Measuring Non-cooperation in Dialogue
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1587418
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016)
- First page
- 1925
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- December
- Year of publication
- 2016
- URL
-
https://www.aclweb.org/anthology/C16-1181.pdf
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the first-ever quantitative method for measuring linguistic non-cooperation. It was evaluated on a novel corpus of political dialogue, but being able to detect non-cooperative dialogue has broader utility, e.g., for call centre monitoring. Accepted at the world-class COLING conference, the paper consolidates and extends prior work, providing a definitive account and robust evaluation. Reichel & Lendvai (2018) extended the approach to discourse prosody. Lupkowski & Rybacka (2016) used our method to analyse the judge-program conversations at the Loebner Turing test contest. The method is developed further in an EPSRC project (EP/T024666/1; OU (lead), Cambridge, Sheffield and Toshiba).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -