{"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/multilingual-part-of-speech-tagging-with","title":"Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss","arxiv_id":"1604.05529","date":"2016-04-19","proceeding":"ACL 2016 8","authors":["Barbara Plank","Anders Søgaard","Yoav Goldberg"],"abstract":"Bidirectional long short-term memory (bi-LSTM) networks have recently proven\nsuccessful for various NLP sequence modeling tasks, but little is known about\ntheir reliance to input representations, target languages, data set size, and\nlabel noise. We address these issues and evaluate bi-LSTMs with word,\ncharacter, and unicode byte embeddings for POS tagging. We compare bi-LSTMs to\ntraditional POS taggers across languages and data sizes. We also present a\nnovel bi-LSTM model, which combines the POS tagging loss function with an\nauxiliary loss function that accounts for rare words. The model obtains\nstate-of-the-art performance across 22 languages, and works especially well for\nmorphologically complex languages. Our analysis suggests that bi-LSTMs are less\nsensitive to training data size and label corruptions (at small noise levels)\nthan previously assumed.","url_abs":"http://arxiv.org/abs/1604.05529v3","url_pdf":"http://arxiv.org/pdf/1604.05529v3.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":"multilingual-part-of-speech-tagging-with","repo_url":"https://github.com/bplank/bilstm-aux","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multilingual-part-of-speech-tagging-with","repo_url":"https://github.com/ilyagusev/rnnmorph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multilingual-part-of-speech-tagging-with","repo_url":"https://github.com/timerstime/SDG4DA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"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/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"Bi-LSTM","rank_in_archive_order":19,"of":20,"metrics":{"Accuracy":"97.22"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-ud","task":"Part-Of-Speech Tagging","dataset":"UD","model":"Bi-LSTM","rank_in_archive_order":4,"of":5,"metrics":{"Avg accuracy":"96.40"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.05529","atlas_url":"https://app.syntology.ai/?focus=1604.05529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.05529"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/bplank/bilstm-aux","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ilyagusev/rnnmorph","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/timerstime/SDG4DA","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"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":1,"samples":[{"code_sha256_prefix":"7cd9c10b78a3b0e1","entry":"drop","repo":"bplank/bilstm-aux","repo_kind":"official","path":"src/structbilty.py","file_url":"https://github.com/bplank/bilstm-aux/blob/HEAD/src/structbilty.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7cd9c10b78a3b0e1"}},{"code_sha256_prefix":"38d94fe63b23b68c","entry":"build_dense_chars_layer","repo":"ilyagusev/rnnmorph","repo_kind":"listed","path":"rnnmorph/char_embeddings_model.py","file_url":"https://github.com/ilyagusev/rnnmorph/blob/HEAD/rnnmorph/char_embeddings_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38d94fe63b23b68c"}},{"code_sha256_prefix":"6e1bbd301beb5989","entry":"convert_from_opencorpora_tag","repo":"ilyagusev/rnnmorph","repo_kind":"listed","path":"rnnmorph/data_preparation/process_tag.py","file_url":"https://github.com/ilyagusev/rnnmorph/blob/HEAD/rnnmorph/data_preparation/process_tag.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e1bbd301beb5989"}},{"code_sha256_prefix":"90ae33fed83d4f02","entry":"process_gram_tag","repo":"ilyagusev/rnnmorph","repo_kind":"listed","path":"rnnmorph/data_preparation/process_tag.py","file_url":"https://github.com/ilyagusev/rnnmorph/blob/HEAD/rnnmorph/data_preparation/process_tag.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90ae33fed83d4f02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}