Query autocompletion/autosuggest has strict latency requirements. This latest work by Linkedin incorporates context and deep semantics to improve the quality of autosuggestions and uses an unnormalized language model to keep latency requirements within industry standards.
https://arxiv.org/abs/2008.02879
https://dl.acm.org/doi/abs/10.1145/3366424.3382183
https://arxiv.org/pdf/2008.08180.pdf
https://arxiv.org/pdf/1907.00937.pdf
https://sdm-dsre.github.io/pdf/named_entity.pdf
https://arxiv.org/pdf/2004.14245.pdf
Amazon is one of the world’s largest e-commerce sites and Amazon Search powers the majority of Amazon’s sales. As a consequence, even small improvements in relevance ranking both positively influence the shopping experience of millions of customers and significantly impact revenue. In the past, Amazon’s product search engine consisted of several handtuned ranking functions using a handful of input features. A lot has changed since then. In this talk we are going to cover a number of relevance algorithms used in Amazon Search today. We will describe a general machine learning framework used for ranking within categories, blending separate rankings in All Product Search, NLP techniques used for matching queries and products, and algorithms targeted at unique tasks of specific categories — books and fashion.
http://ceur-ws.org/Vol-2410/paper37.pdf