Applying Bidirectional LSTM to predict the specific word tags in Thai language sentence by using large corpus (LST20)
-
Updated
Sep 21, 2026 - Jupyter Notebook
Applying Bidirectional LSTM to predict the specific word tags in Thai language sentence by using large corpus (LST20)
Thai-text-classification
Efficient Named Entity Recognition (NER) for informal Thai job postings. This project fine-tunes WangchanBERTa and PhayaThaiBERT to extract structured HR data from unstructured social media text without the latency or cost of LLM APIs.
AI + Blockchain review verification (WangchanBERTa + Solidity)
Thai sentiment analysis of restaurant reviews using WangChanBERTa fine-tuning + Typhoon LLM data synthesis (CS450)
Fine-tuned WangchanBERTa for 12-label Thai news classification on a 20k-article Prachatai corpus (0.76 micro-F1 / 0.70 macro-F1). Includes diagnosis of political-news bias and a documented mitigation strategy.
Thai NBA Fan Comment Sentiment Classification
AI ภูมิคุ้มกันมิจฉาชีพ "ยิ่งโดนโกง ยิ่งฉลาด" — LINE Scam-Shield + AI honeypot + feedback loop (PSU Future Tech Challenge 2026)
This repository stores any Class Tutorial , project and assignment from Course : Text Mining and Sentiment in KDAI Curriculum
To associate your repository with the wangchanberta topic, visit your repo's landing page and select "manage topics."