Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 24634661
- Type
- D - Journal article
- DOI
-
10.1016/j.csl.2019.06.009
- Title of journal
- Computer Speech and Language
- Article number
- -
- First page
- 123
- Volume
- 59
- Issue
- -
- ISSN
- 0885-2308
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2019
- 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 pioneering work introducing Reinforcement Learning to Natural Language Generation (NLG), which has now become a new standard in the field as evidenced by citations The paper summarises and extends 2 conference contributions, which were both presented at ACL, the premier venue in NLP. This work has led to: 2 successful EPSRC standard proposals (joint value over £1M; EP/N017536/1, EP/M005429/1), an invited research stay at Nuance Communications in Silicon Valley with Ronald.Kaplan@nuance.com (who received the ACL'19 lifetime achievement award), and several invited research seminar talks at international leading institutions, including ICSI Berkeley, Heidelberg and Cambridge Uni.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -