The

Zeldes, Amir; Das, Debopam; Maziero, Erick Galani; Antônio, Juliano Desiderato; Iruskieta, Mikel

doi:10.18653/v1/w19-2713

Cited by 13 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter, meanwhile, connects the EDU-boundary representations, which enhances the model's ability to capture long-range dependencies between EDUs. 2 We could not compare our segmentation results with the DISRPT 2019 Shared Task (Zeldes et al, 2019) participants. We found few inconsistencies in the settings.…”

Section: Ablation Studymentioning

confidence: 99%

RST Parsing from Scratch

Nguyen¹,

Nguyen²,

Joty³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

We introduce a novel top-down end-to-end formulation of document level discourse parsing in the Rhetorical Structure Theory (RST) framework. In this formulation, we consider discourse parsing as a sequence of splitting decisions at token boundaries and use a seq2seq network to model the splitting decisions. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite; rather, it yields segmentation as part of the parsing process. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high scoring trees. With extensive experiments on the standard English RST discourse treebank, we demonstrate that our parser outperforms existing methods by a good margin in both end-to-end parsing and parsing with gold segmentation. More importantly, it does so without using any handcrafted features, making it faster and easily adaptable to new languages and domains.

show abstract

Section: Ablation Studymentioning

confidence: 99%

RST Parsing from Scratch

Nguyen¹,

Nguyen²,

Joty³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…We could not compare our segmentation results with the DISRPT 2019 Shared Task[121] participants. We found few inconsistencies in the se ings.…”

mentioning

confidence: 99%

Structured pointing networks for natural language understanding

Nguyen¹

View full text Add to dashboard Cite

I would like to express my sincere gratitude towards my supervisors, Assist. Prof. Sha q Joty and Dr. Xiaoli Li, for providing invaluable guidance and encouragement throughout my PhD journey. ey inspire me with many valuable lessons, amongst of which help to enhance my passion to discover new problems and solutions. ey are not only my supervisors but also my friends, who are always there to support me both mentally and technically. It has been my pleasure to work under my supervisors' mentorship.In addition, I am thankful to my friends and also collaborators whom I have learned so much from. Firstly, I would like to express my gratitude to Xuan-Phi Nguyen and Tay Yi for their inestimable support and motivation to help me to complete my work. I would also like to thank my other colleagues and friends in the NTU-NLP group including Jwala, Han Cheol, Lin Xiang, Simeng, Maruf and Tasnim for their discussion and inspiration. I feel very lucky and appreciate to have them as friends and as part of my PhD journey.

show abstract

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

The

Cited by 13 publications

References 17 publications

RST Parsing from Scratch

RST Parsing from Scratch

Structured pointing networks for natural language understanding

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

Contact Info

Product

Resources

About