CRMSP: A Semi-supervised Approach for Key Information Extraction with Class-Rebalancing and Merged Semantic Pseudo-Labeling

TL;DR

This paper introduces CRMSP, a semi-supervised method for Key Information Extraction that rebalances pseudo-labels and clusters tail features, significantly improving performance on benchmark datasets.

Contribution

The paper presents a novel semi-supervised approach with class-rebalancing and semantic pseudo-labeling modules, addressing tail class challenges in KIE.

Findings

Achieves state-of-the-art results on three benchmarks.

Improves F1-score by 3.24% on CORD dataset.

Effectively balances tail class pseudo-labels.

Abstract

There is a growing demand in the field of KIE (Key Information Extraction) to apply semi-supervised learning to save manpower and costs, as training document data using fully-supervised methods requires labor-intensive manual annotation. The main challenges of applying SSL in the KIE are (1) underestimation of the confidence of tail classes in the long-tailed distribution and (2) difficulty in achieving intra-class compactness and inter-class separability of tail features. To address these challenges, we propose a novel semi-supervised approach for KIE with Class-Rebalancing and Merged Semantic Pseudo-Labeling (CRMSP). Firstly, the Class-Rebalancing Pseudo-Labeling (CRP) module introduces a reweighting factor to rebalance pseudo-labels, increasing attention to tail classes. Secondly, we propose the Merged Semantic Pseudo-Labeling (MSP) module to cluster tail features of unlabeled data by assigning samples to Merged Prototypes (MP). Additionally, we designed a new contrastive loss specifically for MSP. Extensive experimental results on three well-known benchmarks demonstrate that CRMSP achieves state-of-the-art performance. Remarkably, CRMSP achieves 3.24% f1-score improvement over state-of-the-art on the CORD.