Papers › Decomposed Meta-Learning for Few-Shot Sequence Labeling

Decomposed Meta-Learning for Few-Shot Sequence Labeling

4 Mar 2024IEEE/ACM Transactions on Audio, Speech, and Language Processing (Volume: 32) 2024 3archive 2025-07-28

Tingting Ma, Qianhui Wu, Huiqiang Jiang, Jieru Lin, Börje F. Karlsson, Tiejun Zhao, Chin-Yew Lin

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 support 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.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

microsoft/vert-papers officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decomposed Meta-Learning for Few-Shot Named Entity Recognition (arXiv:2204.05751; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity TypingEvent DetectionFew-shot NERMeta-LearningMiscellaneousNamed Entity RecognitionNamed Entity Recognition (NER)Natural Language UnderstandingPOS TaggingPart-Of-Speech TaggingSlot Fillingnamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-shot NER Few-NERD (INTER) DecomposedMetaSL 10 way 1~2 shot 55.61±0.32 #7 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) DecomposedMetaSL 10 way 5~10 shot 67.85±0.18 #7 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) DecomposedMetaSL 5 way 1~2 shot 62.09±0.93 #7 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) DecomposedMetaSL 5 way 5~10 shot 71.26±0.15 #7 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTER) DecomposedMetaSL Average 63.99 #7 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) DecomposedMetaSL 10 way 1~2 shot 43.03±0.29 #6 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) DecomposedMetaSL 10 way 5~10 shot 57.58±0.26 #6 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) DecomposedMetaSL 5 way 1~2 shot 49.90±0.33 #6 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) DecomposedMetaSL 5 way 5~10 shot 64.36±0.20 #6 of 13 Archive leaderboard report
Few-shot NER Few-NERD (INTRA) DecomposedMetaSL Average 53.72 #6 of 13 Archive leaderboard report
POS Tagging Twitter POS DecomposedMetaSL Accuracy 81.01±0.15 #1 of 1 Archive leaderboard report
POS Tagging WSJ POS DecomposedMetaSL Accuracy 91.78±0.21 #1 of 1 Archive leaderboard report
Slot Filling SNIPS DecomposedMetaSL F1 (1-shot) avg 74.89 #10 of 10 Archive leaderboard report
Slot Filling SNIPS DecomposedMetaSL F1 (5-shot) avg 84.54 #10 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

MAML

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections