Posts Tagged ‘semantic memory’

3 Jan

Podcast: How Amazon’s Alexa Learns

Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Talks. Tagged: , , , .

Much of the ballyhoo around intelligent home assistance devices is that they make life easier for us: from regulating our thermostats to freeing our hands while we check a favorite recipe for roast turkey, to playing that favorite jam to get us pumped up in the morning. And it turns out that because these devices are designed to learn from our patterns and habits, they become more helpful the longer we live with them.

In this podcast, Ashwin Ram, one of the minds behind Amazon Alexa, describes how the company is balancing privacy concerns with natural language recognition to design a more effective device.

KelloggInsight podcast with Jennifer Cutler, Northwestern University’s Kellogg School of Management

 

LISTEN TO THE PODCAST / READ THE TRANSCRIPT:

insight.kellogg.northwestern.edu/article/podcast-how-amazons-alexa-learns

31 Dec

TED: Imagine a world of AI

Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Talks. Tagged: , , , , , , , , , , , .

Ashwin Ram works on the AI behind Alexa, one of several new bots that might change the way your home and your life function within the next few years. Imagine a bot that turns on your lights, shops for you, even helps you make decisions. Learn more about a bot-enabled future that might have you saying (like Shah Rukh Khan does): “Alexa, I love you!”

 

TALK & TRANSCRIPT:
#TomorrowsWorld made easier with Artificial Intelligence. #TEDTalksIndiaNayiSoch

ted.com/talks/ashwin_ram_could_bots_make_your_life_better

BEHIND THE SCENES:
Innovator and entrepreneur, Ashwin Ram believes AI will changes our lives in future. #TomorrowsWorld #TEDTalksIndiaNayiSoch

youtube.com/watch?v=kDvIsRuaq5k

FULL #TOMORROWSWORLD EPISODE:
Can you imagine what #TomorrowsWorld will be like? Shah Rukh Khan introduces.

tedtalksindianayisoch.hotstar.com/TED/episode-4.php

ALL TED TALKS INDIA NAYI SOCH:
#TEDTalksIndiaNayiSoch is a groundbreaking TV series showcasing new thinking from some of the brightest brains in India and beyond and hosted by “The King of Bollywood,” Shah Rukh Khan.

ted.com/series/ted_talks_india_nayi_soch

28 Nov

Conversational AI: The Science behind the Alexa Prize

Posted by cognitivecomputing in Agents, Language, Learning, Talks. Tagged: , , , , , , , , , , , , .

Conversational agents are exploding in popularity. However, much work remains in the area of social conversation as well as free-form conversation over a broad range of domains and topics. To advance the state of the art in conversational AI, Amazon launched the Alexa Prize, a 2.5-million-dollar university competition where sixteen selected university teams were challenged to build conversational agents, known as “socialbots”, to converse coherently and engagingly with humans on popular topics such as Sports, Politics, Entertainment, Fashion and Technology for 20 minutes.

The Alexa Prize offered the academic community a unique opportunity to perform research with a live system used by millions of users. The competition provided university teams with real user conversational data at scale, along with the user-provided ratings and feedback augmented with annotations by the Alexa team. This enabled teams to effectively iterate and make improvements throughout the competition while being evaluated in real-time through live user interactions.

To build their socialbots, university teams combined state-of-the-art techniques with novel strategies in the areas of Natural Language Understanding, Context Modeling, Dialog Management, Response Generation, and Knowledge Acquisition. To support the teams’ efforts, the Alexa Prize team made significant scientific and engineering investments to build and improve Conversational Speech Recognition, Topic Tracking, Dialog Evaluation, Voice User Experience, and tools for traffic management and scalability.

This paper outlines the advances created by the university teams as well as the Alexa Prize team to achieve the common goal of solving the problem of Conversational AI.

