Abstract
This paper presents a probabilistic method to simulate task-oriented human-computer dialogues at the intention level, that may be used to improve or to evaluate the performance of spoken dialogue systems. Our method uses a network of hidden Markov models (HMMs) to predict system and user intentions, where a "language model" predicts sequences of goals and the component HMMs predict sequences of intentions. We compare standard HMMs, input HMMs and input-output HMMs in an effort to better predict sequences of intentions. In addition, we propose a dialogue similarity measure to evaluate the realism of the simulated dialogues. We performed experiments using the DARPA communicator corpora and report results with three different metrics: dialogue length, dialogue similarity and precision-recall
Original language | English |
---|---|
Title of host publication | IEEE Workshop on Automatic Speech Recognition and Understanding, 2005. |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 290-295 |
ISBN (Electronic) | 0-7803-9479-8 |
ISBN (Print) | 0-7803-9478-X |
DOIs | |
Publication status | Published - 2005 |
Event | IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'05) - Cancún, Mexico Duration: 27 Nov 2005 → 1 Dec 2005 |
Workshop
Workshop | IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU'05) |
---|---|
Country/Territory | Mexico |
City | Cancún |
Period | 27/11/05 → 1/12/05 |