Attention, intentions, and the structure of discourse
Computational Linguistics
On the controlled elicitation of spontaneous speech
Speech Communication - Special issue on phonetics and phonology of speaking styles: reduction and elaboration in speech communication
Prosodic predictors of discourse finality in spontaneous monologues
Speech Communication
Assessing agreement on classification tasks: the kappa statistic
Computational Linguistics
The Role of Pause Occurrence and Pause Duration in the Signaling of Narrative Structure
PorTAL '02 Proceedings of the Third International Conference on Advances in Natural Language Processing
Discourse segmentation of spoken dialogue: an empirical approach
Discourse segmentation of spoken dialogue: an empirical approach
Discourse segmentation by human and automated means
Computational Linguistics
Intention-based segmentation: human reliability and correlation with linguistic cues
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Combining multiple knowledge sources for discourse segmentation
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Intonational features of local and global discourse structure
HLT '91 Proceedings of the workshop on Speech and Natural Language
| Hi-index | 0.00 |
This paper describes an experiment we conducted in order to test the reliability of two discourse segmentation models which have been widely used in computational linguistics. The main purpose of the test is to pick one of them for our future research, which aims to assess the role of prosody in structuring discourse in European Portuguese. We compared the models of Grosz and Sidner (1986) and Passonneau and Litman (1997) using spontaneous speech. The latter displayed a higher level of consensus among coders. We also observed that listening to the original speech influenced the level of agreement among coders.