The large-scale nature of product catalog and the changing demands of customer queries makes product search a challenging problem. The customer queries are ambiguous and implicit. They may be looking for an exact match of their query, or a functional equivalent (i.e., substitute), or an accessory to go with it (i.e., complement). It is important to distinguish these three categories from merely classifying an item for a customer query as relevant or not. This information can help direct the customer and improve search applications to understand the customer mission. In this paper, we formulate search relevance as a multi-class classification problem and propose a graph-based solution to classify a given query-item pair as exact, substitute, complement, or irrelevant (ESCI). The customer engagement (clicks, add-to-cart, and purchases) between query and items serve as a crucial information for this problem. However, existing approaches rely purely on the textual information (such as BERT) and do not sufficiently focus on the structural relationships. Another challenge in including the structural information is the sparsity of such data in some regions. We propose Structure-Aware multilingual LAnguage Model (SALAM), that utilizes a language model along with a graph neural network, to extract region-specific semantics as well as relational information for the classification of query-product pairs. Our model is first pre-trained on a large region-agnostic dataset and behavioral graph data and then fine-tuned on region-specific versions to address the sparsity. We show in our experiments that SALAM significantly outperforms the current matching frameworks on the ESCI classification task in several regions. We also demonstrate the effectiveness of using a two-phased training setup (i.e., pre-training and fine-tuning) in capturing region-specific information. Also, we provide various challenges and solutions for using the model in an industrial setting and outline its contribution to the e-commerce engine.

Graph-based Multilingual Language Model: Leveraging Product Relations for Search Relevance

Mostly with growth of the information sector, in particular the World wide web and the mobile Internet, the volume of information that we’ll have to contend with is rapidly increasing. To a certain degree, users could get the information they need from the Internet. And in context of these vast availability and proliferation of information, users need an efficient way of finding only important and interesting information. How to optimize usability during information search process is still not addressed. Searching was the key feature of a conventional search engine. There has been insufficient customization in search engines to be used by searchers during the information extraction process. This article thus analysed and discussed the personalized recommendations of searches using a tailored framework that supports search engines. We describe a comprehensive review of the study on search engine customization for web-based queries. The study is partially systematic and, also at end of the study, we discuss the difficulties of personalizing search engines.

/pdf/a-survey-on-the-use-of-personalized-model-based-search-36isau9y2y.pdf

Taofiq Adeola Bakare

Papers

A Survey on the Use of Personalized Model-Based Search Engine