Posts Tagged ‘semantic memory’

Conversational AI: Voice-Based Intelligent Agents

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:
Keynote talks at The AI Conference (2017), Stanford ASES Summit (2017), Stanford ASES Summit (2017), Global AI Conference (2016).
Keynote panel at Conversational Interaction Conference (2016).
Lightning TED-style talks at IIT Bay Area Conference (2017), Intersect (2017).

Join the Alexa Prize Journey and Test the Socialbots

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.



Announcing the Sponsored Teams for the 2016-2017 Alexa Prize

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.


The Alexa Prize: $2.5M to Advance Conversational AI

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?


Socio-Semantic Conversational Information Access

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).

Socio-Semantic Conversational Information Access

The main contributions of this thesis revolve around development of an integrated conversational recommendation system, combining data and information models with community network and interactions to leverage multi-modal information access. We have developed a real time conversational information access community agent that leverages community knowledge by pushing relevant recommendations to users of the community. The recommendations are delivered in the form of web resources, past conversation and people to connect to. The information agent (cobot, for community/ collaborative bot) monitors the community conversations, and is ‘aware’ of users’ preferences by implicitly capturing their short term and long term knowledge models from conversations. The agent leverages from health and medical domain knowledge to extract concepts, associations and relationships between concepts; formulates queries for semantic search and provides socio-semantic recommendations in the conversation after applying various relevance filters to the candidate results. The agent also takes into account users’ verbal intentions in conversations while making recommendation decision.

One of the goals of this thesis is to develop an innovative approach to delivering relevant information using a combination of social networking, information aggregation, semantic search and recommendation techniques. The idea is to facilitate timely and relevant social information access by mixing past community specific conversational knowledge and web information access to recommend and connect users with relevant information. Language and interaction creates usable memories, useful for making decisions about what actions to take and what information to retain.

Cobot leverages these interactions to maintain users’ episodic and long term semantic models. The agent analyzes these memory structures to match and recommend users in conversations by matching with the contextual information need. The social feedback on the recommendations is registered in the system for the algorithms to promote community preferred, contextually relevant resources. The nodes of the semantic memory are frequent concepts extracted from user’s interactions. The concepts are connected with associations that develop when concepts co-occur frequently. Over a period of time when the user participates in more interactions, new concepts are added to the semantic memory. Different conversational facets are matched with episodic memories and a spreading activation search on the semantic net is performed for generating the top candidate user recommendations for the conversation.

The tying themes in this thesis revolve around informational and social aspects of a unified information access architecture that integrates semantic extraction and indexing with user modeling and recommendations.

Read the dissertation:

Socio-Semantic Conversational Information Access

by Saurav Sahay

PhD dissertation, College of Computing, Georgia Institute of Technology, November 2011.

CBArch: A Case-Based Reasoning Framework for Conceptual Design of Commercial Buildings

The paper describes the first phase of development of a Case-Base Reasoning (CBR) system to support early conceptual design of buildings. As specific context of application, the research focuses on energy performance of commercial buildings, and the early identification of energy-related features that contribute to its outcomes. The hypothesis is that bringing knowledge from relevant precedents may facilitate this identification process, thus offering a significant contribution for early analysis and decision-making.

The paper introduces a proof-of-concept for such a system, proposing a novel integration of Case-Based Reasoning, Parametric Modeling (Building Information Modeling), and Ontology Classification. While CBR provides a framework to store and retrieve cases at an instance level, Parametric Modeling offers a framework for rule-based geometric adaptation and evaluation. The ontology is intended to provide a semantic representation, so that new design concepts can be created, classified and retained for further reuse. Potential advantages and limitations of this three-level integration approach are discussed along with recommendations for future development.

CBArch: A Case-Based Reasoning Framework for Conceptual Design of Commercial Buildings

by Andrés Cavieres, Urjit Bhatia, Preetam Joshi, Fei Zhao, Ashwin Ram

AAAI-11 Spring Symposium on Artificial Intelligence and Sustainable Design