Adaptive generation in dialogue systems using dynamic user modeling
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14475426
- Type
- D - Journal article
- DOI
-
10.1162/COLI_a_00203
- Title of journal
- Computational Linguistics
- Article number
- -
- First page
- 883
- Volume
- 40
- Issue
- 4
- ISSN
- 0891-2017
- Open access status
- Out of scope for open access requirements
- Month of publication
- December
- Year of publication
- 2014
- URL
-
-
- 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
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper appears in the top archival journal for Natural Language Processing and Computational Linguistics. The ideas developed in this paper led directly to user modelling and adaptation aspects of our successful Alexa prize systems in 2017 and 2018, which has led to the creation of a spin-out company Alana AI in 2020. This work also fed into the EC H2020 projects MuMMER (900Keuro) and SPRING (1.1Meuro) on adaptive conversational interaction with robots.
Contribution:
Co-creation of the overall model, the evaluation framework, and technical methodology using Reinforcement Learning. Assisted with data analysis and co-wrote the paper.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
