Ai-assisted text composition for automated content authoring using transformer-based language models
buir.contributor.author | Alpdemir, Yusuf | |
dc.contributor.author | Alpdemir, Yusuf | |
dc.contributor.author | Alpdemir, Mahmut Nedim | |
dc.coverage.spatial | Hammamet, TUNISIA | |
dc.date.accessioned | 2025-02-22T07:59:12Z | |
dc.date.available | 2025-02-22T07:59:12Z | |
dc.date.issued | 2024-06-23 | |
dc.department | Department of Computer Engineering | |
dc.description | Conference Name:2024 IEEE international conference on advanced systems and emergent technologies, icaset 2024 | |
dc.description.abstract | In this paper, we introduce a hybrid method that combines the use of Controllable Text Generation (CTG) approach via Large Language Models (LLMs), fine-tuned language models and sentence transformers in a single framework to generate real-author styled articles in Turkish language. As such, we seek to exemplify hybrid solutions that produce real-human styled high-quality contents, given limited resources and relatively short text prompts as inputs. To achieve this, we introduce a novel method to assemble an author-specific article in different coherence and fluency levels, based on phrasal control of the CTG process. Control phrases are automatically assembled based on a semantic correlation measure calculated using sentence embed dings corresponding to author articles, that are obtained from pre-trained sentence transformers. | |
dc.identifier.doi | 10.1109/IC_ASET61847.2024.10596255 | |
dc.identifier.isbn | 979-8-3503-8489-5 | |
dc.identifier.uri | https://hdl.handle.net/11693/116614 | |
dc.language.iso | English | |
dc.publisher | IEEE | |
dc.relation.isversionof | https://dx.doi.org/10.1109/IC_ASET61847.2024.10596255 | |
dc.subject | Machine learning | |
dc.subject | Language models | |
dc.subject | Text generation | |
dc.subject | Text classification | |
dc.subject | Customized content generation | |
dc.subject | Transformer architectures | |
dc.title | Ai-assisted text composition for automated content authoring using transformer-based language models | |
dc.type | Conference Paper |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- AI_-_Assisted_Text_Composition_for_Automated_Content_Authoring_Using_Transformer-Based_Language_Models.pdf
- Size:
- 481.36 KB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: