arrow_back Deep Learning in the Browser: Explorable Explanations, Model Inference & Rapid Prototyping
Building and driving adoption for a robust semantic search system
Submitted by Hrishikesh Ganu (@hrishikeshvganu) on Tuesday, 12 June 2018
Section: Crisp Talk Technical level: Intermediate
This talk focuses on how to use deep learning based sub-word embeddings to create a practical search system robust to queries with mis-spellings, SMS lingo etc. Lifts of upto 20% in search recall compared to commercial solutions were demonstrated with retrieval latency of just 50 milliseconds for queries with mis-spellings and other aberrations.
This talk will be based on a paper published at NAACL-2018
In addition to technical details we will also talk about softer aspects of doing data science. Especially our experience working with business and engineering and how to convince the leadership to adopt products. I’ll share anecdotes based on my work with several clients at Mu Sigma, internal teams at Amazon and at Intuit.
The CUI imperative
What is Zelda?
What does business want?
QnA: we’ll take questions towards the end
Hrishi did his Master’s from Indian Institute of Science (IISc), Bangalore where he worked on Computer Vision for studying atomization in Cryogenic Rocket Engines. Post that he did a full-time MBA from IIM-Kozhikode. He has been working in the ML/Analytics space for over 10 years and has had long stints at Amazon Core ML and at Mu Sigma before joining Intuit’s IAT team. At Intuit, he’s working on NLP with a focus on creating algorithms that are robust to noise in user input.
Aside of work he spends time playing with his 3-year-old daughter and in solving puzzles.