OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision

TL;DR

This paper introduces OA-Mine, a weakly supervised open-world attribute mining framework that extracts new product attributes and values from textual descriptions, addressing the challenge of constantly evolving e-commerce product types.

Contribution

The work presents a novel framework combining candidate generation and clustering to discover new attributes and values with minimal supervision, leveraging pre-trained language models.

Findings

Outperforms strong baselines on large datasets

Effectively generalizes to unseen attributes

Handles open-world, evolving product types

Abstract

Automatic extraction of product attributes from their textual descriptions is essential for online shopper experience. One inherent challenge of this task is the emerging nature of e-commerce products -- we see new types of products with their unique set of new attributes constantly. Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data. In this work, we study the attribute mining problem in an open-world setting to extract novel attributes and their values. Instead of providing comprehensive training data, the user only needs to provide a few examples for a few known attribute types as weak supervision. We propose a principled framework that first generates attribute value candidates and then groups them into clusters of attributes. The candidate generation step probes a pre-trained language model to extract phrases from product titles. Then, an attribute-aware fine-tuning method optimizes a multitask objective and shapes the language model representation to be attribute-discriminative. Finally, we discover new attributes and values through the self-ensemble of our framework, which handles the open-world challenge. We run extensive experiments on a large distantly annotated development set and a gold standard human-annotated test set that we collected. Our model significantly outperforms strong baselines and can generalize to unseen attributes and product types.