Papers › Character-based Thai Word Segmentation with Multiple Attentions

Character-based Thai Word Segmentation with Multiple Attentions

1 Sep 2021RANLP 2021 9archive 2025-07-28

Thodsaporn Chay-intr, Hidetaka Kamigaito, Manabu Okumura

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.

PaperPDFConference PDFCode

Code

tchayintr/thwcc-attn officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

SegmentationThai Word Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Thai Word Segmentation BEST-2010 Multiple Attentions (char-word-cc) F1-Score 0.9899 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections