An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Xuemei, Wang, Jun, Su, Qi, Huang, Chu-ren, Gu, Jinghang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915349227634688
author Tang, Xuemei
Wang, Jun
Su, Qi
Huang, Chu-ren
Gu, Jinghang
author_facet Tang, Xuemei
Wang, Jun
Su, Qi
Huang, Chu-ren
Gu, Jinghang
contents 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 two-stage curriculum learning (TCL) framework specifically designed for sequence labeling tasks. The TCL framework enhances training by gradually introducing data instances from easy to hard, aiming to improve both performance and training speed. Furthermore, we explore different metrics for assessing the difficulty levels of sequence labeling tasks. Through extensive experimentation on six Chinese word segmentation (CWS) and Part-of-speech tagging (POS) datasets, we demonstrate the effectiveness of our model in enhancing the performance of sequence labeling models. Additionally, our analysis indicates that TCL accelerates training and alleviates the slow training problem associated with complex models.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13534
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling
Tang, Xuemei
Wang, Jun
Su, Qi
Huang, Chu-ren
Gu, Jinghang
Computation and Language
Artificial Intelligence
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 two-stage curriculum learning (TCL) framework specifically designed for sequence labeling tasks. The TCL framework enhances training by gradually introducing data instances from easy to hard, aiming to improve both performance and training speed. Furthermore, we explore different metrics for assessing the difficulty levels of sequence labeling tasks. Through extensive experimentation on six Chinese word segmentation (CWS) and Part-of-speech tagging (POS) datasets, we demonstrate the effectiveness of our model in enhancing the performance of sequence labeling models. Additionally, our analysis indicates that TCL accelerates training and alleviates the slow training problem associated with complex models.
title An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.13534