Thai sentence segmentation using large language models
Narongkorn Panitsrisit, Attapol Thamrongrattanarit · 2022
Thai sentence segmentation has been on the topic of interest among Thai NLP communities. However, not much literature has explored the use of transformer-based large language models to tackle the issue. We conduct three experiments on the LST20 corpus, including (1) fine-tuning WangchanBERTa, a large language model pre-trained on Thai, across different classification tasks, (2) joint learning for clause and sentence segmentation, and (3) cross-lingual transfer using the multilingual model XLM-RoBERTa. Our findings show that WangchanBERTa outperforms other models in Thai sentence segmentation, and fine-tuning it with token and contextual information further improves its performance. However, cross-lingual transfer from English and Chinese to Thai is not effective for this task.