AE-smnsMLC: Multi-Label Classification with Semantic Matching and Negative Label Sampling for Product Attribute Value Extraction

TL;DR

This paper introduces AE-smnsMLC, a multi-label classification approach for product attribute value extraction that leverages semantic matching and negative label sampling, effectively handling weak annotations and improving extraction accuracy in e-Commerce.

Contribution

It reformulates attribute value extraction as a multi-label classification task and proposes a novel model with semantic matching and negative label sampling for better performance.

Findings

Outperforms existing methods on real-world e-Commerce datasets.

Effectively handles weakly-annotated data without positional labels.

Demonstrates superior accuracy in attribute value extraction.

Abstract

Product attribute value extraction plays an important role for many real-world applications in e-Commerce such as product search and recommendation. Previous methods treat it as a sequence labeling task that needs more annotation for position of values in the product text. This limits their application to real-world scenario in which only attribute values are weakly-annotated for each product without their position. Moreover, these methods only use product text (i.e., product title and description) and do not consider the semantic connection between the multiple attribute values of a given product and its text, which can help attribute value extraction. In this paper, we reformulate this task as a multi-label classification task that can be applied for real-world scenario in which only annotation of attribute values is available to train models (i.e., annotation of positional information of attribute values is not available). We propose a classification model with semantic matching and negative label sampling for attribute value extraction. Semantic matching aims to capture semantic interactions between attribute values of a given product and its text. Negative label sampling aims to enhance the model's ability of distinguishing similar values belonging to the same attribute. Experimental results on three subsets of a large real-world e-Commerce dataset demonstrate the effectiveness and superiority of our proposed model.