Citation Export
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, Ji Eun | - |
dc.contributor.author | Sohn, Kyung Ah | - |
dc.date.issued | 2023-01-01 | - |
dc.identifier.issn | 0736-587X | - |
dc.identifier.uri | https://aurora.ajou.ac.kr/handle/2018.oak/37009 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85174814928&origin=inward | - |
dc.description.abstract | Unsupervised 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.sponsorship | This 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.iso | eng | - |
dc.publisher | Association for Computational Linguistics (ACL) | - |
dc.subject.mesh | Robust performance | - |
dc.subject.mesh | Syntactic information | - |
dc.subject.mesh | Syntax parsing | - |
dc.subject.mesh | Transfer method | - |
dc.title | Fluency Matters! Controllable Style Transfer with Syntax Guidance | - |
dc.type | Conference | - |
dc.citation.conferenceName | 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023 | - |
dc.citation.edition | WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop | - |
dc.citation.endPage | 171 | - |
dc.citation.startPage | 162 | - |
dc.citation.title | Proceedings of the Annual Meeting of the Association for Computational Linguistics | - |
dc.identifier.bibliographicCitation | Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.162-171 | - |
dc.identifier.doi | 2-s2.0-85174814928 | - |
dc.identifier.scopusid | 2-s2.0-85174814928 | - |
dc.identifier.url | https://aclweb.org/ | - |
dc.type.other | Conference Paper | - |
dc.subject.subarea | Computer Science Applications | - |
dc.subject.subarea | Linguistics and Language | - |
dc.subject.subarea | Language and Linguistics | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.