End-to-End Neural Ranking for eCommerce Product Search: an application of task models and textual embeddings

TL;DR

This paper explores neural ranking models for eCommerce product search, comparing distributed and local-interaction approaches, and introduces a new dataset from click-through logs for training and evaluation.

Contribution

It presents a novel dataset for eCommerce relevance modeling and evaluates state-of-the-art IR models, highlighting their strengths and limitations in this context.

Findings

Local-interaction models reduce ranking errors by one-third compared to baseline.

Distributed models do not outperform the baseline on the new dataset.

Local-interaction models are more effective for relevance ranking in eCommerce.

Abstract

We consider the problem of retrieving and ranking items in an eCommerce catalog, often called SKUs, in order of relevance to a user-issued query. The input data for the ranking are the texts of the queries and textual fields of the SKUs indexed in the catalog. We review the ways in which this problem both resembles and differs from the problems of IR in the context of web search. The differences between the product-search problem and the IR problem of web search necessitate a different approach in terms of both models and datasets. We first review the recent state-of-the-art models for web search IR, distinguishing between two distinct types of model which we call the distributed type and the local-interaction type. The different types of relevance models developed for IR have complementary advantages and disadvantages when applied to eCommerce product search. Further, we explain why the conventional methods for dataset construction employed in the IR literature fail to produce data which suffices for training or evaluation of models for eCommerce product search. We explain how our own approach, applying task modeling techniques to the click-through logs of an eCommerce site, enables the construction of a large-scale dataset for training and robust benchmarking of relevance models. Our experiments consist of applying several of the models from the IR literature to our own dataset. Empirically, we have established that, when applied to our dataset, certain models of local-interaction type reduce ranking errors by one-third compared to the baseline tf-idf. Applied to our dataset, the distributed models fail to outperform the baseline. As a basis for a deployed system, the distributed models have several advantages, computationally, over the local-interaction models. This motivates an ongoing program of work, which we outline at the conclusion of the paper.