Query2Prod2Vec Grounded Word Embeddings for eCommerce

TL;DR

Query2Prod2Vec is a novel model that creates grounded word embeddings for eCommerce by mapping words to product spaces, improving accuracy and data efficiency in product search applications.

Contribution

It introduces a new approach to grounding lexical representations in product embeddings using shopping sessions and merchandising annotations, outperforming existing NLP and IR techniques.

Findings

Model achieves higher accuracy than known NLP and IR methods.

Utilizes shopping sessions and annotations for effective embedding learning.

Emphasizes data efficiency for practical eCommerce applications.

Abstract

We present Query2Prod2Vec, a model that grounds lexical representations for product search in product embeddings: in our model, meaning is a mapping between words and a latent space of products in a digital shop. We leverage shopping sessions to learn the underlying space and use merchandising annotations to build lexical analogies for evaluation: our experiments show that our model is more accurate than known techniques from the NLP and IR literature. Finally, we stress the importance of data efficiency for product search outside of retail giants, and highlight how Query2Prod2Vec fits with practical constraints faced by most practitioners.