{"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/robust-multilingual-part-of-speech-tagging","title":"Robust Multilingual Part-of-Speech Tagging via Adversarial Training","arxiv_id":"1711.04903","date":"2017-11-14","proceeding":"NAACL 2018 6","authors":["Michihiro Yasunaga","Jungo Kasai","Dragomir Radev"],"abstract":"Adversarial training (AT) is a powerful regularization method for neural\nnetworks, aiming to achieve robustness to input perturbations. Yet, the\nspecific effects of the robustness obtained from AT are still unclear in the\ncontext of natural language processing. In this paper, we propose and analyze a\nneural POS tagging model that exploits AT. In our experiments on the Penn\nTreebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages),\nwe find that AT not only improves the overall tagging accuracy, but also 1)\nprevents over-fitting well in low resource languages and 2) boosts tagging\naccuracy for rare / unseen words. We also demonstrate that 3) the improved\ntagging performance by AT contributes to the downstream task of dependency\nparsing, and that 4) AT helps the model to learn cleaner word representations.\n5) The proposed AT model is generally effective in different sequence labeling\ntasks. These positive results motivate further use of AT for natural language\ntasks.","url_abs":"http://arxiv.org/abs/1711.04903v2","url_pdf":"http://arxiv.org/pdf/1711.04903v2.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":"robust-multilingual-part-of-speech-tagging","repo_url":"https://github.com/michiyasunaga/pos_adv","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chunking-on-conll-2000","task":"Chunking","dataset":"CoNLL 2000","model":"Adversarial Training","rank_in_archive_order":8,"of":9,"metrics":{"Exact Span F1":"95.25"},"uses_additional_data":false},{"leaderboard":"/sota/chunking-on-conll-2000","task":"Chunking","dataset":"CoNLL 2000","model":"BiLSTM-CRF","rank_in_archive_order":9,"of":9,"metrics":{"Exact Span F1":"95.18"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"Adversarial Bi-LSTM","rank_in_archive_order":61,"of":73,"metrics":{"F1":"91.56"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"Adversarial Bi-LSTM","rank_in_archive_order":8,"of":20,"metrics":{"Accuracy":"97.59"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-ud","task":"Part-Of-Speech Tagging","dataset":"UD","model":"Adversarial Bi-LSTM","rank_in_archive_order":2,"of":5,"metrics":{"Avg accuracy":"96.65"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.04903","atlas_url":"https://app.syntology.ai/?focus=1711.04903","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":"1711.04903"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.04903\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.04903"},"call":"get_concepts_for_paper(arxiv_id=\"1711.04903\")"}],"by_repo":[{"repo":"michiyasunaga/pos_adv","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":"9ec6eac290b5a327653e136ace1222d453f5cfd27baf224773746ca99f39396d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}