Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

TL;DR

FUTEX is a novel framework for weakly supervised multi-label classification of full-text scientific papers, leveraging structural information like citation networks and hierarchical organization to improve classification accuracy without extensive labeled data.

Contribution

The paper introduces FUTEX, which effectively utilizes structural signals such as citation links and section hierarchy for weakly supervised classification of full-text papers, addressing fine-grained and multi-label challenges.

Findings

FUTEX outperforms existing weakly supervised baselines.

FUTEX matches fully supervised classifiers with minimal labeled data.

Structural information significantly enhances classification performance.

Abstract

Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only using category descriptions (e.g., category names, category-indicative keywords). Existing studies on weakly supervised paper classification are less concerned with two challenges: (1) Papers should be classified into not only coarse-grained research topics but also fine-grained themes, and potentially into multiple themes, given a large and fine-grained label space; and (2) full text should be utilized to complement the paper title and abstract for classification. Moreover, instead of viewing the entire paper as a long linear sequence, one should exploit the structural information such as citation links across papers and the hierarchy of sections and paragraphs in each paper. To tackle these challenges, in this study, we propose FUTEX, a framework that uses the cross-paper network structure and the in-paper hierarchy structure to classify full-text scientific papers under weak supervision. A network-aware contrastive fine-tuning module and a hierarchy-aware aggregation module are designed to leverage the two types of structural signals, respectively. Experiments on two benchmark datasets demonstrate that FUTEX significantly outperforms competitive baselines and is on par with fully supervised classifiers that use 1,000 to 60,000 ground-truth training samples.