.png){kind=icon}
.png){kind=icon}
Return
Best-Fit Document: Enhancing Compositional Generalization in Multi-label Text Classification
.png){kind=icon}
PRE
AI
DOI：10.1007/978-981-95-3349-7_25.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-label text classification (MLTC) presents a complex challenge, requiring classifiers to assign multiple labels to each document, resulting in diverse label combinations across a large corpus. While substantial advancements have been made in traditional MLTC tasks, existing studies often overlook the impact of compositional generalization (CG) challenges on model performance. Current models struggle to generalize to novel and complex label combinations, which are typically formed from fundamental labels. This study addresses this limitation by proposing a straightforward and scalable data grouping approach, termed best-fit document (BFD), which optimizes large-scale training documents based on their lengths to enhance the classifier's capacity to model novel label combinations. A comprehensive evaluation of BFD was conducted across four datasets with specialized data splits. The experimental findings indicate that our method significantly enhances the CG ability of classification models on the evaluated benchmarks.
Keywords:
Multi-label Text Classification
Compositional Generalization
Journal
N
IF:
0
Papers:
32
Citations:
0