Several weeks ago, I wrote a post advocating the use of AI for query understanding. I argued that holistic query understanding with embeddings and deep learning is a great way to look beyond keywords and not only classify queries into categories or topics, but also to recognize queries that represent similar or equivalent intent.
Now I’m proud to share work that my colleague Aritra Mandal has been doing in this area. Aritra, an applied researcher on eBay’s query understanding team, presented at the MICES 2021 ecommerce search conference on “Using AI to Understand Search Intent”. It’s a whirlwind tour explaining how to use AI to categorize queries and recognize query equivalence or similarity.
I highly recommend this presentation to anyone working on ecommerce search. It outlines how to train a query categorization model from click or purchase data, as well as how to recognize equivalent queries from surface query similarity and post-search data. As he says, the devil is in the details, and there’s a bunch of work necessary to translate these ideas into a production-ready system. Still, these are ideas you will want in your toolbox!