| Weighted abduction for plan ascription | | BIBAK | Full-Text | 1-25 | |
| Douglas E. Appelt; Martha E. Pollack | |||
| We describe an approach to abductive reasoning called weighted abduction,
which uses inference weights to compare competing explanations for observed
behavior. We present an algorithm for computing a weighted-abductive
explanation, and sketch a model-theoretic semantics for weighted abduction. We
argue that this approach is well suited to problems of reasoning about mental
state. In particular, we show how the model of plan ascription developed by
Konolige and Pollack can be recast in the framework of weighted abduction, and
we discuss the potential advantages and disadvantages of this encoding. Keywords: Plan recognition; Plan evaluation; Mental-state ascription; Abduction;
Evaluation metrics | |||
| A meta-rule approach to flexible plan recognition in dialogue | | BIBAK | Full-Text | 27-53 | |
| Rhonda Eller; Sandra Carberry | |||
| Although a number of researchers have demonstrated that reasoning on a model
of the user's plans and goals is helpful in language understanding and response
generation, current models of plan inference cannot handle naturally occurring
dialogue. This paper argues that model building from less than ideal dialogues
has a great deal in common with processing ill-formed input. It defines
well-formedness constraints for information-seeking dialogues and contends that
strategies for interpreting ill-formed input can be applied to the problem of
modeling the user's plan during an ill-formed dialogue. It presents a meta-rule
approach for hypothesizing the cause of dialogue ill-formedness, and describes
meta-rules for relaxing the plan inference process and enabling the
consideration of alternative hypotheses. The advantages of this approach are
that it provides a unified framework for handling both well-formed and
ill-formed dialogue, avoids unnatural interpretations when the dialogue is
proceeding smoothly, and facilitates a nonmonotonic plan recognition system. Keywords: Plan recognition; Dialogue; Ill-formedness | |||
| Controlling inference in plan recognition | | BIBAK | Full-Text | 55-82 | |
| James Mayfield | |||
| An algorithm based on an assessment of the completeness of an explanation
can be used to control inference in a plan recognition system: If the
explanation is complete, inference is stopped. If the explanation is
incomplete, inference is continued. If it cannot be determined whether the
explanation is complete, then the system weighs the strength of its interest in
continuing the analysis against the estimated cost of doing so. This algorithm
places existing heuristic approaches to the control of inference in plan
recognition into a unified framework. The algorithm rests on the principle that
the decision to continue processing should be based primarily on the
explanation chain itself, not on external factors. Only when an analysis of the
explanation chain proves inconclusive should outside factors weigh heavily in
the decision. Furthermore, a decision to discontinue chaining should never be
final; other components of the system should have the opportunity to request
that an explanation chain be extended. An implementation of the algorithm,
called PAGAN, demonstrates the usefulness of this approach. Keywords: plan recognition; abduction; control of inference; explanation; natural
language understanding; consultation systems | |||
| On the interaction between plan recognition and intelligent interfaces | | BIBAK | Full-Text | 83-115 | |
| Bradley A. Goodman; Diane J. Litman | |||
| Plan recognition is an active research area in automatic reasoning, as well
as a promising approach to engineering interfaces that can exploit models of
user's plans and goals. Much research in the field has focused on the
development of plan recognition algorithms to support particular user/system
interactions, such as found in naturally occurring dialogues. However, two
questions have typically remained unexamined: 1) exactly what kind of interface
tasks can knowledge of a user's plans be used to support across communication
modalities, and 2) how can such tasks in turn constrain development of plan
recognition algorithms? In this paper we present a concrete exploration of
these issues. In particular, we provide an assessment of plan recognition, with
respect to the use of plan recognition in enhancing user interfaces. We clarify
how use of a user model containing plans makes interfaces more intelligent and
interactive (by providing an intelligent assistant that supports such tasks as
advice generation, task completion, context-sensitive responses, error
detection and recovery). We then show how interface tasks in turn provide
constraints that must be satisfied in order for any plan recognizer to
construct and represent a plan in ways that efficiently support these tasks.
Finally, we survey how interfaces are fundamentally limited by current plan
recognition approaches, and use these limitations to identify and motivate
current research. Our research is developed in the context of CHECS, a
plan-based design interface. Keywords: plan recognition; intelligent interfaces; user models; multimodal
communication; computer-aided design | |||
| Student modeling to support multiple instructional approaches | | BIBAK | Full-Text | 117-154 | |
| Robert V. London | |||
| Intelligent computer-assisted instruction (ICAI) systems have continually
sought increased flexibility to respond appropriately to the multi-faceted
interests of students. Research on the Image student modeler of the Guidon2
ICAI system has developed a multiple-anticipation approach to plan generation
and interpretation that directly meets a wide range of communication goals:
providing information support, encouraging exploration with interesting
elaborations, recognizing strategic mistakes in actions and plans, evaluating
success in domain tasks, diagnosing misconceptions, and recommending
improvements for mistakes.
