Multi-lingual and Cross-genre Discourse Unit Segmentation

Bourgonje, Peter; Schafer, Robin

doi:10.18653/v1/w19-2714

Cited by 7 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of the systems from DISRPT 2019 use lexical features, where the best systems (Muller et al, 2019; are recurrent neural networks. The system that is most similar to the current work is the (best) system from Bourgonje and Schäfer (2019), who use a random forest classifier and extract features at the token-level, e.g. surface form, POS tag, position in the sentence, succeeding punctuation mark.…”

Section: Resultsmentioning

confidence: 99%

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

Section: Resultsmentioning

confidence: 99%

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

show abstract

“…Several teams participated in the DISRPT 2019. Among the best proposals to mention some: Tony [47] employ single-layer bi-directional LSTM models with different pre-trained embeddings, and they get the best results using contextual embeddings.DFKI RF [48] uses a Random Forest (based on Scikit-learn [49] whose input is a combination of dependency tree and constituency syntax information. In addition, they use a LSTM-based method (based on Keras [50]) with pre-trained word embeddings [51].…”

Section: Related Workmentioning

confidence: 99%

“…DFKI RF [48] uses a Random Forest (based on Scikit-learn [49] whose input is a combination of dependency tree and constituency syntax information. In addition, they use a LSTM-based method (based on Keras [50]) with pre-trained word embeddings [51].…”

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

“…The main results for connective detection are given in Table 4. Three systems approached this task, though the DFKI system was not adapted substantially from the segmentation scenario, leading to low performance (Bourgonje and Schäfer, 2019), and did not report results on automatically parsed data. ToNy again has the highest scores for the most datasets, obtaining the highest mean F-score for the plain tokenized scenario, and coming second to GumDrop only on the Turkish dataset in the gold syntax scenario.…”

Section: Connective Detectionmentioning

confidence: 99%

The

Zeldes¹,

Das²,

Maziero³

et al. 2019

Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019

View full text Add to dashboard Cite

In 2019, we organized the first iteration of a shared task dedicated to the underlying units used in discourse parsing across formalisms: the DISRPT Shared Task on Elementary Discourse Unit Segmentation and Connective Detection. In this paper we review the data included in the task, which cover 2.6 million manually annotated tokens from 15 datasets in 10 languages, survey and compare submitted systems and report on system performance on each task for both annotated and plaintokenized versions of the data. * Discourse Relation Parsing and Treebanking (DIS-RPT): 7th Workshop on Rhetorical Structure Theory and Related Formalisms (https://sites.google.com/ view/disrpt2019) was held in conjunction with Annual Conference of the NAACL 2019 in Minneapolis, MN.

show abstract

Multi-lingual and Cross-genre Discourse Unit Segmentation

Cited by 7 publications

References 21 publications

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

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

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

The

Contact Info

Product

Resources

About