ThaiWritableGAN: Handwriting Generation under Given Information

Mookdarsanit, Lawankorn; Mookdarsanit, Pakpoom

doi:10.12785/ijcds/100165

Cited by 3 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the experiments, T2I by stable diffusion could generate images in the highest quality as the stable diffusion applied self-attention to weight the tokens. 11, the presented TH-T2I could be contributed to many local arts and cultures to preserve Thai as the digital heritage on the open-source world, e.g., Thai amulet (Mookdarsanit, 2020)., colorful Siamese fighting fishes (Mookdarsanit & Mookdarsanit, 2019a)., Thai dance gestures (Mookdarsanit & Mookdarsanit, 2018b)., Muay-Thai Folklores (Mookdarsanit & Mookdarsanit, 2018a). or nutrients and calories estimation in Thai-foods (Mookdarsanit & Mookdarsanit, 2020c).…”

Section: Resultsmentioning

confidence: 99%

“…Or scene text detection (Kobchaisawat, Chalidabhongse & Satoh, 2020). Thai-HDR recognizes the variety of Thai handwriting styles and generates different Thai handwriting styles written by AGI (Mookdarsanit & Mookdarsanit, 2021b).…”

Section: Thai-nlp Timelinementioning

confidence: 99%

“…Above all, Thai-NLP areas have been continuously developed. They could be categorized into text categorization (Mookdarsanit & Mookdarsanit, 2019)., sentiment analysis (Haruechaiyasak, Kongthon, Palingoon & Trakultaweekoon, 2013)., part of speech tagging (Boonkwan & Supnithi, 2017)., human resource language intelligence (Mookdarsanit & Mookdarsanit, 2020b)., plagiarism detection (Taerungruang & Aroonmanakun, 2018)., news summarization (Ketui, Theeramunkong & Onsuwan, 2013)., fake news detection (Mookdarsanit & Mookdarsanit, 2021b)., and TH-EN machine translation (Lowphansirikul, Polpanumas, Rutherford & Nutanong, 2022). To shift a new paradigm of Thai-NLP area, this paper presented a novel Thai Text-to-Image (TH-T2I) prompt engineering to generate an image according to Thai text as contributing a new baseline LLM enhancing from TH-EN machine translation.…”

Section: Thai-nlp Timelinementioning

confidence: 99%

“…As motivated by Thaidessert image synthesis (Mookdarsanit & Mookdarsanit, 2018d)., TH-T2I could be further enhanced in many semantic Image-Text relations in Thai culture and art (Mookdarsanit & Rattanasiriwongwut, 2017c). Available on large-scale social media: street surveillance (Sutthaluang & Prakancharoen, 2020)., plant recognition (Mookdarsanit & Mookdarsanit, 2019b)., image location estimation (Mookdarsanit & Rattanasiriwongwut, 2017b)., Buddhism and temples (Mookdarsanit & Rattanasiriwongwut, 2017a)., food image description (Soimart & Mookdarsanit, 2017a)., tourism classifi cation (Mookdarsanit & Mookdarsanit, 2018c)., GPS place estimation (Soimart & Mookdarsanit, 2017b), pesticide analytics (Sutthaluang, 2019)., agricultural product quality (Mookdarsanit & Mookdarsanit, 2021a)., facial verifi cation and recognition (Soimart & Mookdarsanit, 2016)., and cosmetic recommender systems (Mookdarsanit & Mookdarsanit, 2023).…”

Section: Presented Th-t2i As a New Paradigm Of Thai-nlpmentioning

confidence: 99%

“…To enhance the conventional T2T translation model (e.g., text categorization, TH-EN machine translation) into T2I, Thai Text-to-Image (TH-T2I), prompt engineering was presented as one of the new challenges of Thai natural language processing areas that are proposed to translate the Thai text into an image. For the academic movement beyond education (Mookdarsanit & Mookdarsanit, 2022)., TH-T2I could be a baseline model in T2I on Thai for future Thai AI competitions (e.g., BEST Hackathon organized by NECTEC) that were proposed to preserve Thai as the digital heritage inherited by the next generation of Thai AGI researchers. As well as planting the Thai digital Treebank, future digital donations might be in Thai speech, handwriting, or textual comments on social media to make Thai a fruitful resource and library comparable to other high-resource languages.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Thai Text-to-Image Prompt Engineering by Pre-Trained Large Language With Stable Diffusion Model

Mookdarsanit,

Mookdarsanit

2023

AzJHPC

View full text Add to dashboard Cite

Text-to-image (T2I) generation is a new area of large language models (LLMs), a type of prompt engineering involving inputting a textual description to generate an image. To shift a new paradigm of Thai natural language processing (Thai-NLP), this paper first presents state-of-the-art Thai Text-to-Image prompt engineering (TH-T2I) to translate Thai text into a semantic image according to the semantic Thai textual description. The pre-trained SCB-MT-EN-TH model is employed for Text-to-Text (T2T) translation. Moreover, the image generation is done according to a semantic text prompt by a stable diffusion model. The T2T is evaluated by Bi-lingual Evaluation Understudy (BLEU), while T2I is done by Inception and Frechet Inception Distance (FID). The images generated by TH-T2I were of high quality, as measured by Inception and FID. TH-T2I contributes to a T2I baseline model in Thai, preserving the Thai cultural language on digital heritage.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Thai-nlp Timelinementioning

confidence: 99%

Section: Thai-nlp Timelinementioning

confidence: 99%

Section: Presented Th-t2i As a New Paradigm Of Thai-nlpmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Thai Text-to-Image Prompt Engineering by Pre-Trained Large Language With Stable Diffusion Model

Mookdarsanit,

Mookdarsanit

2023

AzJHPC

View full text Add to dashboard Cite

show abstract

Classification and keyword extraction of online harassment text in Thai social network

Hemtanon,

Phetkrachang,

Yangyuen

2023

Bulletin EEI

View full text Add to dashboard Cite

Online harassment in social network services (SNS) is a type of cyberbullying issue that needs to be addressed and required preventive measures. In this paper, we develop a detection of cyberbullying regarding harassment textual posts in Thai on the Facebook SNS. We collect public posts and ask experts to label the post as positive or negative regarding harassment posts or not. The annotated data are trained for binary classification considering words in the centre as features to predict malicious intent to insult and threaten other users. The information gain score obtained in generating a prediction model is ranked for the top 20 words with the highest score as significant words involving online harassment. From experiments, the results show that the detection performance obtained a 0.78 f1 score on average. The result analysis indicated that the word surface approach helps detect insulting post decently, but some posts with metaphor to tone down the malicious intent may not be detected as harmful semantic intent are hidden behind word form. Top-20 significant words for bullying showed that bullying posts were body-shaming and lower social status.

show abstract

Faithful Resilience: Profit and Support Strategies of Religious Institutions amidst the COVID-19 Crisis

Joob¹,

Wiwanitkit

2023

Khazanah Theologia

View full text Add to dashboard Cite

This article presents an analysis of the observation on making a profit for religious institutions and providing social support during the COVID-19 pandemic in a tropical country in Indochina. The study utilizes a descriptive approach, combining a literature review and a case study to explore the specific situation in the region. The article begins with an introduction to the concept of social marketing and then focuses on a unique form of religiously related social marketing: the production and sale of amulets. The potential benefits for religious establishments in terms of both financial gain and social support are highlighted. Furthermore, a detailed case study on ritual amulet marketing during the COVID-19 outbreak crisis is provided, shedding light on the strategies employed and the outcomes achieved. The findings suggest that social marketing by religious institutions can be a valuable advertising tool even during times of public crisis. The article concludes by emphasizing the potential of social marketing as an effective means for religious institutions to address societal needs and generate positive impacts. This research contributes to the understanding of the role of religious organizations in the promotion of social welfare and offers insights for practitioners seeking innovative approaches to navigate challenging circumstances.

show abstract

ThaiWritableGAN: Handwriting Generation under Given Information

Cited by 3 publications

References 0 publications

Thai Text-to-Image Prompt Engineering by Pre-Trained Large Language With Stable Diffusion Model

Thai Text-to-Image Prompt Engineering by Pre-Trained Large Language With Stable Diffusion Model

Classification and keyword extraction of online harassment text in Thai social network

Faithful Resilience: Profit and Support Strategies of Religious Institutions amidst the COVID-19 Crisis

Contact Info

Product

Resources

About