Abstract

In this talk Daniel will cover the goals and some of the technical challenges of building Facebook’s Post Search, a product that allows people to search through more than 2 trillion posts shared on the network. He will highlight some of the key pieces of this large-scale information retrieval system, including his main areas of work: spelling correction and natural language processing.

Daniel Bernhardt has been working on the Search team at Facebook London since August 2013. He is interested in search relevance, metrics and query rewriting. His current work concerns query expansions for Facebook Post Search which includes semantic representations for queries and query terms, machine learning components for ranking and classification as well as quality measurement. Before joining Facebook he was a software engineer in web search at Bing London. In 2009 he received a PhD in affective computing from the Computer Laboratory, University of Cambridge.