A steptorial ("step tutorial") is a new interaction strategy for learning complex topics. Conventional tutorials�such as Khan Academy-style…
We explore advanced machine learning and reflective user interfaces to scale the national Crisis Text Line. We are using state-of-the-art p…
A library of Python 2.7 code for facilitating commonsense reasoning with ConceptNet4. This makes high-level features of the ConceptNet4 cod…
Making optimal decisions can improve a wide array of situations. Humans often perform well on small, focused choices, but performance degra…
We are working on ways to detect sensitive themes in the online discussions between teenagers on social networks, and to match them to simi…
Time Out is an experimental user interface system for addressing cyberbullying on social networks. A Reflective User Interface (RUI) is a n…
Currently each app lives in its own little world, with its own interface. Apps are usually unable to communicate with each other and unable…
A major problem for natural language interfaces is their inability to handle text whose meaning depends in part on context. If a user asks…
Raconteur is a story-editing system for conversational storytelling that provides intelligent assistance in illustrating a story with photo…
It's well known that living in a foreign country dramatically improves the effectiveness of learning a second language over classroom study…
Analogy is a powerful comparison mechanism, commonly thought to be central to human problem solving. Analogies like "an atom is like the so…
What motivates people? What changes do people want in the world? We approach questions of this kind by mining goals and plans from text-bas…
Computers usually require us to be precise about what we want them to do and how we want them to do it, but humans find it hard to be so fo…
The choices we make about diet, environment, medications, or alternative therapies constitute a massive collection of "everyday experiments…
Common Consensus is a fun, self-sustaining web-based game that both collects and validates commonsense knowledge about everyday goals. Goal…
This project aims to collect and reason over common-sense knowledge in languages other than English. We have collected large bodies of comm…
Today, people can tell stories by composing, manipulating, and sequencing individual media artifacts using digital technologies. However, t…
A ConceptNet in English is already established and working well. We are now attempting to expand it to other languages and cultures. This p…
Consumer electronics devices are becoming more complicated, intimidating users. These devices do not know anything about everyday life or h…
We want to build programming systems that can converse with their users to build computer programs. Such systems will enable users without …
A long-standing dream of artificial intelligence has been to put common-sense knowledge into computers�enabling machines to reason about ev…
One of the biggest challenges for the digital economy is what to do when things go wrong. Orders get misplaced, numbers mistyped, requests …
This project explores how modern graphical interface techniques and explicit support for the user's problem-solving activities can make mor…
How would you browse a VERY large display space, such as a street map of the entire world? The traditional solution is zoom and pan, but th…
The biggest problem facing artificial intelligence today is how to teach computers enough about the everyday world so that they can reason …
Because common-sense knowledge differs culturally, misunderstandings frequently occur. Because differences can be subtle, there has been li…
Recognition-based technology has made substantial advances in the past few years because of enhanced algorithms and faster processing speed…
This project aims to develop an intelligent personal-finance advisory agent that bridges the gap between the novice user and the expert mod…
The Open Mind Common Sense project has collected hundreds of thousands of statements of common-sense knowledge from volunteers on the Inter…
Common sense enables us to build innovative recommendation systems that are more interactive and user-friendly than traditional collaborati…
Technical documentation for hardware and software is expensive to produce, and often inaccurate and inadequate. We are exploring a new appr…
Current experiments in agent software rely mostly on domain-specific applications that either have been programmed from scratch, or explici…
Effective image annotation and retrieval is bound up with image use. In this project, annotation, retrieval, and use are integrated, facili…
Story understanding is a notoriously difficult problem in AI. Broad-spectrum, common-sense knowledge about the world is a good resource, bu…
We are building a new kind of agent that acts as a user's assistant in browsing the World Wide Web. Many current Web tools perform searches…
ToDoGo is a system for managing to-do lists on mobile devices. ToDoGo understands how to-do list entries relate to a user's everyday life a…
Agent software can perform tasks automatically on behalf of a user, but how does the agent come to learn what the user wants? Sometimes the…
When computers automatically generate video game environments, the result is often as simplistic as a randomly generated maze. Using the Op…
Increasingly, software agents will need to detect certain kinds of semantically significant information that appear amidst a larger body of…
Electronic commerce on the Web is thriving, but consumers still have trouble finding products to meet their needs and desires. We introduce…
We are developing a new interface for text chat, to assist conversational partners who don't necessarily speak each others' languages perfe…
MakeBelieve is a story-generation agent that uses common-sense knowledge to interactively compose short fictional texts with a user. A user…
The advent of PDAs, digital cameras, audio recorders, and wearables enables the collection of useful information in a variety of media. But…
A novice search-engine user may find searching the Web for information difficult and frustrating because he may naturally express search go…
EventNet is the common-sense approach to goal planning. By extracting cause-effect and action-goal links from Open Mind Common Sense, we bu…
Most e-commerce sites today are little more than electronic catalogs of product offerings. Consumer input is limited to requirements questi…
Most story representation and annotation focuses on low-level annotations such as parts of speech. We are trying to annotate English proble…
Users don�t want to browse the Web on mobile devices, they want to complete actions. Adeo is an application that streamlines accessing the …
ARIA (Annotation and Retrieval Integration Agent) is a software agent that acts as an assistant to a user writing email or Web pages. As th…
Globuddy is a common-sense-based application that helps English-speakers to communicate in a foreign language. In addition to translating …
Tim Berners-Lee envisions information on the Web being given well-defined meaning, creating the Semantic Web, which would then enable user-…
Current voice-recognition software relies on statistical techniques to determine which words a user has said. This project attempts to leve…
Users have high-level goals when they browse the Web or perform searches. However, the two primary user interfaces positioned between user…
Programming is the art of constructing a story about objects and what they do in various situations, expressed in programming languages whi…
Cell-phone contact lists represent a very large peer-to-peer network. We are creating a cell-phone-based application that allows users to p…
People cannot type as fast as they think, especially when faced with the constraints of mobile devices. The focus of this project is develo…
Our translation assistant applies common-sense logic to the problem of translating speech in real time from one language to another. Using …
Segu� is a browsing agent that can discern the user's changes of interest by examining browsing history. The agent represents the pages in …
We are working on learning agents that can automate semi-repetitive graphical procedures by watching a user perform the procedures on concr…
When browsing the Web, what quality information does the user have about the information underlying the links? The only hint behind links i…
What would it mean to browse collaboratively? In business meetings or family situations, several people may be attending a browsing session…
This project helps a community tell its collective story through collaborative hypertext. Members of the community contribute many short an…