Schedule: Text, Language, and Speech sessions

Delip Rao and Brian McMahan explore natural language processing with deep learning, walking you through neural network architectures and NLP tasks and teaching you how to apply these architectures for those tasks. Read more.

Garrett Hoffman walks you through deep learning methods for natural language processing and natural language understanding tasks, using a live example in Python and TensorFlow with StockTwits data. Methods include word2vec, recurrent neural networks and variants (LSTM, GRU), and convolutional neural networks. Read more.

Justina Petraityte offers a hands-on walk-through of developing intelligent AI assistants based entirely on machine learning and using only the open source tools Rasa NLU and Rasa Core. You'll learn the fundamentals of conversational AI and best practices for developing AI assistants that scale and learn from real conversational data. Read more.

Twitter is a company with massive amounts of data, so it's no wonder that the company applies machine learning in myriad of ways. Cibele Montez Halasz and Satanjeev Banerjee describe one of those use cases: timeline ranking. They share some of the optimizations that the team has made—from modeling to infrastructure—in order to have models that are both expressive and efficient. Read more.

New AI solutions in question answering, chatbots, structured data extraction, text generation, and inference all require deep understanding of the nuances of human language. David Talby shares challenges, risks, and best practices for building NLU-based systems, drawing on examples and case studies from products and services built by Fortune 500 companies and startups over the past seven years. Read more.

Turning ML into magical products often requires complex distributed systems that bring with them a unique ML-specific set of infrastructure problems. Using AI to label GitHub issues as an example, Jeremy Lewi and Hamel Husain demonstrate how to use Kubeflow and Kubernetes to build and deploy ML products. Read more.

Word embeddings such as word2vec have revolutionized language modeling. Maryam Jahanshahi discusses exponential family embeddings, which apply probabilistic embedding models to other data types. Join in to learn how TapRecruit implemented a dynamic embedding model to understand how tech skill sets have changed over three years. Read more.

Sumeet Vij and Matt Speck showcase an innovative application of deep learning to power cognitive conversational agents. You'll learn how chatbots can overcome the limitations of limited training datasets by leveraging transfer learning and deep pretrained models for NLP and how machine learning can advance robotic process automation (RPA) from “robotic” to “cognitive” automation. Read more.

Vijay Agneeswaran and Abhishek Kumar offer an overview of capsule networks and explain how they help in handling spatial relationships between objects in an image. They also show how to apply them to text analytics. Vijay and Abhishek then explore an implementation of a recurrent capsule network and benchmark the RCN with capsule networks with dynamic routing on text analytics tasks. Read more.

Using AI to combat financial crime is more than strong fraud detection models monitoring transactions. Banks follow significant anti-money laundering (AML) and "know your customer" (KYC) laws and procedures, wrought with growth chained to cost and requiring auditable automation. Kyle Hoback walks you through a series of case studies that utilize AI-powered RPA that address AML and KYC. Read more.

Ming-Wei Chang offers an overview of a new language representation model called BERT (Bidirectional Encoder Representations from Transformers). Unlike recent language representation models, BERT is designed to pretrain deep bidirectional representations by jointly conditioning on both left and right context in all layers. Read more.

Anoop Katti explores the shortcomings of the existing techniques for understanding 2D documents and offers an overview of the Character Grid (Chargrid), a new processing pipeline pioneered by data scientists at SAP. Read more.

Chakri Cherukuri demonstrates how to apply machine learning techniques in quantitative finance, covering use cases involving both structured and alternative datasets. The focus of the talk will be on promoting reproducible research (through Jupyter notebooks and interactive plots) and interpretable models. Read more.

Tammy Bilitzky shares a case study that details lights-out automation and explains how DCL uses AI to transform massive volumes of confidential disparate data into searchable and structured information. Along the way, she outlines considerations for architecting a solution that processes a continuous flow of 5M+ “pages” of complex work units. Read more.

Jaewon Lee and Sihyeung Han walk you through implementing a self-trained dialogue model using AutoML and the Chatbot Builder Framework. You'll discover the value of AutoML, which allows you to provide better model, and learn how AutoML can be applied in different areas of NLP, not just for chatbots. Read more.