ai assistant summit - san francisco;

Notes on talks at AI Assistant Summit in San Francisco.

Thursday - 25 January

Siva Reddy - Stanford NLP Group

The State of Natural Language Understanding: Past, Present and Future

Ian Lane - Carnegie Mellon University

Deep Learning for Spoken Language Understanding
People also don’t understand dialog fully. 5.5% error rate - but they ask questions in order to disambiguate.
By trying to understand what person is saying helps to bias the system into correctly transcribing
bi-directional LSTM work for pretty much everythingu
Estimate domain during parsing

Don’t only model agents but also model users. Different people can have different dialogs,
So the types of users should be modeled. The user model and agent model can converse with each other.
Then we can test if this looks like actual dialogs that people can have. This improves performance dramatically
Error handling is actually hard. You need the bot to take the user on track if he inputs nonsense. You also need to throw garbage information out of the system.

Eric Saund - Saund Laboratories

Cognitive Belief Modeling for Naturalistic Dialog Management

Look-up: Noah Goodman at Stanford

Rushin Shah - Facebook

NLP, Parsing, Information Extraction, Dialog and Question Answering

Maja J Mataric - USC -

Pararth Shah - Google

Building a Conversational Agent Overnight with Dialogue Self-Play
Dialogue research team. Use DL to model dialogs. DL is a loser.
Goal oriented dialog.
Coreference - pronouns
Entailment - Imply something

Alok Kothari - Apple

Siri’s Natural Language Understanding
From rule based to deep learning techniques.
2b queries a week.

NLU in Siri
1) Domain chooser
2) Action classifier (get verb)
3) Parsing

Start with a rule based when you have no data

Chandra Khatri - AI Scientist, Alexa

Amazon Alexa Prize - in Conversational AI

Nikhil Mane - Conversational Engineer at Autodesk

AVA - Autodesk Virtual Assistant (B2C)

Friday - 26 January

Enhancing Fashion Chatbots with Visual Signals -

Or Cohen

Sowmiya Chocka Narayanan - Lily -

Emotion Intelligence for Clothing Shopping

Conversational AI for College Success - AdmitHub

Andrew Magliozzi - Co-Founder

Embodied Conversational Agent - GeneYes

Kinuko Masaki - SmartEar - CEO

SmartEar Website

The Future of Voice Computing is in the Ear

Their AI assistant is similar to our ideas in terms of B2B.

Parsing voice is hard. All NLP research about text, parsing, trees helps very little.

Amazing product and a very good presentation.

AI first company - actually they’re trying to of-source hardware to someone else. They tried to create an in-ear device for the past year - and it’s hard, not interesting and they’re looking to partner with hardware manufacturer instead.

Anitha Kannan - AI for Healthcare - Curai

Mehdi Samadi - Solvvy

Conversational Agents and the Future of Intelligent Customer Experience - Elena Sokolova

Jane Nemcova VP Global Services for Machine Intelligence - Lionbridge

Sanjana Ramprasad - Mya Systems @sanjana_rampi

Mya Systems Website

Crowd sourcing dialogs. Create scenarios and make real people take roles.


Ivan Crewkov -
Growing the Generation of AI-Natives