Information density and overlap in spoken dialogue
- Submitting institution
-
The University of Hull
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1396276
- Type
- D - Journal article
- DOI
-
10.1016/j.csl.2015.11.001
- Title of journal
- Computer speech & language
- Article number
- -
- First page
- 82
- Volume
- 37
- Issue
- -
- ISSN
- 0885-2308
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- URL
-
http://www.sciencedirect.com/science/article/pii/S0885230815000972
- 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
-
5
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the key outputs from Dethlefs’ PhD thesis. It had academic impact after being highlighted in a standard reference on Natural Language Generation (NLG) in Gatt and Krahmer (2018) Survey of the State of the Art in Natural Language Generation: Core Tasks, applications and evaluation, (Journal of Artificial Intelligence, Vol 61. DOI: https://doi.org/10.1613/jair.5477 ) as one of few existing approaches that addresses uncertainty in NLG through a stochastic planning framework. The work has potential for further impact in deep learning systems in that the hierarchical decomposition proposed is able to learn more efficiently without significant performance loss.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -