Misspelling Error Detection in Thai Language Application

Somboonsak, Patsaraporn

doi:10.1145/3301551.3301584

Cited by 3 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is consistent with other studies such as Vaithiyanathan & Muniraj [12], Zaki et al [23] and Thammarak et al [18]. In addition, Thai characters that often result in error include headless characters, such as ก and ธ, and letters with slightly different shapes, such as ด and ตand ฎ and ฏ, which is consistent with the study of Somboonsak [17], Mookdarsanit & Mookdarsanit [15] and Thammarak et al [18].…”

Section: Discussionsupporting

confidence: 91%

“…However, the proposed method produced a decreased accuracy compared to Arief et al [26], which used Google Cloud Vision to extract large-scale scanned documents. Consistent with results from previous studies, conversions of English documents provided higher accuracy than other language documents [17].…”

Section: Discussionsupporting

confidence: 91%

“…In addition, they constructed a dictionary and N-gram language model for detecting and correcting errors at the post-processing step, and results improved up to 98%. Somboonsak [17] used the longest matching, maximum matching, left and right conditional probabilities, and a feature-based approach to create an application for correcting Thai grammatical errors. Kesorn & Phawapoothayanchai [35] enhanced the performance of OCR using an approximate string-matching technique.…”

Section: Figure 2 Example Of a Thai Word With Three Elements: Letters...mentioning

confidence: 99%

“…Many studies in Thailand have focused on applying optical character recognition (OCR) [14,15] or machine learning technology [16]; however, findings demonstrate that Thai character recognition is still less effective than that of English characters. Somboonsak [17] found detecting new words that were not in the dictionary and adding new words to the dictionary difficult. Chomphuwiset [16] identified problems with memorizing two Thai words that combine into one word, indentation, and space and considered developing post-processing techniques to solve this problem in the future.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API

Thammarak

Sirisathitkul²,

Kongkla³

et al. 2022

Civ Eng J

View full text Add to dashboard Cite

This study aims to develop an automated data digitization system for the Thai vehicle registration certificate. It is the first system developed as a web service Application Programming Interface (API), which is essential for any enterprise to increase its business value. Currently, this system is available on “www.carjaidee.com”. The system involves four steps: 1) an embedded frame aligns a document to be correctly recognised in the image acquisition step; 2) sharpening and brightness filtering techniques to enhance image quality are applied in the pre-processing step; 3) the Google Cloud Vision API receives a prompt to proceed in the recognition step; 4) a specific domain dictionary to improve accuracy rate is developed for the post-processing step. This study defines 92 images for the experiment by counting the correct words and terms from the output. The findings suggest that the proposed method, which had an average accuracy of 93.28%, was significantly more accurate than the original method using only the Google Cloud Vision API. However, the system is limited because the dictionaries cannot automatically recognise a new word. In the future, we will explore solutions to this problem using natural language processing techniques. Doi: 10.28991/CEJ-2022-08-07-09 Full Text: PDF

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Discussionsupporting

confidence: 91%

Section: Figure 2 Example Of a Thai Word With Three Elements: Letters...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API

Thammarak

Sirisathitkul²,

Kongkla³

et al. 2022

Civ Eng J

View full text Add to dashboard Cite

show abstract

“…Sine phone is a personal device and is expected to stay with the same person almost all the time, therefore, is it much easier to provide access to the information or monitoring related services through the same device [2]. Currently, various devices, such as smartphones, appliances, traffic lights, wearable devices, vehicles, and industrial sensors, are including smart cities, e-healthcare, intelligent transportation, and disaster response [2,5,33,34].…”

Section: Mobile Medical Applicationmentioning

confidence: 99%

Development Innovation to Predict Dengue Affected Area and Alert People with Smartphones

Somboonsak

2020

Int. J. Onl. Eng.

Self Cite

View full text Add to dashboard Cite

<p class="0abstract">Dengue remains a significant problem that needs to be addressed urgently in Thailand. Although Thailand has spread the dengue fever for more than sixty years, however, it is still found dengue patients in every province and spread to various areas. There is also a variable pattern of disease occurring each year, so it is necessary to have tools to help forecast area to allow the related organization and the people in the area plan to prevent dengue fever that may occur next year. This research aimed to create innovation for predicting dengue fever regions, namely ThaiDengue, by collecting data from dengue patients in Chatuchak District, Bangkok, Thailand, from January 2014 to December 2018. There was a total of 358,524 dengue patients from the Bureau of vector-borne diseases applied to the prediction of patients in the next year with the ARIMA model (1,1,0) (1,1,0). It is predicted that in 2019, Thailand will have dengue patients around 95,000 cases, which has the number of dengue patients close to the year 2018. In the next step, application development and database on fog computing. Fog computing is an evolving technology that brings the benefits achieved by could computing to the periphery of the network devices for faster data analytics. It is better suited than cloud computing for meeting the demands of numerous emerging applications such as self-driving cars, traffic lights, smart homes. While the ThaiDengue consists of the main menu: how to use, forecast, surveillance calendar, notification, disease map, notify patients, contact the Bureau of vector-borne, knowledge information, and scan the QR code. After that, the result of the development, the researcher has the Bureau of vector-borne disease of Thailand used to forecasts, create a GPS map of dengue outbreaks, and create a calendar for dengue monitoring. After that, send a message to alert the people in the area of dengue via a smartphone and send additional emails. The results from using the application found this application can be used as a tool to help the Bureau of vector-borne diseases, to plan dengue fever control and alert the people in the risk areas of dengue outbreak and users are very satisfied with the use of the application.</p>

show abstract

Methods, Models and Tools for Improving the Quality of Textual Annotations

Artese

Gagliardi

2022

Modelling

View full text Add to dashboard Cite

In multilingual textual archives, the availability of textual annotation, that is keywords either manually or automatically associated with texts, is something worth exploiting to improve user experience and successful navigation, search and visualization. It is therefore necessary to study and develop tools for this exploitation. The paper aims to define models and tools for handling textual annotations, in our case keywords of a scientific library. With the background of NLP, machine learning and deep learning approaches are presented. They allow us, in supervised and unsupervised ways, to increase the quality of keywords. The different steps of the pipeline are addressed, and different solutions are analyzed, implemented, evaluated and compared, using statistical methods, machine learning and artificial neural networks as appropriate. If possible, off-the-shelf solutions will also be compared. The models are trained on different datasets already available or created ad hoc with common characteristics with the starting dataset. The results obtained are presented, commented and compared with each other.

show abstract

Misspelling Error Detection in Thai Language Application

Cited by 3 publications

References 12 publications

Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API

Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API

Development Innovation to Predict Dengue Affected Area and Alert People with Smartphones

Methods, Models and Tools for Improving the Quality of Textual Annotations

Contact Info

Product

Resources

About