{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/unsupervised-neural-word-segmentation-for","title":"Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling","arxiv_id":"1810.03167","date":"2018-10-07","proceeding":"EMNLP 2018 10","authors":["Zhiqing Sun","Zhi-Hong Deng"],"abstract":"Previous traditional approaches to unsupervised Chinese word segmentation\n(CWS) can be roughly classified into discriminative and generative models. The\nformer uses the carefully designed goodness measures for candidate\nsegmentation, while the latter focuses on finding the optimal segmentation of\nthe highest generative probability. However, while there exists a trivial way\nto extend the discriminative models into neural version by using neural\nlanguage models, those of generative ones are non-trivial. In this paper, we\npropose the segmental language models (SLMs) for CWS. Our approach explicitly\nfocuses on the segmental nature of Chinese, as well as preserves several\nproperties of language models. In SLMs, a context encoder encodes the previous\ncontext and a segment decoder generates each segment incrementally. As far as\nwe know, we are the first to propose a neural model for unsupervised CWS and\nachieve competitive performance to the state-of-the-art statistical models on\nfour different datasets from SIGHAN 2005 bakeoff.","url_abs":"http://arxiv.org/abs/1810.03167v1","url_pdf":"http://arxiv.org/pdf/1810.03167v1.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":"unsupervised-neural-word-segmentation-for","repo_url":"https://github.com/Edward-Sun/SLM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chinese-word-segmentation","task_name":"Chinese Word Segmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.03167","atlas_url":"https://app.syntology.ai/?focus=1810.03167","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1810.03167"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.03167\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.03167"},"call":"get_concepts_for_paper(arxiv_id=\"1810.03167\")"}],"by_repo":[{"repo":"Edward-Sun/SLM","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bdae4030a4f929b2d3e88606aa51b04a98fa0f12763e871fcdbf2d1c0ba4f080","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}