Conversational AI: The Science behind the Alexa Prize

by Ashwin Ram, Rohit Prasad, Chandra Khatri, Anu Venkatesh, Raefer Gabriel, Qing Liu, Jeff Nunn, Behnam Hedayatnia, Ming Cheng, Ashish Nagar, Eric King, Kate Bland, Amanda Wartick, Yi Pan, Han Song, Sk Jayadevan, Gene Hwang, Art Pettigrue

Proceedings of the 2017 Alexa Prize
Invited talk at NIPS-2017 Workshop on Conversational AI
Invited talk at re:Invent 2017 (with Spyros Matsoukas)

READ THE PAPER:

arxiv.org/abs/1801.03604

WATCH THE TALK:

youtu.be/pn5QJQZjGpM

			

		


	
		

			

				13
				Oct
			

			
Conversational News Experiences

			

			Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Talks.			Tagged: , , , .			

			

				
News consumption is a passive experience—reading print or online newspapers, listening to radio shows and podcasts, watching television broadcasts. News producers create, curate, and organize  content which consumers absorb passively. With the advent of interactive conversational technologies ranging from chatbots to voice-based conversational assistants such as Amazon Alexa, there is an opportunity to engage consumers in more interactive experiences around news.


At the Computation+Journalism symposium held at Northwestern University this year, Emily Withrow, editor at Quartz Bot Studio and assistant professor at Northwestern’s Medill School of Journalism and I had a fireside chat to share recent technological developments in this area and explore what kinds of conversational news experiences these technologies might enable.


Panel at the 2017 Computation+Journalism Symposium, Northwestern University, Evanston, IL. #cj2017 

			

		


	
		

			

				29
				Aug
			

			
Announcing the 2017 Alexa Prize Finalists

			

			Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Web / Web 2.0.			Tagged: , , , , , , , , , , .			

			

				
We’ve hit another milestone in the Alexa Prize, a $2.5 million university competition to advance conversational AI. University teams from around the world have been hard at work to create a socialbot, an AI capable of conversing coherently and engagingly with humans on popular topics and news events for 20 minutes.


I am now excited to announce the university teams that will be competing in the finals! After hundreds of thousands of conversations, the two socialbots with the highest average customer ratings during the semifinal period are Alquist from the Czech Technical University in Prague and Sounding Board from the University of Washington in Seattle. The wildcard team is What’s Up Bot from Heriot-Watt University in Edinburgh, Scotland.


READ MORE:


developer.amazon.com/blogs/alexa/post/783df492-4770-4b11-81ac-59e009669d56/announcing-the-2017-alexa-prize-finalists


 

			

		


	
		

			

				1
				Jun
			

			
Conversational AI: Voice-Based Intelligent Agents

			

			Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Talks, Web / Web 2.0.			Tagged: , , , , , , , , , .			

			

				
As we moved from the age of the keyboard, to the age of touch, and now to the age of voice, natural conversation in everyday language continues to be one of the ultimate challenges for AI. This is a difficult scientific problem involving knowledge acquisition, natural language understanding, natural language generation, context modeling, commonsense reasoning and dialog planning, as well as a complex product design problem involving user experience and conversational engagement.


I will talk about why Conversational AI is hard, how conversational agents like Amazon Alexa understand and respond to voice interactions, how you can leverage these technologies for your own applications, and the challenges that still remain.


Variants of this talk presented (click links for video):


 


Keynote talks at The AI Conference (2017), O’Reilly AI Conference (2017), The AI Summit (2017), Stanford ASES Summit (2017), MLconf AI Conference (2017), Global AI Conference (2016).


 


Distinguished lectures at Georgia Tech/GVU (2017), Northwestern University (2017).


 


Keynote panel at Conversational Interaction Conference (2016).




 


Lightning TED-style talks at IIT Bay Area Conference (2017), Intersect (2017).


 



			

		


	
		

			

				18
				May
			

			
Join the Alexa Prize Journey and Test the Socialbots

			

			Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Web / Web 2.0.			Tagged: , , , , , , , , , , .			

			

				
On September 29, 2016, Amazon announced the Alexa Prize, a $2.5 million university competition to advance conversational AI through voice. In April, university teams from around the world assembled at the appropriately named Day 1 building in Seattle for the Alexa Prize Summit. The event was a base camp for teams to share learnings and make preparations for the most challenging leg of their journey: to build and scale an AI capable of conversing coherently and engagingly with humans for 20 minutes.


As they build their “socialbots,” they will encounter esoteric problems like context modeling and dialog planning as well as exoteric problems like user experience and conversational engagement. And they will need all the help they can get.


We invite you to join the students on their journey and help them along the way. You can interact with their socialbots simply by saying, “Alexa, let’s chat” on any device with Alexa.


READ MORE:

developer.amazon.com/blogs/alexa/post/e4cc64d1-f334-4d2d-8609-5627939f9bf7/join-the-alexa-prize-journey-and-test-the-socialbots


 

			

		


	
		

			

				14
				Nov
			

			
Announcing the Sponsored Teams for the 2016-2017 Alexa Prize

			

			Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Web / Web 2.0.			Tagged: , , , , , , , , , , , .			

			

				
On September 29, 2016, Amazon announced the Alexa Prize, a $2.5 million university competition to advance conversational AI through voice. We received applications from leading universities across 22 countries. Each application was carefully reviewed by senior Amazon personnel against a rigorous set of criteria covering scientific contribution, technical merit, novelty, and ability to execute. Teams of scientists, engineers, user experience designers, and product managers read, evaluated, discussed, argued, and finally selected the ten teams who would be invited to participate in the competition. Wait, make that twelve; we received so many good applications from graduate and undergraduate students that we decided to sponsor two additional teams.


Today, we’re excited to announce the 12 teams selected to compete with an Amazon sponsorship.


READ MORE:


developer.amazon.com/blogs/post/Tx1UXVV4VJTPYTL/announcing-the-sponsored-teams-for-the-2016-2017-alexa-prize

			

		


	
		

			

				29
				Sep
			

			
The Alexa Prize: $2.5M to Advance Conversational AI

			

			Posted by cognitivecomputing in Agents, Language, Learning, Opinion, Web / Web 2.0.			Tagged: , , , , , , , , , , , .			

			

				
Artificial intelligence (AI) is becoming ubiquitous. With advances in technology, algorithms, and sheer compute power, it is now becoming practical to utilize AI techniques in many everyday applications including transportation, healthcare, gaming, productivity, and media. Yet one seemingly intuitive task for humans still eludes computers: natural conversation. Simple and natural for humans, voice communication in everyday language continues to be one of the ultimate challenges for AI.


Today, we are pleased to announce the Alexa Prize, a $2.5 million university competition to advance conversational AI through voice. Teams of university students around the world are invited to participate in the Alexa Prize (see contest rules for details). The challenge is to create a socialbot, an Alexa skill that converses coherently and engagingly with humans on popular topics for 20 minutes. We challenge teams to invent an Alexa socialbot smart enough to engage in a fun, high quality conversation on popular topics for 20 minutes.


Are you up to the challenge?


READ MORE:


developer.amazon.com/public/community/post/Tx221UQAWNUXON3/Are-you-up-to-the-Challenge-Announcing-the-Alexa-Prize-2-5-Million-to-Advance-Co

			

		


	
		

			

				15
				Apr
			

			
Socio-Semantic Conversational Information Access

			

			Posted by cognitivecomputing in Health & Wellness, Language, Web / Web 2.0.			Tagged: , , , , , .			

			

				
We develop an innovative approach to delivering relevant information using a combination of socio-semantic search and filtering approaches. The goal is to facilitate timely and relevant information access through the medium of conversations by mixing past community specific conversational knowledge and web information access to recommend and connect users and information together. Conversational Information Access is a socio-semantic search and recommendation activity with the goal to interactively engage people in conversations by receiving agent supported recommendations. It is useful because people engage in online social discussions unlike solitary search; the agent brings in relevant information as well as identifies relevant users; participants provide feedback during the conversation that the agent uses to improve its recommendations.


Socio-Semantic Conversational Information Access


by Saurav Sahay, Ashwin Ram


WWW-2012 Workshop on Community Question Answering on the Web (CQA-12).

			

		


	
		

			
« Older Entries