Push Singh

Open Mind Common Sense: Knowledge Acquisition from the General Public

Open Mind Common Sense is a knowledge acquisition system designed to acquire commonsense knowledge from the general public over the web. We describe and evaluate our first fielded system, which enabled the construction of a 450,000 assertion commonsense knowledge base. We then discuss how our second-generation system addresses weaknesses discovered in the first. The new system acquires facts, descriptions, and stories by allowing participants to construct and fill in natural language templates. It employs word-sense disambiguation and methods of clarifying entered knowledge, analogical inference to provide feedback, and allows participants to validate knowledge and in turn each other.

Commonsense Reasoning in and Over Natural Language

ConceptNet is a very large semantic network of commonsense knowledge suitable for making various kinds of practical inferences over text. ConceptNet captures a wide range of commonsense concepts and relations like those in Cyc, while its simple semantic network structure lends it an ease-of-use comparable to WordNet. To meet the dual challenge of having to encode complex higher-order concepts, and maintaining ease-of-use, we introduce a novel use of semi-structured natural language fragments as the knowledge representation of commonsense concepts. In this paper, we present a methodology for reasoning flexibly about these semi-structured natural language fragments. We also examine the tradeoffs associated with representing commonsense knowledge in formal logic versus in natural language. We conclude that the flexibility of natural language makes it a highly suitable representation for achieving practical inferences over text, such as context finding, inference chaining, and conceptual analogy.

Beating Common Sense into Interactive Applications

A long-standing dream of artificial intelligence has been to put commonsense knowledge into computers -- enabling machines to reason about everyday life. Some projects, such as Cyc, have begun to amass large collections of such knowledge. However, it is widely assumed that the use of common sense in interactive applications will remain impractical for years, until these collections can be considered sufficiently complete and commonsense reasoning sufficiently robust. Recently, at the Massachusetts Institute of Technologys Media Laboratory, we have had some success in applying commonsense knowledge in a number of intelligent interface agents, despite the admittedly spotty coverage and unreliable inference of todays commonsense knowledge systems. This article surveys several of these applications and reflects on interface design principles that enable successful use of commonsense knowledge.

Aria: an agent for annotating and retrieving images

The paper discusses Aria, an interface agent designed to assist users by preactively looking for opportunities for image annotation and retrieval. While it does not completely automate the image annotation and retrieval process, Aria dramatically reduces user interface overhead, which can lead to better annotated image libraries and fewer missed opportunities for image use.

Human dynamics: computation for organizations

The human dynamics group at the MIT Media Laboratory proposes that active pattern analysis of face-to-face interactions within the workplace can radically improve the functioning of the organization. There are several different types of information inherent in such conversations: interaction features, participants, context, and content. By aggregating this information, high-potential collaborations and expertise within the organization can be identified, and information efficiently distributed. Examples of using wearable machine perception to characterize face-to-face interactions and using the results to initiate productive connections are described, and privacy concerns are addressed.

Teaching Machines about Everyday Life

In order to build software that can deeply understand people and our problems, we require computational tools that give machines the capacity to learn and reason about everyday life. We describe three commonsense knowledge bases that take unconventional approaches to representing, acquiring, and reasoning with large quantities of commonsense knowledge. Each adopts a different approach — ConceptNet is a large-scale semantic network, LifeNet is a probabilistic graphical model, and StoryNet is a database of story-scripts. We describe the evolution, architecture and operation of these three systems, and conclude with a discussion of how we might combine them into an integrated commonsense reasoning system.

An architecture of diversity for commonsense reasoning

Although computers excel at certain bounded tasks that are difficult for humans, such as solving integrals, they have difficulty performing commonsense tasks that are easy for humans, such as understanding stories. In this Technical Forum contribution, we discuss commonsense reasoning and what makes it difficult for computers. We contend that commonsense reasoning is too hard a problem to solve using any single artificial intelligence technique. We propose a multilevel architecture consisting of diverse reasoning and representation techniques that collaborate and reflect in order to allow the best techniques to be used for the many situations that arise in commonsense reasoning. We present story understanding—specifically, understanding and answering questions about progressively harder children’s texts—as a task for evaluating and scaling up a commonsense reasoning system.

ComicKit: acquiring story scripts using common sense feedback

At the Media Lab we are developing a resource called StoryNet, a very-large database of story scripts that can be used for commonsense reasoning by computers. This paper introduces ComicKit, an interface for acquiring StoryNet scripts from casual internet users. The core element of the interface is its ability to dynamically make common-sense suggestions that guide user story construction. We describe the encouraging results of a preliminary user study, and discuss future directions for ComicKit.

Elaborating sensor data using temporal and spatial commonsense reasoning

Ubiquitous computing has established a vision of computation where computers are so deeply integrated into our lives that they become both invisible and everywhere. In order to have computers out of sight and out of mind, they will need a deeper understanding of human life. LifeNet (Singh and Williams, 2003) is a model that functions as a computational model of human life that attempts to anticipate and predict what humans do in the world from a first-person point of view. LifeNet utilizes a general knowledge storage (Singh, 2002) gathered from assertions about the world input by the web community at large. In this work, we extend this general knowledge with sensor data gathered in vivo. By adding these sensor-network data to LifeNet, we are enabling a bidirectional learning process: both bottom-up segregation of sensor data and top-down conceptual constraint propagation, thus correcting current metric assumptions in the LifeNet conceptual model by using sensor measurements. Also, in addition to having LifeNet learning general common sense metrics of physical time and space, it will also learn metrics to a specific lab space and chances for recognizing specific individual human activities, and thus be able to make both general and specific spatial/temporal inferences, such as predicting how many people are in a given room and what they might be doing. This paper discusses the following topics: (1) details of the LifeNet probabilistic human model, (2) a description of the plug sensor network used in this research, and (3) a description of an experimental design for evaluation of the LifeNet learning method

Reports on the 2005 AAAI Spring Symposium Series

The Association for the Advancement of Artificial Intelligence presented its 2005 Spring Symposium Series on Monday through Wednesday, March 21-23, 2005 at Stanford University in Stanford, California. The topics of the eight symposia in this symposium series were (1) AI Technologies for Homeland Security; (2) Challenges to Decision Support in a Changing World; (3) Developmental Robotics; (4) Dialogical Robots: Verbal Interaction with Embodied Agents and Situated Devices; (5) Knowledge Collection from Volunteer Contributors; (6) Metacognition in Computation; (7) Persistent Assistants: Living and Working with AI; and (8) Reasoning with Mental and External Diagrams: Computational Modeling and Spatial Assistance.