Coarse-to-Fine Decoding for Neural Semantic Parsing
- Submitting institution
-
University of Edinburgh
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 86127165
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/P18-1068
- Title of conference / published proceedings
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- First page
- 731
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- July
- Year of publication
- 2018
- 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)
-
D - Language, Interaction and Robotics
- Citation count
- 24
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Won best-paper award at ACL 2018, the premier NLP conference (acceptance rate 20%). Focuses on semantic parsing, the task of converting natural language to machine interpretable meaning representations. Exploits an intuitive idea, namely that meaning representations have a core component that is reused across expressions and specific details which are domain and language specific. The model has now been incorporated into Allen NLP an open-source platform for research on deep learning methods with over 10K downloads. This work has further led to a collaboration with Amazon in Cambridge and a grant on their part to port the approach to Wikidata.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -