Ajou University repository

Fluency Matters! Controllable Style Transfer with Syntax Guidance
Citations

SCOPUS

0

Citation Export

DC Field Value Language
dc.contributor.authorHan, Ji Eun-
dc.contributor.authorSohn, Kyung Ah-
dc.date.issued2023-01-01-
dc.identifier.issn0736-587X-
dc.identifier.urihttps://aurora.ajou.ac.kr/handle/2018.oak/37009-
dc.identifier.urihttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85174814928&origin=inward-
dc.description.abstractUnsupervised text style transfer is a challenging task that aims to alter the stylistic attributes of a given text without affecting its original content. One of the methods to achieve this is controllable style transfer, which allows for the control of the degree of style transfer. However, an issue encountered with controllable style transfer is the instability of transferred text fluency when the degree of the style transfer changes. To address this problem, we propose a novel approach that incorporates additional syntax parsing information during style transfer. By leveraging the syntactic information, our model is guided to generate natural sentences that effectively reflect the desired style while maintaining fluency. Experimental results show that our method achieves robust performance and improved fluency compared to previous controllable style transfer methods.-
dc.description.sponsorshipThis work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2022R1A2C1007434), and also by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2023-2018-0-01431) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation).-
dc.language.isoeng-
dc.publisherAssociation for Computational Linguistics (ACL)-
dc.subject.meshRobust performance-
dc.subject.meshSyntactic information-
dc.subject.meshSyntax parsing-
dc.subject.meshTransfer method-
dc.titleFluency Matters! Controllable Style Transfer with Syntax Guidance-
dc.typeConference-
dc.citation.conferenceName13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023-
dc.citation.editionWASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop-
dc.citation.endPage171-
dc.citation.startPage162-
dc.citation.titleProceedings of the Annual Meeting of the Association for Computational Linguistics-
dc.identifier.bibliographicCitationProceedings of the Annual Meeting of the Association for Computational Linguistics, pp.162-171-
dc.identifier.doi2-s2.0-85174814928-
dc.identifier.scopusid2-s2.0-85174814928-
dc.identifier.urlhttps://aclweb.org/-
dc.type.otherConference Paper-
dc.subject.subareaComputer Science Applications-
dc.subject.subareaLinguistics and Language-
dc.subject.subareaLanguage and Linguistics-
Show simple item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Sohn, Kyung-Ah Image
Sohn, Kyung-Ah손경아
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.