Loading…

Log in to bookmark your favorites and sync them to your phone or calendar.

AI Assistant Stage [clear filter]
Thursday, January 24
 

9:05am

Compère Welcome - AI Assistant Stage
Speakers
avatar for Ann Thyme-Gobbel, Sound United

Ann Thyme-Gobbel, Sound United

Voice & Natural Language UI / UX Researcher & Designer, Sound United
While doing a PhD in Cognitive Science and Linguistics at UCSD, Ann's interest in phonetics and NLP led to a dissertation using neural networks to model how speakers of a language form new words via paradigm patterning and token analogy. After that, Ann did R&D and product development... Read More →


Thursday January 24, 2019 9:05am - 9:15am
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

9:15am

Past, Present, and Future of Conversational AI
Conversational AI has always been the holy grail task for many scientists since the last several decades. Yet we observe tremendous advances from the early spoken language understanding systems used for call routing in 80s to modern personal assistants. In this talk, I will review the origins of conversational AI giving examples from pioneering systems, then present an overview of modern industrial and academic goal-oriented conversational systems, showing directions in our quest to building ultimate AI machines talking to humans.

Speakers
avatar for Gokhan Tur, Uber AI Labs

Gokhan Tur, Uber AI Labs

Director of Conversational AI, Uber AI Labs
Dr. Gokhan Tur is a leading artificial intelligence expert on human/machine conversational language understanding systems. He co-authored more than 150 papers published in journals or books and presented at conferences. He is the editor of the book entitled "Spoken Language Understanding... Read More →


Thursday January 24, 2019 9:15am - 9:40am
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

9:40am

Why Aren't Our AI Assistants Smarter?
Do our current crop of AI Assistants really use AI? If not, are they still useful? We'll look at the current state of AI Assistants, the challenges of building them, and speculate on what the future might bring.

Speakers
avatar for Cathy Pearl, Google

Cathy Pearl, Google

Head of Conversation Design Outreach, Google
Cathy Pearl is Head of Conversation Design Outreach at Google, and the author of the O'Reilly book, "Designing Voice User Interfaces". She's been designing and creating Voice User Interfaces (VUIs) for nearly 20 years and is passionate about helping everyone make the best conversational... Read More →


Thursday January 24, 2019 9:40am - 10:05am
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

11:00am

Dialog Management with a Software 2.0 Stack
Multi-turn conversations with users are hard. Writing code to handle each dialog path is easy to get started with but does not scale to all variations. Purely data-driven approaches are tough to get off the ground. How do we cross this chasm? This talk will present an approach to reliably scale to the long tail of conversational interactions using a combination of software development and machine learning.

Thursday January 24, 2019 11:00am - 11:20am
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

11:20am

Machine Learning for Continuous Improvement
The Autodesk Virtual Agent, AVA, plays a critical role in the Autodesk Digital Help & Experience organization’s goal of providing a seamless blend of digital and human support across all Autodesk help properties. In this talk, Nikhil will share how their virtual assistant has evolved since going live last year. He will touch upon AVA's beginnings in the customer support domain, improvements using customer interaction data, how to develop conversational analytics, integrating machine learning work from other teams and finally modularization strategy.

Speakers
avatar for Nikhil Mane, Autodesk

Nikhil Mane, Autodesk

Engineer - Conversation AI, Autodesk
Nikhil Mane is a Conversation Engineer at Autodesk developing technology with the goal of making it easy for customers to seek support. He works on developing software for delivering conversational solutions, exploring new technologies for expanding the team's capabilities and defining... Read More →


Thursday January 24, 2019 11:20am - 11:40am
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

11:40am

Conversational AI @ Facebook
Conversational AI is becoming a key part of various products at Facebook, including Portal, Messenger suggestions, Marketplace, recommendations, to name just a few. Being able to ship delightful conversational experiences means we also need to invest in solving hard research problems in areas such as language understanding, dialog management and language generation. In this talk, I will talk about some of the current work we're doing in these areas, as all as work we've done with Pytorch in order to enable our research scientists to quickly prototype and deploy advanced NLP models.

