Adelheit Stein

Cases, scripts, and information-seeking strategies: On the design of interactive information retrieval systems

Abstract The support of effective interaction of the user with the other components of the system is a central problem for information retrieval. In this paper, we present a theory of such interactions taking place within a space of information-seeking strategies, and discuss how such a concept can be used to design for effective interaction. In particular, we propose a model of information retrieval system design based on the ideas of: a multidimensional space of information-seeking strategies; dialogue structures for information seeking; cases of specific information-seeking dialogues; anti, scripts as distinguished prototypical cases. We demonstrate the use of this model by discussing in some detail the MERIT system, a prototype information retrieval system, that incorporates these design principles.

Modeling the illocutionary aspects of information-seeking dialogues

Abstract A dialogue model is presented that incorporates the illocutionary aspects of information-seeking dialogues. Directive, commissive, and assertive types of dialogue acts (e.g., asking, offering, rejecting, answering, and evaluating) are represented by a complex transition network. The model determines all legitimate types and sequences of dialogue acts and regulates the role assignments (e.g., when the information seeker and the information provider temporarily exchange their roles). Finally, an approach to integrating the illocutionary layer with other layers—which deal with thematical and rhetorical coherence—is outlined. Such an integrated model can serve as a basis for the design of human-computer dialogue systems.

Structuring collaborative information-seeking dialogues

Conversational approaches to human—computer collaboration have so far mostly been employed for the design of natural language interfaces. It is claimed, however, that the conversational interaction model described in the paper can also feasibly be applied to graphical and multimodal interactions. The model comprises two interrelated parts: first, the description of local discourse structures and functional interrelations between dialogue acts to capture (local) conversational tactics, and second, the description of global structures by so-called dialogue scripts which are related to (global) information-seeking strategies. The application of the model in a multi-media information retrieval system is described in the conclusions to the paper.

User-Tailored Planning of Mixed Initiative Information-Seeking Dialogues

Intelligent dialogue systems usually concentrate on user support at the level of the domain of discourse, following a plan-based approach. Whereas this is appropriate for collaborative planning tasks, the situation in interactive information retrieval systems is quite different: there is no inherent plan-goal hierarchy, and users are known to often opportunistically change their goals and strategies during and through interaction. We need to allow for mixed-initiative retrieval dialogues, where the system evaluates the users individual dialogue behavior and performs situation-dependent interpretation of user goals, to determine when to take the initiative and to change the control of the dialogue, e.g., to propose (new) problem-solving strategies to the user. In this article, we present the dialogue planning component of a concept- oriented, logic-based retrieval system (MIRACLE). Users are guided through the global stages of the retrieval interaction but may depart, at any time, from this guidance and change the direction of the dialogue. When users submit ambiguous queries or enter unexpected dialogue control acts, abductive reasoning is used to generate interpretations of these user inputs in light of the dialogue history and other internal knowledge sources. Based on these interpretations, the system initiates a short dialogue offering the user suitable options and strategies for proceeding with the retrieval dialogue. Depending on the users choice and constraints resulting from the history, the system adapts its strategy accordingly.

COLLATE – A collaboratory supporting research on historic European films

In the COLLATE project, we aim to design and implement a Web-based collaboratory for archives, scientists, and end users working with digitized cultural material. Our example domain is the historic film documentation comprising digitized material about European films of the early 20th century. Designed as a content- and context-based knowledge working environment for distributed user groups, the COLLATE system supports both individual work and collaboration of domain experts who are analyzing, evaluating, indexing, and annotating material in the data repository. The system provides appropriate task-based interfaces for indexing and annotating. As a multifunctional means of in-depth analysis, annotations can be made individually but also collaboratively, for example in the form of annotation of annotations. Combining results from manual and automatic indexing procedures, elaborate content- and context-based information retrieval mechanisms can be applied.

Customizable Retrieval Functions Based on User Tasks in the Cultural Heritage Domain

The cultural heritage domain dealing with digital surrogates of rare and fragile historic artifacts is one of the most promising areas for establishing collaboratories, i.e. shared virtual working environments for groups of users. However, in order to be considered a useful tool, such a system must reflect and support the specific tasks which are typical for the domain. The system design presented here takes into account a variety of activities, e.g., source analysis, which are supported by a task-specific selection of appropriate retrieval functions, e.g., access to OCR results and annotations. The tasks are explicitly modeled, thus the corresponding user interfaces can be automatically generated.

Generating cooperative system responses in information retrieval dialogues

This paper describes the Corinna system which integrates a theoretical approach to dialogue modeling with text generation techniques to conduct cooperative dialogues in natural language. It is shown how the dialogue model COR can be augmented by adding discourse relations as an additional level of description which is particularly valuable for the generation of dialogue acts.

Automatic Generation of a Complex Dialogue History

We briefly review our dialogue model and present a first approach to automatic analysis of interactive information retrieval dialogues based on this model. We discuss the assumptions that we have to place on the model, present an algorithm that given a certain action from either participant calculates the set of relevant partial structures that could represent this action, and discuss some criteria for selecting one of these structures.

Usability and assessments of multimodal interaction in the SPEAK! system: an experimental case study

Abstract This article discusses an experimental evaluation of an adaptive, multimodal user interface which generates context-sensitive help for guiding a users interaction with an information retrieval system. Test users were studied during their interaction with three versions of the SPEAK! system. Two versions offered active help, either in the form of spoken or written output, whereas a control version provided standard passive help texts only. The study was explorative in nature and mainly relied on qualitative data analyses. In order to evaluate the dialogue guidance/active help approach and the influence of the output modes, evaluation criteria focused on usability and subjective satisfaction of users with the interaction. The study was designed to be open for the exploration of typical usage patterns and the users own evaluation criteria. Data from the observations, users*think-aloud comments, and an open-ended questionnaire were combined and further qualified by differential analyses considering ...

Queries in context: access to digitized historic documents in a collaboratory for the humanities

In contrast to standard digital libraries, systems addressing the specific requirements of cultural heritage need to deal with digitized material like scanned documents instead of borne digital items. Such systems aim at providing the means for domain experts, e.g. historians, to collaboratively work with the given material. To support their work, automatic indexing mechanisms for both textual and pictorial digitized documents need to be combined with retrieval methods exploiting the content as well as the context of information items for precise searches. In the COLLATE project we devised several access methods using textual contents, feature extraction from images, metadata, and annotations provided by the users.