A BERT-based Hierarchical Classification Model with Applications in Chinese Commodity Classification

TL;DR

This paper introduces a large-scale hierarchical product dataset from JD.com and proposes HFT-BERT, a BERT-based model that effectively classifies products within a hierarchical structure, especially excelling with longer texts.

Contribution

The paper provides a large, openly accessible hierarchical product dataset and develops HFT-BERT, a novel hierarchical classification model leveraging BERT for improved accuracy.

Findings

HFT-BERT achieves performance comparable to existing methods on short texts.

HFT-BERT significantly outperforms in classifying longer texts like books.

The dataset facilitates future research in product categorization.

Abstract

Existing e-commerce platforms heavily rely on manual annotation for product categorization, which is inefficient and inconsistent. These platforms often employ a hierarchical structure for categorizing products; however, few studies have leveraged this hierarchical information for classification. Furthermore, studies that consider hierarchical information fail to account for similarities and differences across various hierarchical categories. Herein, we introduce a large-scale hierarchical dataset collected from the JD e-commerce platform (www.JD.com), comprising 1,011,450 products with titles and a three-level category structure. By making this dataset openly accessible, we provide a valuable resource for researchers and practitioners to advance research and applications associated with product categorization. Moreover, we propose a novel hierarchical text classification approach based on the widely used Bidirectional Encoder Representations from Transformers (BERT), called Hierarchical Fine-tuning BERT (HFT-BERT). HFT-BERT leverages the remarkable text feature extraction capabilities of BERT, achieving prediction performance comparable to those of existing methods on short texts. Notably, our HFT-BERT model demonstrates exceptional performance in categorizing longer short texts, such as books.