In order to meet pragmatic system constraints, Image must provide its full range of advice simultaneously, continually, and quickly. It drops many of the simplifying assumptions typically used by plan recognition user modelers, including assumptions of closed-world knowledge and of the user's correctness, cooperation, and unified goal. To maintain efficiency for dynamic plan recognition, Image relies instead on two assumptions of cognitive economy, contextual relevance and conceptual easiness, which are operational forms of Grice's maxims of relation and quantity. Its multiple-anticipation approach to plan management provides all of the requisite information together and allows incremental updating and relaxation methods of interpretation, even when students are shifting focus frequently. Keywords: Student modeling; user modeling; plan recognition; ICAI; instruction | |||
| Intention structure and extended responses in a portable natural language interface | | BIBAK | Full-Text | 155-179 | |
| Judith Schaffer Sider; John D. Burger | |||
| This paper describes discourse processing in King Kong, a portable natural
language interface. King Kong enables users to pose questions and issue
commands to a back end system. The notion of a discourse is central to King
Kong, and underlies much of the intelligent assistance that Kong provides to
its users. Kong's approach to modeling discourse is based on the work of Grosz
and Sidner (1986). We extend Grosz and Sidner's framework in several ways,
principally to allow multiple independent discourse contexts to remain active
at the same time. This paper also describes King Kong's method of intention
recognition, which is similar to that described in Kautz and Allen (1986) and
Carberry (1988). We demonstrate that a relatively simple intention recognition
component can be exploited by many other discourse-related mechanisms, for
example to disambiguate input and resolve anaphora. In particular, this paper
describes in detail the mechanism in King Kong that uses information from the
discourse model to form a range of cooperative extended responses to queries in
an effort to aid the user in accomplishing her goals. Keywords: discourse modeling; user modeling; plan recognition; misconception
correction; presumption validation; cooperative responses | |||
| Generating tailored definitions using a multifaceted user model | | BIBA | Full-Text | 181-210 | |
| Margaret H. Sarner; Sandra Carberry | |||
| This paper presents a computational strategy for reasoning on a multifaceted user model to generate definitions tailored to the user's needs in a task-oriented dialogue. The strategy takes into account the current focus of attention in the user's partially constructed plan, the user's domain knowledge, and the user's receptivity to different kinds of information. It constructs a definition by weighting both the strategic predicates that might comprise a definition and the propositions that might be used to fill them. These weights are used to construct a definition that includes the information deemed most useful, using information of lesser importance as necessary to adhere to common rhetorical practices. This strategy reflects our hypothesis that beliefs about the appropriate content of a definition should guide selection of a rhetorical strategy, instead of the choice of a rhetorical strategy determining content. | |||
| Generating help for users of application software | | BIBAK | Full-Text | 211-248 | |
| C. Tattersall | |||
| Help for users of Information Processing Systems (IPSs) is typically based
upon the presentation of pre-stored texts written by the system designers for
predictable situations. Though advances in user interface technology have eased
the process of requesting advice, current on-line help facilities remain tied
to a back-end of canned answers, spooled onto users, screens to describe
queried facilities.
This paper argues that the combination of a user's knowledge of an application and the particular states which a system can assume require different answers for the large number of possible situations. Thus, a marriage of techniques from the fields of text generation and Intelligent Help Systems research is needed to construct responses dynamically. Furthermore, it is claimed that the help texts should attempt to address not only the immediate needs of the user, but to facilitate learning of the system by incorporating a variety of educational techniques to specialise answers in given contexts. A computational scheme for help text generation based on schema of rhetorical predicates is presented. Using knowledge of applications programs and their users, it is possible to provide a variety of answers in response to a number of questions. The approach uses object-oriented techniques to combine different information from a variety of sources in a flexible manner, yielding responses which are appropriate to the state of the IPS and to the user's level of knowledge. Modifications to the scheme which resulted from its evaluation in the EUROHELP project are described, together with ongoing collaborative work and further research developments. Keywords: Text generation; Intelligent help; knowledge representation | |||
| Modeling user action planning: A comprehension based approach | | BIBAK | Full-Text | 249-285 | |
| Stephanie M. Doane; Suzanne M. Mannes | |||
| We review our efforts to model user command production in an attempt to
characterize the knowledge users of computers have at various stages of
learning. We modeled computer users with a system called NETWORK (Mannes and
Kintsch, 1988; 1991) and modeled novice, intermediate, and expert UNIX command
production data collected by Doane et al. (1990b) with a system called UNICOM
(Doane et al., 1989a; 1991). We use the construction-integration theory of
comprehension proposed by Kintsch (1988) as a framework for our analyses. By
focusing on how instructions activate the knowledge rele/ant to the performance
of the specified task, we have successfully modeled major aspects of correct
user performance by incorporating in the model knowledge about individual
commands and knowledge that allows the correct combination of elementary
commands into complex, novel commands. Thus, experts can be modeled in both
NETWORK and in UNICOM. We further show that salient aspects of novice and
intermediate performance can be described by removing critical elements of
knowledge from the expert UNICOM model. Results suggest that our
comprehension-based approach has promise for understanding user interactions
and implications for system design are discussed. Keywords: levels of user expertise; human-computer interaction; novel plans; discourse
comprehension | |||
| Exploiting user feedback to compensate for the unreliability of user models | | BIBAK | Full-Text | 287-330 | |
| Johanna D. Moore; Cécile L. Paris | |||
| Natural Language is a powerful medium for interacting with users, and
sophisticated computer systems using natural language are becoming more
prevalent. Just as human speakers show an essential, inbuilt responsiveness to
their hearers, computer systems must "tailor" their utterances to users.
