Zero to State-Of-The-Art
Search Engines

Get your team up to speed with our hands-on deep training on Information Retrieval. Based on the materials presented at top academic conferences.

What is it about?

Search is perhaps the most familiar and valuable service for the Internet. Google processes over a billion queries per day, more than 30% of all e-commerce transactions are attributed to web search and more than 50% if the within-site search is included. Given merely a few keywords, a search engine can return ten highly relevant links in a matter of milliseconds and search over zettabytes of heterogeneous content such as text, images, and videos. Designing such a system involves the solution of many challenging engineering challenges.

In this training we provide all necessary knowledge to design a complete fully-functional search engine from scratch. We start from the content representation, storage and indexing, consider basic and advanced information retrieval models, and provide an in-depth review of machine learning approaches for search ranking. Next, we talk about the search user interface aspects, proper evaluation, A/B testing and experiment design methodologies specifically developed for search systems. Finally, we switch to the hands-on part of the training and help the participants design their own search engines using Elasticsearch and by incorporating all lectured materials. We will use publicly accessible learning to rank datasets for machine learning and text collections (e.g. ClueWeb or Wikipedia dumps), as well as data relevant for your company or organization.

Training Content