Work

An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling

Year: 2025

Type: conference-paper

Abstract: Sequence labeling models often benefit from incorporating external knowledge.However, this practice introduces data heterogeneity and complicates the model with additional modules, leading to increased expenses for training a high-performing model.To address this challenge, we propose a dual-stage curriculum learning (DCL) framework specifically designed for sequence labeling tasks.The DCL framework enhances training by gradually introducing data instances from easy to hard.Additionally, we introduce a dynamic metric for evaluating the difficulty levels of sequence labeling tasks.Experiments on several sequence labeling datasets show that our model enhances performance and accelerates training, mitigating the slow training issue of complex models 1 .

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-short.38

Authors: Xuemei Tang, Jun Wang, Qi Su, Chu-Ren Huang, Jinghang Gu

Institutions: Hong Kong Polytechnic University, Peking University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Hong Kong Polytechnic University