{"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/a-grounded-unsupervised-universal-part-of","title":"A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages","arxiv_id":"1904.05426","date":"2019-04-10","proceeding":"NAACL 2019 6","authors":["Ronald Cardenas","Ying Lin","Heng Ji","Jonathan May"],"abstract":"Unsupervised part of speech (POS) tagging is often framed as a clustering\nproblem, but practical taggers need to \\textit{ground} their clusters as well.\nGrounding generally requires reference labeled data, a luxury a low-resource\nlanguage might not have. In this work, we describe an approach for low-resource\nunsupervised POS tagging that yields fully grounded output and requires no\nlabeled training data. We find the classic method of Brown et al. (1992)\nclusters well in our use case and employ a decipherment-based approach to\ngrounding. This approach presumes a sequence of cluster IDs is a `ciphertext'\nand seeks a POS tag-to-cluster ID mapping that will reveal the POS sequence. We\nshow intrinsically that, despite the difficulty of the task, we obtain\nreasonable performance across a variety of languages. We also show\nextrinsically that incorporating our POS tagger into a name tagger leads to\nstate-of-the-art tagging performance in Sinhalese and Kinyarwanda, two\nlanguages with nearly no labeled POS data available. We further demonstrate our\ntagger's utility by incorporating it into a true `zero-resource' variant of the\nMalopa (Ammar et al., 2016) dependency parser model that removes the current\nreliance on multilingual resources and gold POS tags for new languages.\nExperiments show that including our tagger makes up much of the accuracy lost\nwhen gold POS tags are unavailable.","url_abs":"http://arxiv.org/abs/1904.05426v1","url_pdf":"http://arxiv.org/pdf/1904.05426v1.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":"a-grounded-unsupervised-universal-part-of","repo_url":"https://github.com/isi-nlp/universal-cipher-pos-tagging","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"decipherment","task_name":"Decipherment"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.05426","atlas_url":"https://app.syntology.ai/?focus=1904.05426","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":"1904.05426"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.05426\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.05426"},"call":"get_concepts_for_paper(arxiv_id=\"1904.05426\")"}],"by_repo":[{"repo":"isi-nlp/universal-cipher-pos-tagging","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":"c8c1bd5863659c01e51257ffc8385115de83cc61cf50e6ca0eb9c9a92b03e999","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}