Speakers
avatar for Rushin Shah, Facebook

Rushin Shah, Facebook

Senior Manager, Facebook Conversational AI
Rushin Shah is a senior manager leading the natural language understanding group at Facebook Conversational AI. Previously, he was at Siri at Apple for 5 years, where he built and headed the natural language understanding group. He also worked at the query understanding group at Yahoo... Read More →


Thursday January 24, 2019 11:40am - 12:00pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

12:00pm

Building Customer Service Virtual Agents Faster and Smarter by Analyzing Human-to-human Interactions with ML
Innovative companies are modernizing their contact centers by adopting AI-powered virtual agents to improve customer satisfaction by providing helpful service 24/7, globally. But for brands building a virtual agent, the critical questions are:
  • What are the best use cases for the virtual agent?
  • What questions do customers ask and how do they phrase them (including follow-ups)?
  • How to ensure virtual agents responds helpfully?
  • What is the optimal time to do a hand-off to a live agent?
Particularly for companies with large customer service operations, answering the questions above manually is slow, based on guesswork, and creates gaps that put customer satisfaction at risk. In this session, attendees will learn how machine learning techniques can unlock actionable insights from human-to-human interactions in contact center chat and call logs -- making development much faster, and virtual agents much smarter.

Speakers
avatar for Ofer Ronen, Chatbase

Ofer Ronen, Chatbase

General Manager, Chatbase
Ofer Ronen is the general manager of Chatbase, a conversational analytics service brought to you by Area 120 (a products incubator operated by Google). Previously, he was CEO of Pulse.io, an app performance monitoring service (acquired by Google), and CEO of ad network Sendori (acquired... Read More →



Thursday January 24, 2019 12:00pm - 12:25pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

1:20pm

Artificial Training Data: How to Automate Your Bot Training
One of the main problems with the current generation of chatbots is that they require large amounts of training data. If you want your chatbot to recognize a specific intent, you need to provide it with a large number of sentences that express that intent. Until now, these large training corpora had to be generated manually, with one or more people writing many different sentences for each intent, vertical and language that needed to be recognized in your chatbot. Bitext Artificial Training Data technology (also called Natural Language Generation) automatically generates many different sentences with the same meaning as the original one, in order to automate the most resource-intensive part of the bot creation process.

Speakers
avatar for Antonio Valderrábanos, Bitext

Antonio Valderrábanos, Bitext

Founder & CEO, Bitext
Antonio has a long experience on how to use Deep Linguistic Analysis to solve business problems in the area of text analysis.His current focus is on how to exploit linguistic knowledge to improve machine learning and AI engines, to make them smarter and easier to train. Chatbots are... Read More →


Thursday January 24, 2019 1:20pm - 1:45pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

1:45pm

Adding Structure to Spoken Language Understanding
Typically spoken language understanding(SLU) systems factor the language understanding problem into intent classification and slot tagging.
This presents an inherent limitation for more complex linguistic phenomenon like coordination where the  user expresses multiple intents in a statement.
In this talk we present 2 ways in which we can add structure to SLU. First, we talk about incorporating an external parser to solve coordination if we want to extend a legacy system.
Second we pose SLU as a shallow semantic parsing problem which is also able to handle tasks like Question answering. We also talk about solving the data sparsity issue by doing transfer learning between domains and by using techniques like delexicalization and copy mechanism.

Speakers
avatar for Rahul Goel, Alexa AI

Rahul Goel, Alexa AI

Machine Learning Scientist, Alexa AI
Rahul Goel is a machine learning scientist at Alexa AI where he works on improving spoken language understanding and dialog systems. Many of his contributions are currently deployed in Alexa. His research interests include dialog systems, language understanding, deep learning, and... Read More →


Thursday January 24, 2019 1:45pm - 2:10pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

2:10pm

Chatbots: The (Long) Tail Wags the Dog
Give a customer a chatbot meant to help them track packages, and they’ll ask it to change their delivery address, send them proof of delivery and cook them dinner. In general, customers expect chatbots to handle a large quantity of very specific tasks, and each task requires custom, time consuming, hard coded API integrations. That’s not scalable. In this talk, I’ll go over the novel AI and UX techniques that Eloquent Labs uses to tackle this problem -- and how we’re using our approach to make chatbots work in customer facing environments.

Speakers
avatar for Arun Chaganty, Eloquent Labs

Arun Chaganty, Eloquent Labs

Head of Artificial Intelligence, Eloquent Labs
Arun Chaganty is the Head of AI at Eloquent Labs and recently graduated with a PhD from the Stanford NLP group. He is interested in making it easier for people to scale up the information they are able to access, process and comprehend through robust machine learning systems with... Read More →


Thursday January 24, 2019 2:10pm - 2:35pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

2:35pm

Open-Ended Challenges in Dialog Systems
Dialog Systems have come a long way, especially with advancements brought by assistants such as Alexa. However, there are several open-ended challenges which makes it hard to build fully Conversational Dialog Systems. In this talk, I will go over some of these open-ended challenges and discuss how to address them.

