Text analytics 101: Deep learning and attention networks all the way to production

pramod singh (Walmart Labs ), Akshay Kulkarni (Publicis Sapient)

13:30–17:00 Tuesday, 15 October 2019

Location: Buckingham Room - Palace Suite

Implementing AI

Secondary topics: Deep Learning, Machine Learning, Text, Language, and Speech

Average rating:

(2.40, 10 ratings)

Who is this presentation for?

Data scientists, data engineers, data architects, CxOs, and software engineers

Level

Beginner

Description

According to industry estimates, more than 80% of the data being generated is in an unstructured format, maybe in the form of text, an image, audio, or video. Data is generated as we speak, write, tweet, use social media, send messages, use ecommerce, or perform various other activities. Textual data is the most common, accounting for more than 50% of existing data. A lot of insights can be mined from this huge repository of unstructured datasets, but it requires a sophisticated approach.

In order to produce significant and actionable insights from text data, it’s necessary to make use of natural language processing (NLP) coupled with machine learning, deep learning, and state-of-the-art techniques in this space. With the latest developments and improvements in the field of deep learning and artificial intelligence, many demanding natural language processing tasks become easy to implement and execute. Text generation is one of the tasks that can be built using deep learning models, especially recurrent neural networks and its variant, long short-term memories (LSTMs).

Text generation is a language modeling problem. Language modeling is at the heart of many natural language processing tasks, such as speech synthesis, session systems, and text synthesis. A well-trained language model learns the probability of a word appearing based on a sequence of previous words used in the text. Language models can be used at the level of characters, n-grams, sentences, and even paragraphs.

Vijay Srinivas Agneeswaran, Pramod Singh, and Akshay Kulkarni explore how to create a language model that generates natural language text by implementing and forming a recurrent neural network and attention networks built on top of TensorFlow 2.0. They also examine how to efficiently build and use NLP-based applications for text summarization using deep learning networks on TensorFlow 2.0. Text summarization requires a great deal of abstraction, so they use sequence-to-sequence models and bidirectional encoder and decoders.

Not only do you get to see the notebooks for the problems outlined above but also how some of text analytics can be implemented on top of Kubeflow, which helps build scalable productionizable implementations.

Prerequisite knowledge

A basic understanding of deep learning

What you'll learn

Get an introduction to NLP and different components, such as summarization and generation, and NLP using deep learning, such as why deep learning-based frameworks are required for NLP tasks
An understanding of TensorFlow 2.0, state-of-the-art recurrent neuron network, LSTMs, and attention networks for NLP tasks
Learn about TensorFlow 2.0 notebooks plus end-to-end text analytics code using Kubeflow

pramod singh

Walmart Labs

Pramod Singh is a senior machine learning engineer at Walmart Labs. He has extensive hands-on experience in machine learning, deep learning, AI, data engineering, designing algorithms, and application development. He has spent more than 10 years working on multiple data projects at different organizations. He’s the author of three books Machine Learning with PySpark, Learn PySpark, and Learn TensorFlow 2.0. He’s also a regular speaker at major conferences such as the O’Reilly Strata Data and AI Conferences. Pramod holds a BTech in electrical engineering from BATU, and an MBA from Symbiosis University. He’s also done data science certification from IIM–Calcutta. He lives in Bangalore with his wife and three-year-old son. In his spare time, he enjoys playing guitar, coding, reading, and watching football.

Website

Akshay Kulkarni

Publicis Sapient

Akshay Kulkarni is a senior data scientist with SapientRazorfish’s core AI and data science team, where he’s part of strategy and transformation interventions through AI, manages high priority growth initiatives around data science and works on various machine learning, deep learning, natural language processing, and artificial intelligence engagements by applying state-of-the-art techniques, as well as a renowned AI and machine learning evangelist, an author, and a speaker. He was recently recognized as one of the “top 40 under 40 data scientists” in India by Analytics India Magazine. He’s consulted with several Fortune 500 and global enterprises in driving AI and data science-led strategic transformations. Akshay has a rich experience of building and scaling AI and machine learning businesses and creating significant client impact. He’s actively involved in next gen AI research and is also a part of next gen AI community. Previously, he was part of Gartner and Accenture, where he scaled the AI and data science business. He’s a regular speaker at major data science conferences recently gave a talk on “Sequence Embeddings for Prediction Using Deep Learning” at GIDS. He’s the author of a book on NLP with Apress and currently authoring couple more books with Packt on deep learning and next gen NLP. He is also a visiting faculty (industry expert) at few of the top universities in India. In his spare time, he likes to read, write, code, and help aspiring data scientists.