{"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/mutual-information-maximization-for-simple","title":"Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction","arxiv_id":"1804.07849","date":"2018-04-20","proceeding":"NAACL 2019 6","authors":["Karl Stratos"],"abstract":"We address part-of-speech (POS) induction by maximizing the mutual\ninformation between the induced label and its context. We focus on two training\nobjectives that are amenable to stochastic gradient descent (SGD): a novel\ngeneralization of the classical Brown clustering objective and a recently\nproposed variational lower bound. While both objectives are subject to noise in\ngradient updates, we show through analysis and experiments that the variational\nlower bound is robust whereas the generalized Brown objective is vulnerable. We\nobtain competitive performance on a multitude of datasets and languages with a\nsimple architecture that encodes morphology and context.","url_abs":"http://arxiv.org/abs/1804.07849v4","url_pdf":"http://arxiv.org/pdf/1804.07849v4.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":"mutual-information-maximization-for-simple","repo_url":"https://github.com/karlstratos/mmi-tagger","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"pos","task_name":"POS"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.07849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.07849"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/karlstratos/mmi-tagger","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3ebabcb3894d6042","entry":"compute_many2one_acc","repo":"karlstratos/mmi-tagger","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/karlstratos/mmi-tagger/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ebabcb3894d6042"}},{"code_sha256_prefix":"1e5174891e22d804","entry":"compute_v_measure","repo":"karlstratos/mmi-tagger","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/karlstratos/mmi-tagger/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e5174891e22d804"}},{"code_sha256_prefix":"e7633d29cc5ad34e","entry":"get_majority_mapping","repo":"karlstratos/mmi-tagger","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/karlstratos/mmi-tagger/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7633d29cc5ad34e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}