Natural language generation as incremental planning under uncertainty: adaptive information presentation for statistical dialogue systems
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10602063
- Type
- D - Journal article
- DOI
-
10.1109/TASL.2014.2315271
- Title of journal
- IEEE ACM Transactions on Audio, Speech, and Language Processing
- Article number
- -
- First page
- 979
- Volume
- 22
- Issue
- 5
- ISSN
- 2329-9290
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- 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
-
2
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper presents a rigorous empirical analysis of state-of-the-art neural language generation techniques based on a shared task the authors organised. The work substantially shaped the NLG landscape: 1) The dataset has become a new benchmark as evidenced by citations. 2) Our results have highly influenced academic discourse as evidenced by papers and invited talks from leading NLP researchers and industrialists, as well as social media threads. 3) The task attracted a total of 62 submissions with 1/3 from industry. 4) The work was recognised with a total of 10 invited keynotes and a nomination for a best paper award.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
