Generating Unambiguous and Diverse Referring Expressions
- Submitting institution
-
Edinburgh Napier University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2710372
- Type
- D - Journal article
- DOI
-
10.1016/j.csl.2020.101184
- Title of journal
- Computer Speech and Language
- Article number
- 101184
- First page
- -
- Volume
- 68
- Issue
- -
- ISSN
- 0885-2308
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2020
- 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
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper sets a new state-of-art in Referring Expressions Generation and proposes a new approach that could be applied in other language generation tasks. It is the first paper to propose generating a set of REs instead of one in order to produce more interesting and variable text. The research described in this paper has informed an EPSRC project proposal with Trivago EP/T024917/1 - £416,848 (ranked first out of 13 in the special call on responsible innovation) which looks into developing NLG models from sparse data that are able to generate variable and interesting text.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -