To explain complex phenomena, an explanation system must be able to select information from a formal representation of domain knowledge, organize the selected information into multisentential discourse plans, and realize the discourse plans in text. Although recent years have witnessed significant progress in the development of sophisticated computational mechanisms for explanation, empirical results have been limited. This paper reports on a seven-year effort to empirically study explanation generation from semantically rich, large-scale knowledge bases. In particular, it describes KNIGHT, a robust explanation system that constructs multisentential and multiparagraph explanations from the Biology Knowledge Base, a large-scale knowledge base in the domain of botanical anatomy, physiology, and development. We introduce the Two-Panel evaluation methodology and describe how KNIGHT'S performance was assessed with this methodology in the most extensive empirical evaluation conducted on an explanation system. In this evaluation, KNIGHT scored within "half a grade " of domain experts, and its performance exceeded that of one of the domain experts. 1.

We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear.

This paper introduces the special issue of Knowledge-Based Systems on HumanComputer Collaboration (HCC). It derives a set of fundamental issues from a definition of collaboration, introduces two major approaches to HCC, and surveys each approach, showing how it formulates and addresses the issues. It concludes by proposing some themes that should characterize a unified approach to human-computer collaboration. 1 Introduction Collaboration is a process in which two or more agents work together to achieve shared goals. Thirty researchers came together in Raleigh, North Carolina in October of 1993 for a AAAI Fall Symposium dedicated to this topic. The goal of the symposium was to achieve a better understanding of Human-Computer Collaboration (HCC), collaboration involving at least one human and one computational agent. In particular, the symposium sought to explore the fundamental nature of collaborative problem solving, understand the constraints brought to bear by the differing charac...

this paper, we present a plan-based model for response generation during collaborative planning, based on a recursive Propose-Evaluate-Modify framework for modeling collaboration. We focus on identifying strategies for content selection when 1) the system initiates information-sharing to gather further information in order to make an informed decision about whether to accept a proposal from the user, and 2) the system initiates collaborative negotiation to negotiate with the user to resolve a detected conflict in the user's proposal. When our model determines that information-sharing should be pursued, it selects a focus of information-sharing from among multiple uncertainties that might be addressed, chooses an appropriate information-sharing strategy, and formulates a response that initiates an information-sharing subdialogue. When our model determines that conflicts must be resolved, it selects the most effective conflicts to address in resolving disagreemen t about the user's proposal, iden tiffes appropriate jus tiffcation for the sys tem' s claims, and formulates a response that initiates a negotiation subdialogue

Our goal is to identify the features that pre- dict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on in- tuition or small numbers of constructed ex- amples. We apply a machine learning program, C4.5, to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.

... This paper presents a system to do so. It uses a text planner to determine the content and structure of the captions based on: (1) a representation of the structure of the graphical presentation and its mapping to the data it depicts, (2) a framework for identifying the perceptual complexity of graphical elements, and (3) the structure of the data expressed in the graphic. The output of the planner is further processed regarding issues such as ordering, aggregation, centering, generating referring expressions and lexical choice. We discuss the architecture of our system and its strengths and limitations. Our implementation is currently limited to 2-D charts and maps, but, except for lexical information, it is completely domain independent. We illustrate our discussion with figures and generated captions about housing sales in Pittsburgh.

We present an implemented procedure to select an appropriate connective to link two propositions, which is part of a large text generation system. Each connec- tive is defined as a set of constraints between features of fire propositions it connects. Our focus has been to identify pragmatic features that can be produced by a deep generator to provide a simple representation of connectives. Using these features, we can account for a variety of connective usages, and we can distinguish between similar connectives. We describe how a surface generator can produce complex sentences when given these features in input. The selection procedure is implemented as part of a large functional unification grammar.

In collaborative planning activities, since the agents are autonomous and heterogeneous, it is inevitable that conflicts arise in their beliefs during the planning process. In cases where such conflicts are relevant to the tk at hand, the agents should engage in collaborative negotiation as an attempt to square away the discrepancies in their beliefs. This paper presents a computational strategy for detecting conflicts regarding proposed beliefs and for engaging in collaborative negotiation to resolve the conflicts that warrant resolution. Our model is capable of selecting the most effective aspect to address in its pursuit of conflict resolution in cases where multiple conflicts arise, and of selecting appropriate evidence to justify the need for such modification. Furthermore, by capturing the negotiation process in a recursive Propose-Evaluate-Modify cycle of actions, our model can successfully handle embedded negotiation subdialogues.

Text generation is a field of artificial intelligence aiming at modelling the process of natural language production. Text generation is best characterized as the process of making choices between alternate linguistic realizations under the constraints specified in the input to a text generator. Depending on the practical application, the input can take different forms- streams of numbers in report generation, traces

This paper outlines a number of problems with RST's elaboration relation, and discusses a new model of text structure that results from leaving this relation out of the set of relations. In this model, trees of interclausal/intersentential relations account for the local coherence of a text, while its global coherence is accounted for by a separate device: global focus. 1 Introduction Many theories of discourse propose that a coherent text is one whose clauses, sentences and text spans (or perhaps the propositions expressed by these text units) stand in particular relations to one another. The basic motivation in these theories stems from the observation that a text is more than a sequence of independent units: whether a particular unit makes sense in a given discourse depends not only on this unit by itself, but also on its relationship with the other units in the discourse. This claim has been spelled out in many dierent ways, but there are two requirements that any such theor...