This paper reports the results of a series of connectionist simulations aimed at establishing the value of different types of contexts as predictors of the grammatical categories of words. A comparison is made between ‘compositional’ frames (Monaghan & Christiansen, 2004), and noncompositional or ‘conjoint’ frames (Mintz, 2003). Attention is given to the role of utterance boundaries both as a c...

BACKGROUND Recent research has addressed the suppression of cortical sensory responses to altered auditory feedback that occurs at utterance onset regarding speech. However, there is reason to assume that the mechanisms underlying sensorimotor processing at mid-utterance are different than those involved in sensorimotor control at utterance onset. The present study attempted to examine the dyna...

In this paper, we propose to use an utterance length (duration) dependent threshold for rejecting an unknown input utterance with a general speech (garbage) model. A general speech model, comparing with more sophisticated anti-subword models, is a more viable solution to the utterance rejection problem for low-cost applications with stringent storage and computational constraints. However, the ...

Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train powerful language models with self-supervised objectives, such as Masked Language Model (MLM). Based on a pilot study, we observe three issues of existing general-purpose when they are applied the text-to-SQL semantic parsers: fail dete...

Objective This study was aimed at investigating the best way to seek clarification when failing correctly understand meaning of an English utterance.

A novel graph-based utterance generation method for open-domain dialogue systems is proposed in this paper. After an association graph of words and utterance patterns from a dialogue corpus is constructed, a label propagation algorithm is used for generating system utterances from the words and utterance patterns in the association graph that are found to strongly correlate with the words and u...

Many researchers have been developing natural language dialogue systems as a human-friendly man-machine interface. The human factors in a man-machine dialogue, however, are not obvious enough to understand with regard to how people talk with a dialogue system. 141 dialogues which our dialogue system had in DiaLeague '97 were analyzed at the utterance and dialogue levels, where DiaLeague '97 was...

In this paper, we describe the effectiveness of utterance generation using causal knowledge for a dialogue system. Recently, there has been a variety of research on non-taskoriented dialogue systems; however, an effective approach has not yet been developed. One of the most important reasons for this is that non-task-oriented dialogue systems lack common sense knowledge, which is not in their d...

Speed of utterance is an important factor in smooth and efficient conversation. We report a technique to increase utterance speed and that might improve a speaker's impression and information efficiency in conversation. We used a visual display consisting of optic flows in a large visual field that induced participants' illusory self-motion perception (vection). The speed of vection corresponde...

On the basis of the short-time relative speech rate defined by the authors, this paper examines the optimum width of the smoothing window by perceptual experiments on the naturalness of re-synthesized speech. With the optimum window of 270 ms, relative speech rates are obtained both for ‘fast’ and ‘slow’ utterances of the same sentence, using an utterance produced at a ‘normal’ speech rate. The...