Multilingual segmentation based on neural networks and pre-trained word embeddings

Iruskieta, Mikel; Bengoetxea, Kepa; Salazar, Aitziber Atutxa; Ilarraza, Arantza Díaz de

doi:10.18653/v1/w19-2716

Cited by 5 publications

(2 citation statements)

References 14 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the CU is not always indicated (as sometimes the main topic can be elided), we agree with [10] and [11] in that most of the time the CU can be detected. This has been shown in different corpora and different languages [12–14]. It is noteworthy that, as [9] stated, there are texts with multiple CUs in the RST Basque Treebank: 23,33% (14 of 60 texts).…”

Section: Introductionmentioning

confidence: 70%

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

et al. 2019

Self Cite

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

Section: Introductionmentioning

confidence: 70%

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

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Performance however varies considerably depending on language, and more importantly genre, with F-scores ranging from 0.73 to 0.944. For Iruskieta, Bengoetxea, Salazar and Diaz de Ilarraza (Iruskieta et al, 2019), Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation.…”

Section: Shared Taskmentioning

confidence: 99%

Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019

2019

View full text Add to dashboard Cite

This overview summarizes the main contributions of the accepted papers at the 2019 workshop on Discourse Relation Parsing and Treebanking (DISRPT 2019). Co-located with NAACL 2019 in Minneapolis, the workshop's aim was to bring together researchers working on corpus-based and computational approaches to discourse relations. In addition to an invited talk, eighteen papers outlined below were presented, four of which were submitted as part of a shared task on elementary discourse unit segmentation and connective detection.

show abstract

Delexicalised Multilingual Discourse Segmentation for DISRPT 2021 and Tense, Mood, Voice and Modality Tagging for 11 Languages

Dönicke¹

2021

Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)

View full text Add to dashboard Cite

This paper describes our participating system for the Shared Task on Discourse Segmentation and Connective Identification across Formalisms and Languages. Key features of the presented approach are the formulation as a clause-level classification task, a languageindependent feature inventory based on Universal Dependencies grammar, and compositeverb-form analysis. The achieved F1 is 92% for German and English and lower for other languages. The paper also presents a clauselevel tagger for grammatical tense, aspect, mood, voice and modality in 11 languages.

show abstract

Multilingual segmentation based on neural networks and pre-trained word embeddings

Cited by 5 publications

References 14 publications

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

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

Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019

Delexicalised Multilingual Discourse Segmentation for DISRPT 2021 and Tense, Mood, Voice and Modality Tagging for 11 Languages

Contact Info

Product

Resources

About