{"url":"/task/thai-word-segmentation","name":"Thai Word Segmentation","slug":"thai-word-segmentation","description_markdown":"Thai word segmentation","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":8,"papers_with_code":7,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/thai-word-tokenization-on-best-2010","slug":"thai-word-tokenization-on-best-2010","dataset":"BEST-2010","dataset_url":null,"rows_in_archive":5,"metrics":["F1-Score"],"first_row_in_archive_order":{"model":"LATTE (Linguistic units, lattices, PTMs, GNNs)","paper_title":"LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation","paper_url":"/paper/latte-lattice-attentive-encoding-for","paper_date":"2023-06-01","arxiv_id":null,"code_links":[{"title":"tchayintr/latte-ptm-ws","url":"https://github.com/tchayintr/latte-ptm-ws"},{"title":"tchayintr/latte-ws","url":"https://github.com/tchayintr/latte-ws"}],"syntology":null}},{"leaderboard":"/sota/thai-word-segmentation-on-ws160","slug":"thai-word-segmentation-on-ws160","dataset":"WS160","dataset_url":null,"rows_in_archive":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Stacked Ensemble (CRF)","paper_title":"Domain Adaptation of Thai Word Segmentation Models using Stacked Ensemble","paper_url":"/paper/domain-adaptation-of-thai-word-segmentation","paper_date":"","arxiv_id":null,"code_links":[{"title":"mrpeerat/SEFR_CUT","url":"https://github.com/mrpeerat/SEFR_CUT"}],"syntology":null}}],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":8,"items":[{"url":"/paper/latte-lattice-attentive-encoding-for","title":"LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation","date":"2023-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/character-based-thai-word-segmentation-with","title":"Character-based Thai Word Segmentation with Multiple Attentions","date":"2021-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/handling-cross-and-out-of-domain-samples-in","title":"Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-of-thai-word-segmentation","title":"Domain Adaptation of Thai Word Segmentation Models using Stacked Ensemble","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/thailmcut-unsupervised-pretraining-for-thai","title":"ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attacut-a-fast-and-accurate-neural-thai-word","title":"AttaCut: A Fast and Accurate Neural Thai Word Segmenter","date":"2019-11-16","arxiv_id":"1911.07056","repositories_listed":1,"syntology":null},{"url":"/paper/multi-candidate-word-segmentation-using-bi","title":"Multi-Candidate Word Segmentation using Bi-directional LSTM Neural Networks","date":"2018-05-07","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}