ACCS

Vijay Gabale

Tech Talk at ADCOM 2016

Title : Applying Deep Image and Text Parsing At E-commerce Scale

Abstract: With the wave of discounts from e-commerce 1.0 on decline, online commerce experiences are steadily picking up as the means to acquire and retain consumers in e-commerce 2.0. While consumers interact with buyer-side portals, the organization of products (aka catalogues) acquired through seller-side platforms plays pivotal role towards search, discovery and personalization experiences. Unfortunately, different sellers have different interpretations of the same product and distributed onboarding of products produces poorly organized e-commerce catalogues. This further results in poor and irrelevant search, personalization and recommendations; degrading user experience significantly. Furthermore, due to inherent difficulties in describing and quantifying product details, the problem of organizing products as SKUs in categories such as fashion and lifestyle has been largely unsolved.

In this talk, I will describe how deep learning has made it possible to prepare SKUs for fashion and lifestyle products. We innovate and apply deep image parsing to extract detailed product information from product images. We further apply deep learning models originally conceived for images to process text paragraphs to solve Named Entity Recognition and Disambiguation to produce structured outputs. Using confidence scores of the two process, we then combine results of text and image parsing to merge and create unique products. I will also describe evaluation criteria and several engineering-challenges to build large-scale systems to process product steams and normalize millions of fashion products.
vijay-gabaleBio:
Vijay is a co-founder and CTO at Huew, intelligent fashion commerce platform. Prior to Huew, Vijay was a research scientist at IBM Research labs. Vijay obtained his PhD from IIT Bombay, India in 2012. He has keen interest in solving large-scale systemic problems. His research interests are in deep learning, large-scale machine learning and distributed systems.