Karen Ward

Coordinating turn-taking with gaze

Explores the role of gaze in coordinating turn-taking in mixed-initiative conversation, and specifically how gaze indicators might be usefully modeled in computational dialogue systems. We analyzed about 20 minutes of videotape of eight dialogues by four pairs of subjects performing a simple face-to-face cooperative laboratory task. We extend previous studies by explicating gaze patterns in face-to-face conversations, formalizing the most frequent pattern as a computational model of turn-taking and testing the model through an agent-based simulation. Prior conversation simulations of conversational control acts relied on abstract speech-act representations of control. This study advances the computational account of dialogue through simulation of direct physical expression of gaze to coordinate conversational turns.

Why don't people read the manual?

Few users of computer applications seek help from the documentation. This paper reports the results of an empirical study of why this is so and examines how, in real work, users solve their usability problems. Based on in-depth interviews with 25 subjects representing a varied cross-section of users, we find that users do avoid using both paper and online help systems. Few users have paper manuals for the most heavily used applications, but none complained about their lack. Online help is more likely to be consulted than paper manuals, but users are equally likely to report that they solve their problem by asking a colleague or experimenting on their own. Users cite difficulties in navigating the help systems, particularly difficulties in finding useful search terms, and disappointment in the level of explanation found.

Hands-free documentation

In this paper, we introduce an analysis of the requirements and design choices for hands-free documentation. Hands-busy tasks such as cooking or car repair may require substantial interruption of the task: moving the pan off the burner and wiping hands, or crawling out from underneath the car. We review the need for hands-free documentation and explore the role of task in the use of documentation. Our central analysis examines the roles and characteristics of input and output modalities of hands-free documentation. In particular, we review the use of speech as an input modality, and then visual means and speech as possible output modalities. Finally, we discuss the implications of our analysis for the design of hands-free documentation and suggest future work. The design implications include issues of navigating through the documentation, determining the users task and task-step, establishing mutual understanding of the state of the task, and determining when to start conveying information to the user.

Integrating multiple cues for spoken language understanding

As spoken language interfaces for real-world systems become a practical possibility, it has become apparent that such interfaces will need to draw on a variety of cues from diverse sources to achieve a robustness and naturalness approaching that of human performance [1]. However, our knowledge of how these cues behave in the aggregate is still tantalizingly sketchy. We lack a strong theoretical basis for predicting which cues will prove useful in practice and for specifying how these cues should be combined to signal or cancel out potential interpretations of the communicative signal. In the research program summarized here, we propose to develop and test an initial theory of cue integration for spoken language interfaces. By establishing a principled basis for integrating knowledge sources for such interfaces, we believe that we can develop systems that perform better from a computer-human interaction standpoint.

An interaction initiative model for documentation

In this paper we propose a model of creation and use of documentation based on the concept of mixed-initiative interaction. In our model, successful single-initiative interaction is characterized by grounding of contributions, and successful mixed-initiative interaction is characterized by both grounding and agreement. Just as in spoken conversation, achievement of actual agreement depends on the intentions of both parties; agreement is achieved when the reader follows the documentations instructions. In fact, readers are not obligated to-and often do not-act according to the authors intentions. By making these dynamics explicit, the model can aid authors in developing effective documentation. The paper describes the model and its antecedents, explains the application of the model to documentation, discusses implications such as effects of printed versus electronic forms of documentation, and outlines future work that includes empirical testing of the model.