Decomposed Meta-Learning for Few-Shot Sequence Labeling

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AEIUTYMTK" target="_blank" >RIV/00216208:11320/25:EIUTYMTK - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85187378886&doi=10.1109%2fTASLP.2024.3372879&partnerID=40&md5=5e65c0a82d01180d43b50077e344f24f" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85187378886&doi=10.1109%2fTASLP.2024.3372879&partnerID=40&md5=5e65c0a82d01180d43b50077e344f24f</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2024.3372879" target="_blank" >10.1109/TASLP.2024.3372879</a>

Result language

angličtina

Original language name

Decomposed Meta-Learning for Few-Shot Sequence Labeling

Original language description

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-learning 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. © 2014 IEEE.

Czech name

—

Czech description

—

Type

J_SC - Article in a specialist periodical, which is included in the SCOPUS database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

IEEE/ACM Transactions on Audio Speech and Language Processing

ISSN

2329-9290

e-ISSN

—

Volume of the periodical

32

Issue of the periodical within the volume

2024

Country of publishing house

US - UNITED STATES

Number of pages

14

Pages from-to

1980-1993

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-85187378886