{"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/decomposed-meta-learning-for-few-shot","title":"Decomposed Meta-Learning for Few-Shot Sequence Labeling","arxiv_id":null,"date":"2024-03-04","proceeding":"IEEE/ACM Transactions on Audio, Speech, and Language Processing (Volume: 32) 2024 3","authors":["Tingting Ma","Qianhui Wu","Huiqiang Jiang","Jieru Lin","Börje F. Karlsson","Tiejun Zhao","Chin-Yew Lin"],"abstract":"Few-shot sequence labeling is a general problem formulation for many natural language understanding tasks in data-scarcity scenarios, which require models to generalize to new types via only a few labeled examples. Recent advances mostly adopt metric-based meta--earning and thus face the challenges of modeling the miscellaneous Other prototype and the inability to generalize to classes with large domain gaps. To overcome these challenges, we propose a decomposed meta-learning framework for few-shot sequence labeling that breaks down the task into few-shot mention detection and few-shot type classification, and sequentially tackles them via meta-learning. Specifically, we employ model-agnostic meta-learning (MAML) to prompt the mention detection model to learn boundary knowledge shared across types. With the detected mention spans, we further leverage the MAML-enhanced span-level prototypical network for few-shot type classification. In this way, the decomposition framework bypasses the requirement of modeling the miscellaneous Other prototype. Meanwhile, the adoption of the MAML algorithm enables us to explore the knowledge contained in\r\nsupport examples more efficiently, so that our model can quickly adapt to new types using only a few labeled examples. Under our framework, we explore a basic implementation that uses two separate models for the two subtasks. We further propose a joint model to reduce model size and inference time, making our framework more applicable for scenarios with limited resources. Extensive experiments on nine benchmark datasets, including named entity recognition, slot tagging, event detection, and part-of-speech tagging, show that the proposed approach achieves start-of-the-art performance across various few-shot sequence labeling tasks.","url_abs":"https://tellarin.com/borje/papers/taslp24dml.pdf","url_pdf":"https://tellarin.com/borje/papers/taslp24dml.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":"decomposed-meta-learning-for-few-shot","repo_url":"https://github.com/microsoft/vert-papers/tree/master/papers/DecomposedMetaSL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"few-shot-ner","task_name":"Few-shot NER"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"miscellaneous","task_name":"Miscellaneous"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-ner-on-few-nerd-inter","task":"Few-shot NER","dataset":"Few-NERD (INTER)","model":"DecomposedMetaSL","rank_in_archive_order":7,"of":13,"metrics":{"10 way 1~2 shot":"55.61±0.32","10 way 5~10 shot":"67.85±0.18","5 way 1~2 shot":"62.09±0.93","5 way 5~10 shot":"71.26±0.15","Average":"63.99"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-ner-on-few-nerd-intra","task":"Few-shot NER","dataset":"Few-NERD (INTRA)","model":"DecomposedMetaSL","rank_in_archive_order":6,"of":13,"metrics":{"10 way 1~2 shot":"43.03±0.29","10 way 5~10 shot":"57.58±0.26","5 way 1~2 shot":"49.90±0.33","5 way 5~10 shot":"64.36±0.20","Average":"53.72"},"uses_additional_data":false},{"leaderboard":"/sota/pos-tagging-on-twitter-pos","task":"POS Tagging","dataset":"Twitter POS","model":"DecomposedMetaSL","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"81.01±0.15"},"uses_additional_data":false},{"leaderboard":"/sota/pos-tagging-on-wsj-pos","task":"POS Tagging","dataset":"WSJ POS","model":"DecomposedMetaSL","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"91.78±0.21"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-snips","task":"Slot Filling","dataset":"SNIPS","model":"DecomposedMetaSL","rank_in_archive_order":10,"of":10,"metrics":{"F1 (1-shot) avg":"74.89","F1 (5-shot) avg":"84.54"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"microsoft/vert-papers","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2204.05751"],"harvested_for_calls":[{"arxiv_id":"2204.05751","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.05751"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.05751\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"1e61d227bcd253d3c274eee96d01c39ab510726755384fe88d445158c26a23c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}