segmentation, and [60] (32 texts) and [11] (100 texts) for CU detection. The corpus in Table 2 was randomly divided into 3 non-overlapping datasets: 84 texts as the training set, 28 texts as the development set and 28 texts as the test set (Table 3).…”

Section: Methodsmentioning

confidence: 99%

“…There are several ways of pursuing the automatic segmentation task; using rule based techniques as in: i ) [28] for Basque, ii ) [44] for Spanish, and iii ) [40] for English. Using machine-learning techniques, for example, perceptron, as in [45] for French.…”

Section: Related Workmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

“…One possible significant contribution could be in the field of machine translation. In fact, there have been attempts to develop computer programs capable of analyzing rhetorical structure automatically based on banks of manmade analyses (e.g., da Cunha, San Juan, Torres-Moreno, Cabré, & Sierra, 2012;da Cunha, San Juan, Torres-Moreno, Lloberese, & Castellóne, 2012). If a machine translation system had as its basis the replacement of equivalent rhetorical structures between a source and a translated text, the end products would likely be more satisfactory than they are at present.…”

Section: Discourse Studies and Translationmentioning

confidence: 99%