Erik T. Mueller

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.

Watson: beyond jeopardy!

This paper presents a vision for applying the Watson technology to health care and describes the steps needed to adapt and improve performance in a new domain. Specifically, it elaborates upon a vision for an evidence-based clinical decision support system, based on the DeepQA technology, that affords exploration of a broad range of hypotheses and their associated evidence, as well as uncovers missing information that can be used in mixed-initiative dialog. It describes the research challenges, the adaptation approach, and finally reports results on the first steps we have taken toward this goal.

Event Calculus Reasoning Through Satisfiability

We present an implemented method for encoding reasoning problems of a discrete version of the classical logic event calculus in propositional conjunctive normal form, enabling the problems to be solved efficiently by off-the-shelf complete satisfiability (SAT) solvers. We build on the previous encoding method of Shanahan and Witkowski, extending it to support causal constraints, concurrent events, determining fluents, effect axioms with conditions, events triggered by conditions, gradual change, incompletely specified initial situations, state constraints, and release from the commonsense law of inertia. We present an alternative classical logic axiomatization of the event calculus and prove its equivalence to a standard axiomatization for integer time. We describe our encoding method based on the alternative axiomatization and prove its correctness. We evaluate the method on 14 benchmark reasoning problems for the event calculus and compare performance with the causal calculator on eight problems in the zoo world domain.

Understanding script-based stories using commonsense reasoning

This paper investigates the use of commonsense reasoning to understand texts involving stereotypical activities or scripts. We present a system that understands news stories involving four terrorism scripts. The system (1) builds a commonsense reasoning problem given an information extraction template representing a terrorist incident, and (2) uses commonsense reasoning and a commonsense knowledge base to build a model of the terrorist incident. The reasoning problem, commonsense knowledge base, and model are expressed in the classical logic event calculus. The system was developed using the MUC3 and MUC4 development data set. We present the results of running the system on the MUC3 and MUC4 test data sets, using manually generated answer key templates and templates generated automatically by two MUC4 information extraction systems. We present a detailed analysis of the models produced by the system given automatically generated templates. We present methods for answering questions based on the models produced by our system. We assess the portability of the system by extending it to handle 10 scripts frequent in Project Gutenberg American literature texts.

Story understanding through multi-representation model construction

We present an implemented model of story understanding and apply it to the understanding of a childrens story. We argue that understanding a story consists of building multi-representation models of the story and that story models are efficiently constructed using a satisfiability solver. We present a computer program that contains multiple representations of commonsense knowledge, takes a narrative as input, transforms the narrative and representations of commonsense knowledge into a satisfiability problem, runs a satisfiability solver, and produces models of the story as output. The narrative, models, and representations are expressed in the language of Shanahans event calculus.

Modelling Space and Time in Narratives about Restaurants

This study investigated the automatic modelling of space and time in narratives involving dining in a restaurant. We built a program that (1) uses information extraction techniques to convert narrative texts into templates containing key information about the dining episodes discussed in the narratives, (2) constructs commonsense reasoning problems from the templates, (3) uses commonsense reasoning and a commonsense knowledge base to build models of the dining episodes, and (4) generates and answers questions by consulting the models. We describe the program and present the results of running it on a corpus of web texts and American literature.

A calendar with common sense

Digital devices today have little understanding of their real-world context, and as a result they often make stupid mistakes. To improve this situation we are developing a database of world knowledge called ThoughtTreasure at the same time that we develop intelligent applications. In this paper we present one such application, SensiCal, a calendar with a degree of common sense. We discuss the pieces of common sense important in calendar management and present methods for extracting relevant information from calendar items.

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.

Automating commonsense reasoning using the event calculus

Commonsense reasoning is the human ability to make inferences about properties and events in the everyday world. The automation of commonsense reasoning, long a goal of the field of artificial intelligence [3] and an area of active research in the last decade [8], is attaining a level of maturity. Automating commonsense reasoning allows us to build applications that are more user-friendly and more understanding of the world [2]. Several major computational approaches to commonsense reasoning have been explored. Analogical processing implements the notion that people reason about novel situations by analogy to familiar ones. Probability theory allows us to reason given uncertain knowledge of the state of the world and how the world works. Qualitative reasoning focuses on reasoning about physical systems. Methods based on natural language make use of large textual corpora of commonsense knowledge. Society of mind approaches stress the use of multiple interacting methods and representations. One approach that has achieved a high degree of success because of its steadfast focus on hard benchmark problems of commonsense reasoning, is logic. One logic-based formalism that stands out as both comprehensive and easy to use is the event calculus [4, 9].

WatsonPaths: Scenario-based Question Answering and Inference over Unstructured Information

We present WatsonPaths, a novel system that can answer scenario-based questions. These include medical questions that present a patient summary and ask for the most likely diagnosis or most appropriate treatment. WatsonPaths builds on the IBM Watson question answering system. WatsonPaths breaks down the input scenario into individual pieces of information, asks relevant subquestions of Watson to conclude new information, and represents these results in a graphical model. Probabilistic inference is performed over the graph to conclude the answer. On a set of medical test preparation questions, WatsonPaths shows a significant improvement in accuracy over multiple baselines.