Our goal is to identify the features that predict cue selectlob and placement in order to devise strategies for automatic text generation.

Our two stage methodology for the study of cue usage coordinates an exhaustive corpus analysis with a system for text generation. Coding of the corpus uses Relational Discourse Analysis, a synthesis of two previous accounts of discourse structure. In the first stage of our study, hypotheses about cue usage are evaluated and refined using the corpus analysis. Several initial results concerning how cues mark segment structure are presented here. In the second stage of our study, the results of the corpus analysis are used to determine a set of heuristics to be implemented in a system for text generation. The automatic generation of texts is then used to exercise and further evaluate the heuristics for cue placement. Discourse cues play a crucial role in many discourse processing tasks, including plan recognition (Litman & Allen 1987), anaphora resolution (Grosz & Sidner 1986), and generation of coherent multisentential texts (Elhadad & McKeown 1990; Rosner & Stede 1992; Scott & de Souza...

AURALIZATION OF DOCUMENT STRUCTURE Steve Portigal Advisor: University of Guelph, 1994 Professor T. Carey An experiment compared the effectiveness of auditory, visual, and combination cues to convey document structure. Subjects demonstrated an equivalent level of understanding of the document structure and its content with either a combination cue or a visual cue. Subjects required more time to answer questions in the combination condition than in the visual condition. This suggests a greater cognitive effort is required. A sound-only condition has the poorest performance both in response time and in the subject's answers to questions about the document's structure and its content. Subjects were grouped based on whether or not they replayed sounds as a retention tactic. Subjects who replayed sounds did better than subjects who did not. These results contribute to our understanding of potential uses of sound in user interfaces. The specific cues used here for this particular task do not ...

Our goal is to identify the features that predict cue placement and selection in order to devise strategies for automatic text generation. Much previous work in this area has relied on intuitions, constructed examples, or unsystematic analyses of naturally occurring data. We describe a coding scheme for the exhaustive analysis of discourse, and report two results based on this analysis. Discourse cues play a crucial role in many discourse processing tasks, including plan recognition (Litman and Allen, 1987), anaphora resolution (Grosz and Sidner, 1986), and generation of coherent multisentential texts (Elhadad and McKeown, 1990a; Rosner and Stede, 1992; Scott and de Souza, 1990; Zukerman, 1990). Cues are words or phrases such as because, first, although and also that mark structural and semantic relationships between discourse entities. Research in reading comprehension presents a mixed picture (Goldman and Murray, 1992; Lorch, 1989) suggesting that felicitous use of cues improves co...

This article may be used for research, teaching and private study purposes. Any substantial or systematic reproduction, re-distribution, re-selling, loan or sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of this material. WAYS TO REDUCE MAYER COGNITIVE AND MORENO LOAD