Speakers
avatar for Chandra Khatri, Uber AI Labs

Chandra Khatri, Uber AI Labs

Senior AI Scientist, Uber AI Labs
Chandra Khatri is a Senior AI Scientist at Uber AI driving Conversational AI efforts at Uber. Prior to Uber, he was the Lead AI Scientist at Alexa and was driving the Science for the Alexa Prize Competition, which is a $3.5 Million university competition for advancing the state of... Read More →


Thursday January 24, 2019 2:35pm - 3:00pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

3:00pm

With Great Dialog Comes Great Responsibility
Conversations have extraordinary power. They can harm or heal, obfuscate or enlighten, generate confusion or clarity. They can condition us to subtly alter our behavior, and they even shape how we perceive our own inner emotions. So as we teach our devices to converse with us, how can we wield that power responsibly? And how do we teach our algorithms to do the same?

Speakers
avatar for Deborah Harrison, Microsoft

Deborah Harrison, Microsoft

Senior Conversational UI Design Manager, Microsoft
Deborah Harrison (writer, Microsoft) is one of the original architects of the personality for Microsoft's digital assistant, Cortana. She crafted the core principles that define Cortana's approach to communication and now helps shepherd those principles as Cortana lights up on other... Read More →


Thursday January 24, 2019 3:00pm - 3:25pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

3:55pm

Empathy Training 101
What is empathy?  What are some characteristics of empathy in human conversations, and how can we train virtual assistants to exhibit these properties?  We will explore the nature of empathic communication and explore various NLP and machine learning techniques for imbuing a feeling of compassion in your agents.  These approaches help users feel understood and can be used to improve the user experience of nearly any type of AI assistant.


Speakers
avatar for Casey Sackett, Woebot Labs

Casey Sackett, Woebot Labs

CTO, Woebot Labs
I am a hands-on engineering leader who enjoys being involved in all aspects of technical innovation and delivery, from vision to product design to team management to coding and execution. I have strong interests in health technology and social networking and in ways of using math... Read More →


Thursday January 24, 2019 3:55pm - 4:15pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

4:15pm

Building Neural Conversational Machines at Scale
Advances in deep learning have enabled us to build intelligent systems capable of perceiving and understanding real world from text, speech and images. Yet, building real-world Conversational AI systems at scale and from “scratch” remains a daunting challenge as it requires us to deal with ambiguity, data sparsity and solve complex language, dialog and generation problems.
In this talk, I will present powerful neural structured learning frameworks that tackle the above challenges by leveraging the power of deep learning combined with graphs which allow us to model the structure inherent in language and visual data. Our neural graph learning approach handles massive graphs with billions of vertices and trillions of edges and has been successfully used to power real-world applications such as Smart Reply, image recognition and multimodal experiences in many Google products both on Cloud and on-device. Finally, I will describe our recent work on reinforcement learning for controllable dialog generation, where we train a neural network that produces conversational responses conforming to specific semantic attributes such as sentiment, emotion and personality.

Speakers
avatar for Sujith Ravi, Google

Sujith Ravi, Google

Senior Staff Research Scientist, Google
Dr. Sujith Ravi is a Senior Staff Research Scientist and Senior Manager at Google, where he leads the company’s large-scale graph-based machine learning platform and on-device machine learning efforts that power natural language understanding and image recognition for products used... Read More →


Thursday January 24, 2019 4:15pm - 4:35pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA

4:35pm

Can an AI Assistant be as Important as the Web or as Mobile?
AI Assistants are used billions of times each week and have been baked into more than a billion consumer devices.  People talk to them to accomplish functions like playing songs, sending text messages, setting timers, and more.  However, while these Assistants are useful, today they are not a global paradigm like the Web or like Mobile, which impact every connected user and every connected business.  In this talk, we will discuss what it might take for an Assistant to make the leap to global paradigm, and then illustrate the unique architecture and approach being taken by Samsung’s Bixby Assistant with the goal of doing just that.

Speakers
avatar for Adam Cheyer, Viv Labs/Samsung

Adam Cheyer, Viv Labs/Samsung

Co-Founder and VP Engineering/VP of R&D, Viv Labs/Samsung
Adam Cheyer is co-Founder and VP Engineering of Viv Labs, and after acquisition in 2016, a VP of R&D at Samsung. Previously, Mr. Cheyer was co-Founder and VP Engineering at Siri, Inc. In 2010, Siri was acquired by Apple, where he became a Director of Engineering in the iPhone/iOS... Read More →


Thursday January 24, 2019 4:35pm - 5:00pm
Pacific D-F Hyatt Regency San Francisco, 5 Embarcadero Center, San Francisco, CA 94111, USA