Character-based Thai Word Segmentation with Multiple Attentions

Thodsaporn Chay-intr, Hidetaka Kamigaito, Manabu Okumura


Abstract
Character-based word-segmentation models have been extensively applied to agglutinative languages, including Thai, due to their high performance. These models estimate word boundaries from a character sequence. However, a character unit in sequences has no essential meaning, compared with word, subword, and character cluster units. We propose a Thai word-segmentation model that uses various types of information, including words, subwords, and character clusters, from a character sequence. Our model applies multiple attentions to refine segmentation inferences by estimating the significant relationships among characters and various unit types. The experimental results indicate that our model can outperform other state-of-the-art Thai word-segmentation models.
Anthology ID:
2021.ranlp-1.31
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
264–273
Language:
URL:
https://aclanthology.org/2021.ranlp-1.31
DOI:
Bibkey:
Cite (ACL):
Thodsaporn Chay-intr, Hidetaka Kamigaito, and Manabu Okumura. 2021. Character-based Thai Word Segmentation with Multiple Attentions. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 264–273, Held Online. INCOMA Ltd..
Cite (Informal):
Character-based Thai Word Segmentation with Multiple Attentions (Chay-intr et al., RANLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/2021.ranlp-1.31.pdf
Code
 tchayintr/thwcc-attn