Allen, James


SkeletonScore: Guiding a Semantic Parser to Better Results by Example

AAAI Conferences

The task of semantic parsing is to map natural-language sentences to logical forms representing the underlying meanings of those sentences. Typically, resolving semantic ambiguity is considered to be a side effect of semantic parsing. However a large number of errors in parsing can be attributed to incorrect sense disambiguation in the first place. This can arise from the selection of an incorrect semantic role or semantic type by the parser. This paper applies a knowledge-based algorithm to guide a semantic parser to simultaneously select better semantic types and roles. The algorithm takes into account semantic roles and ontology types to reduce restriction violations arising from incorrect semantic role or type choices, hence increasing the total accuracy of the semantic parser.


Cognitive Orthoses: Toward Human-Centered AI

AI Magazine

This introduction focuses on how human-centered computing (HCC) is changing the way that people think about information technology. The AI perspective views this HCC framework as embodying a systems view, in which human thought and action are linked and equally important in terms of analysis, design, and evaluation. This emerging technology provides a new research outlook for AI applications, with new research goals and agendas.


Learning New Relations from Concept Ontologies Derived from Definitions

AAAI Conferences

Systems that build general knowledge bases from concept definitions mostly focus on knowledge extraction techniques on a per-definition basis. But, definitions rely on subtext and other definitions to concisely encode a concept's meaning. We present a probabilistic inference process where we systematically augment knowledge extracted from several WordNet glosses with subtext and then infer likely states of the world. From those states we learn new semantic relations among properties, states, and events. We show that our system learns more relations than one without subtext and verify this knowledge using human evaluators.


Using the Crowd to Do Natural Language Programming

AAAI Conferences

Natural language programming has proven to be a very challenging task. We present a novel idea which suggests using crowdsourcing to do natural language programming. Our approach asks non-expert workers to provide input/output examples for a task defined in natural language form. We then use a Programming by Example system to induce the intended program from the input/output examples. Our early results are promising, encouraging further research in this area.


Acquiring Commonsense Knowledge for a Cognitive Agent

AAAI Conferences

A critical prerequisite for human-level cognitive systems is having a rich conceptual understanding of the world. We describe a system that learns conceptual knowledge by deep understanding of WordNet glosses. While WordNet is often criticized for having a too fine-grained approach to word senses, the set of glosses do generally capture useful knowledge about the world and encode a substantial knowledge base about everyday concepts. Unlike previous approaches that have built ontologies of atomic concepts from the provided WordNet hierarchies, we construct complex concepts compositionally using description logic and perform reasoning to derive the best classification of knowledge. We view this work as simultaneously accomplishing two goals: building a rich semantic lexicon useful for natural language processing, and building a knowledge base that encodes common-sense knowledge.


A Cognitive Model for Collaborative Agents

AAAI Conferences

We describe a cognitive model of a collaborative agent that can serve as the basis for automated systems that must collaborate with other agents, including humans, to solve problems. This model builds on standard approaches to cognitive architecture and intelligent agency, as well as formal models of speech acts, joint intention, and intention recognition. The model is nonetheless intended for practical use in the development of collaborative systems.



PIM: A Novel Architecture for Coordinating Behavior of Distributed Systems

AI Magazine

Process integrated mechanisms (PIM) offer a new approach to the problem of coordinating the activity of physically distributed systems or devices. Current approaches to coordination all have well-recognized strengths and weaknesses. We propose a novel architecture to add to the mix, called the Process Integrated Mechanism (PIM), which enjoys the advantages of having a single controlling authority while avoiding the structural difficulties that have traditionally led to its rejection in many complex settings. In many situations, PIMs improve on previous models with regard to coordination, security, ease of software development, robustness and communication overhead. In the PIM architecture, the components are conceived as parts of a single mechanism, even when they are physically separated and operate asynchronously. The PIM models offers promise as an effective infrastructure for handling tasks that require a high degree of time-sensitive coordination between the components, as well as a clean mechanism for coordinating the high-level goals of loosely coupled systems. PIM models enable coordination without the fragility and high communication overhead of centralized control, but also without the uncertainty associated with the system-level behavior of a MAS.The PIM model provides an ease of programming with advantages over both multi-agent sys-tems and centralized architectures. It has the robustness of a multi-agent system without the significant complexity and overhead required for inter-agent communication and negotiation. In contrast to centralized approaches, it does not require managing the large amounts of data that the coordinating process needs to compute a global view. In a PIM, the process moves to the data and may perform computations on the components where the data is locally available, sharing only the information needed for coordination of the other components. While there are many remaining research issues to be addressed, we believe that PIMs offer an important and novel tech-nique for the control of distributed systems.


CARDIAC: An Intelligent Conversational Assistant for Chronic Heart Failure Patient Heath Monitoring

AAAI Conferences

We describe CARDIAC, a prototype for an intelligent conversational assistant that provides health monitoring for chronic heart failure patients. CARDIAC supports user initiative through its ability to understand natural language and connect it to intention recognition. The natural language interface allows patients to interact with CARDIAC without special training. The system is designed to understand information that arises spontaneously in the course of the interview. If the patient gives more detail than necessary for answering a question, the system updates the user model accordingly. CARDIAC is a first step towards developing cost-effective, customizable, automated in-home conversational assistants that help patients manage their care and monitor their health using natural language.


Mixed-Initiative Systems for Collaborative Problem Solving

AI Magazine

Mixed-initiative systems are a popular approach to building intelligent systems that can collaborate naturally and effectively with people. But true collaborative behavior requires an agent to possess a number of capabilities, including reasoning, communication, planning, execution, and learning. We describe an integrated approach to the design and implementation of a collaborative problem-solving assistant based on a formal theory of joint activity and a declarative representation of tasks. This approach builds on prior work by us and by others on mixed-initiative dialogue and planning systems.