{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/khmer-word-segmentation-using-conditional","title":"Khmer Word Segmentation Using Conditional Random Fields","arxiv_id":null,"date":"2015-10-15","proceeding":null,"authors":["Vichet Chea","Ye Kyaw Thu","Chenchen Ding","Masao Utiyama","Andrew Finch","Eiichiro Sumita"],"abstract":"Word Segmentation is a critical task that\r\nis the foundation of much natural language processing\r\nresearch. This paper is a study of Khmer word segmentation using an approach based on conditional random\r\nfields (CRFs). A large manually-segmented corpus was\r\ndeveloped to train the segmenter, and we provide details\r\nof a set of word segmentation strategies that were used\r\nby the human annotators during the manual annotation.\r\nThe trained CRF segmenter was compared empirically to\r\na baseline approach based on maximum matching that\r\nused a dictionary extracted from the manually segmented\r\ncorpus. The CRF segmenter outperformed the baseline in\r\nterms of precision, recall and f-score by a wide margin.\r\nThe segmenter was also evaluated as a pre-processing step\r\nin a statistical machine translation system. It gave rise to\r\nsubstantial increases in BLEU score of up to 7.7 points,\r\nrelative to a maximum matching baseline.","url_abs":"https://www2.nict.go.jp/astrec-att/member/ding/KhNLP2015-SEG.pdf","url_pdf":"https://www2.nict.go.jp/astrec-att/member/ding/KhNLP2015-SEG.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"khmer-word-segmentation-using-conditional","repo_url":"https://github.com/VietHoang1512/khmer-nltk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"text-segmentation","task_name":"Text Segmentation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}