Deep Learning for Search in e-commerce

Sonu Sharma and Atul Argarwal • Location: Theater 5 • Back to Haystack 2020

The agenda of the talk has been broken down into two parts:

  1. Query Understanding: [Sonu Sharma] NLP based Deep Learning Models for finding the intent of a Query in a particular taxonomy/categories: Description and Jupyter-notebook demonstration: Multi-Label/Multi-Class Classification Model from scratch in Keras o Feature Engineering in Spark Scala and pandas ImageNet moment of NLP - Latest invention in Word embeddings - ELMO and BeRT NLP based Deep Learning Models for Query Tagging with entities like Brand, Color, Nutrition, product quantity, etc. using Named Entity Recognition: [10mins]: Traditional Word Embeddings like Glove, Fasttext, etc. o Query (Text) Preprocessing Sequence modeling using Convolutional Random Fields (CRF)

  2. Related Searches : [Atul Agarwal] NLP based Deep Learning Model for predicting Next Search Keyword - Model Description and Jupyter Notebook demonstration: Building Sequence to Sequence (Seq2Seq) model using Long Short Term Memory (LSTM) concept of Deep Neural Network in Keras o comparing different word Embeddings e.g. word2vec, fasttext, glove, etc. in popular AI framework such as gensim. Similarity Search based on Facebook AI Research aka FAISS.

Sonu Sharma

LinkedIn Profile

Sonu is currently working as a Software Engineer in Search Team of Walmart Labs International in Bangalore. His core interests include Natural Language Processing and Computer Vision. Over the last 3 years, Walmart International Search has undergone a major transformation and Sonu has been part of the core team which has made this possible. He is primarily involved in building analytics engines and services for the search platform using Deep Learning Models, in the context of Query Understanding, Relevance and Personalisation of Search. He is currently working on Visual Search and personalised search. He is NIT Allahabad 2017 graduate in Computer Science & Engineering.

Atul Argarwal

LinkedIn Profile

Atul is IIIT-Hyderabad 2017 graduate, currently working as a Software Engineer in Search Team of Walmart Labs International in Bangalore. Over the last 3 years, Walmart International Search has undergone a major transformation and Atul has been part of the core team which has made this possible. He is primarily involved in building analytics engines and services for the search platform using Deep Learning in the context of Taxonomy Classification, Reinforcement Learning for Search Relevance & Refinement. He is currently working on seq2seq models for Related and Refined Search. His interests include Natural Language Processing and Computer Vision.