Attribute Extraction from Product Titles in eCommerce

TL;DR

This paper introduces a system for extracting product attributes from short eCommerce titles, combining sequence labeling algorithms with normalization to improve accuracy in a challenging, syntactically sparse context.

Contribution

The paper presents a novel attribute extraction system that effectively combines sequence labeling algorithms with normalization for eCommerce product titles.

Findings

Effective extraction of product attributes demonstrated

Comparison shows improved performance over baseline methods

System performs well on short, unstructured product titles

Abstract

This paper presents a named entity extraction system for detecting attributes in product titles of eCommerce retailers like Walmart. The absence of syntactic structure in such short pieces of text makes extracting attribute values a challenging problem. We find that combining sequence labeling algorithms such as Conditional Random Fields and Structured Perceptron with a curated normalization scheme produces an effective system for the task of extracting product attribute values from titles. To keep the discussion concrete, we will illustrate the mechanics of the system from the point of view of a particular attribute - brand. We also discuss the importance of an attribute extraction system in the context of retail websites with large product catalogs, compare our approach to other potential approaches to this problem and end the paper with a discussion of the performance of our system for extracting attributes.