Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction

TL;DR

This paper introduces a simple knowledge-driven query expansion method for QA-based product attribute extraction, improving accuracy especially for rare and ambiguous attributes in e-commerce data.

Contribution

It proposes a novel query expansion technique using attribute values from training data and training tricks to handle knowledge imperfection, enhancing AVE performance.

Findings

Improves AVE macro F1 by 6.08 points on AliExpress dataset.

Significantly boosts performance for rare attributes (+7.82 macro F1).

Enhances extraction accuracy for ambiguous attributes (+6.86 macro F1).

Abstract

A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products. Although this challenge is partially addressed by a question answering (QA) approach which finds a value in product data for a given query (attribute), it does not work effectively for rare and ambiguous queries. We thus propose simple knowledge-driven query expansion based on possible answers (values) of a query (attribute) for QA-based AVE. We retrieve values of a query (attribute) from the training data to expand the query. We train a model with two tricks, knowledge dropout and knowledge token mixing, which mimic the imperfection of the value knowledge in testing. Experimental results on our cleaned version of AliExpress dataset show that our method improves the performance of AVE (+6.08 macro F1), especially for rare and ambiguous attributes (+7.82 and +6.86 macro F1, respectively).