We examine the problem of generating definite noun phrases that are appropri-ate referring expressions: that is, noun phrases that (a) successfully identify the intended referent to the hearer whilst (b) not conveying to him or her any false conversational implicatures (Grice, 1975). We review several possible computa-tional interpretotions of the conversational implicature maxims, with different computational costs, and argue that the simplest may be the best, because it seems to be closest to what human speakers do. We describe our recommended algorithm in detail, along with a specification of the resources a host system must provide in order to make use of the algorithm, and an implementation used in the natural language generation component of the IDAS system. 1.

The generation of words in speech involves a number of processing stages. There is, first, a stage of conceptual preparation; this is followed by stages of lexical selection, phonological encoding, phonetic encoding and articulation. In addition, the speaker monitors the output and, if necessary, selfcorrects. Major parts of the theory have been computer modelled. The paper concentrates on experimental reaction time evidence in support of the theory. Central to the skill of speaking is our ability to select words that appropriately express our intentions, to retrieve their

Deep dyslexia is an acquired reading disorder marked by the occurrence of semantic errors (e.g., reading RIVER as "ocean"). In addition, patients exhibit a number of other symptoms, including visual and morphological effects in their errors, a part-of-speech effect, and an advantage for concrete over abstract words. Deep dyslexia poses a distinct challenge for cognitive neuropsychology because there is little understanding of why such a variety of symptoms should co-occur in virtually all known patients. Hinton and Shallice (1991) replicated the co-occurrence of visual and semantic errors by lesioning a recurrent connectionist network trained to map from orthography to semantics. While the success of their simulations is encouraging, there is little understanding of what underlying principles are responsible for them. In this paper we evaluate and, where possible, improve on the most important design decisions made by Hinton and Shallice, relating to the task, the network architecture, the training procedure, and the testing procedure. We identify four properties of networks that underly their ability to reproduce the deep dyslexic symptom-complex: distributed orthographic and semantic representations, gradient descent learning, attractors for word meanings, and greater richness of concrete vs. abstract semantics. The first three of these are general connectionist principles and the last is based on earlier theorizing. Taken together, the results demonstrate the usefulness of a connectionist approach to understanding deep dyslexia in particular, and the viability of connectionist neuropsychology in general.

Abstract not found

This thesis examines disfluencies (e.g., "um", repeated words, and a variety of forms of self-repair) in the spontaneous speech of adult normal speakers of American English. Despite their prevalence, disfluencies have traditionally been viewed as irregular events and have received little attention. The goal of the thesis is to provide evidence that, on the contrary, disfluencies show remarkably regular trends in a number of dimensions. These regularities have consequences for models of human language production; they can also be exploited to improve performance in speech applications. The method includes analysis of over 5000 hand-annotated disfluencies from a database (250,000 words) containing three different styles of spontaneous speech: task-oriented human-computer dialog, task-oriented human-human dialog, and human-human conversation on a prescribed topic. The approach is theory-neutral and strongly data-driven. The annotations correspond to observable characteristics ("features") ...

I survey some recent applications-oriented NL generation systems, and claim that despite very different theoretical backgrounds, these systems have a remarkably similar architecture in terms of the modules they divide the generation process into, the computations these modules perform, and the way the modules interact with each other. I also compare this 'consensus architecture' among applied NLG systems with psycholinguistic knowledge about how humans speak, and argue that at least some aspects of the consensns architecture seem to be in agreement with what is known about human language production, despite the fact that psycholinguistic plausibility was not in general a goal of the developers of the surveyed systems.

Note that the text that appeared in printed journal contains very minor typographic and grammatical corrections that do not appear in this version. SpeechSkimmer:

Identifying whether an utterance is a statement, question, greeting, and so forth is integral to effective automatic understanding of natural dialog. Little is known, however, about how such dialog acts (DAs) can be automatically classified in truly natural conversation. This study asks whether current approaches, which use mainly word information, could be improved by adding prosodic information. The study is based on more than 1000 conversations from the Switchboard corpus. DAs were handannotated, and prosodic features (duration, pause, F0, energy, and speaking rate) were automatically extracted for each DA. In training, decision trees based on these features were inferred

Only humans communicate using language and carry on conversations with one another. And the skills of conversation have developed in humans in such a way as to exploit all of the unique affordances of the human body. We make complex representational gestures with our prehensile hands, gaze away and towards one another out of the corners of our centrally set eyes, and use the pitch and melody of our voices to emphasize and clarify what we are saying. Perhaps because conversation is so defining of humanness and human interaction, the metaphor of face-to-face conversation has been applied to human-computer interface design for quite some time. One of the early arguments for the utility of this metaphor gave a list of features of face-to-face conversation that could be applied fruitfully to human-computer interaction, including mixed initiative, nonverbal communication, sense of presence, rules for transfer of control (Nickerson 1976). However, although these feature

this paper, acoustic and prosodic cues to such repairs are identified, based on an analysis of a corpus taken from the ARPA Air Travel Information System database, and methods are proposed for exploiting these cues for repair detection, especially the task of modeling word fragments, and repair correction. The relative contributions of these speech-based cues, as well as other text-based repair cues, are examined in a statistical model of repair site detection that achieves a precision rate of 91% and recall of 86% on a prosodically labeled corpus of repair utterances. (This paper appears in the Journal of the Acoustical Society of America, 95 (3), March 1994, pp.1603--1616.) PACS numbers: 43.72Ja,43.70.B,43.70.Bk,43.70.Fq Nakatani&Hirschberg, JASA 2 Introduction