Recognizing this, researchers devised user models and strategies for exploiting
them in order to enable systems to produce the "best" answer for a particular
user.
Because these efforts were largely devoted to investigating how a user model could be exploited to produce better responses, systems employing them typically assumed that a detailed and correct model of the user was available a priori, and that the information needed to generate appropriate responses was included in that model. However, in practice, the completeness and accuracy of a user model cannot be guaranteed. Thus, unless systems can compensate for incorrect or incomplete user models, the impracticality of building user models will prevent much of the work on tailoring from being successfully applied in real systems. In this paper, we argue that one way for a system to compensate for an unreliable user model is to be able to react to feedback from users about the suitability of the texts it produces. We also discuss how such a capability can actually alleviate some of the burden now placed on user modeling. Finally, we present a text generation system that employs whatever information is available in its user model in an attempt to produce satisfactory texts, but is also capable of responding to the user's follow-up questions about the texts it produces. Keywords: question answering; natural language generation; adaptive systems; text
planning; explanation; expert systems; user modeling | |||
| Interactive user modeling: An integrative explicit-implicit approach | | BIBAK | Full-Text | 331-365 | |
| Eyal Shifroni; Benny Shanon | |||
| User modeling issues are examined in the context of a user-adapted guidance
system. The system provides users with instructions about natural tasks without
introducing a special time-consuming sub-dialog to learn the user's knowledge.
A model for providing such guidance is developed on the basis of a
phenomenological analysis of human guidance, and illustrated by a system that
gives directions in geographical domains. The main features of the user model
design include: (1) Both implicit and explicit acquisition methods are employed
in a flexible manner; (2) The guidance instructions and the user model are
generated incrementally and interchangeably; (3) User's responses and
no-responses are employed as a source of information for the user modeling. The
model and the resulting system's performance are examined in light of recent
development in the cognitive literature. Keywords: User-Model; Guidance Systems; Advisory Systems; Man-Machine Interaction;
Natural-Language Generation | |||
| Modeling the user knowledge by belief networks | | BIBAK | Full-Text | 367-388 | |
| Fiorella De Rosis; Sebastiano Pizzutilo | |||
| This paper describes the user modeling component of EPIAIM, a consultation
system for data analysis in epidemiology. The component is aimed at
representing knowledge of concepts in the domain, so that their explanations
can be adapted to user needs. The first part of the paper describes two studies
aimed at analysing user requirements. The first one is a questionnaire study
which examines the respondents' familiarity with concepts. The second one is an
analysis of concept descriptions in textbooks and from expert epidemiologists,
which examines how discourse strategies are tailored to the level of experience
of the expected audience. The second part of the paper describes how the
results of these studies have been used to design the user modeling component
of EPIAIM. This module works in a two-step approach. In the first step, a few
trigger questions allow the activation of a stereotype that includes a "body"
and an "inference component". The body is the representation of the body of
knowledge that a class of users is expected to know, along with the probability
that the knowledge is known. In the inference component, the learning process
of concepts is represented as a belief network. Hence, in the second step the
belief network is used to refine the initial default information in the
stereotype's body. This is done by asking a few questions on those concepts
where it is uncertain whether or not they are known to the user, and
propagating this new evidence to revise the whole situation. The system has
been implemented on a workstation under UNIX. An example of functioning is
presented, and advantages and limitations of the approach are discussed. Keywords: formal representation of user models; user stereotypes; levels of user
expertise; belief networks; discourse strategies; user tailored explanations | |||