Domain transfer for deep natural language generation from abstract meaning representations
- Submitting institution
-
The University of Hull
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1396279
- Type
- D - Journal article
- DOI
-
10.1109/mci.2017.2708558
- Title of journal
- IEEE computational intelligence magazine
- Article number
- -
- First page
- 18
- Volume
- 12
- Issue
- 3
- ISSN
- 1556-603X
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2017
- URL
-
http://ieeexplore.ieee.org/document/7983466/
- 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
-
0
- Research group(s)
-
-
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper was a methodological precursor of research proposed and used in a grant on natural language generation from knowledge graph - funded by Stanford AI spin-off Diffbot: https://www.diffbot.com/ . The work was presented as a keynote talk at the NIPS 2016 workshop “Let’s Discuss: Learning Methods for Dialogue”: http://letsdiscussnips2016.weebly.com/ amongst some of the most prominent leaders in the field from academia and industry. The use of knowledge graphs in NLP tasks also inspired the use of knowledge graph-based sentiment embeddings in Annika Schoene’s PhD thesis.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -