An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining

TL;DR

This study explores how structured Linked Data from the Web can be utilized for product data mining in e-commerce, demonstrating that word embeddings significantly improve classification and linking tasks, despite limitations in data coverage.

Contribution

It introduces methods for leveraging Linked Open Data to create language resources for product classification and linking, and evaluates their effectiveness in e-commerce.

Findings

Word embeddings improve accuracy by up to 6.9 percentage points.

Other methods like language model pre-training and translation are less effective.

Structured data biases and vocabulary gaps limit performance.

Abstract

The Linked Open Data practice has led to a significant growth of structured data on the Web in the last decade. Such structured data describe real-world entities in a machine-readable way, and have created an unprecedented opportunity for research in the field of Natural Language Processing. However, there is a lack of studies on how such data can be used, for what kind of tasks, and to what extent they can be useful for these tasks. This work focuses on the e-commerce domain to explore methods of utilising such structured data to create language resources that may be used for product classification and linking. We process billions of structured data points in the form of RDF n-quads, to create multi-million words of product-related corpora that are later used in three different ways for creating of language resources: training word embedding models, continued pre-training of BERT-like language models, and training Machine Translation models that are used as a proxy to generate product-related keywords. Our evaluation on an extensive set of benchmarks shows word embeddings to be the most reliable and consistent method to improve the accuracy on both tasks (with up to 6.9 percentage points in macro-average F1 on some datasets). The other two methods however, are not as useful. Our analysis shows that this could be due to a number of reasons, including the biased domain representation in the structured data and lack of vocabulary coverage. We share our datasets and discuss how our lessons learned could be taken forward to inform future research in this direction.