Improving Language Modelling with Noise Contrastive Estimation
- Submitting institution
-
The University of Kent
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13781
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
- First page
- 5277
- Volume
- -
- Issue
- -
- ISSN
- 2374-3468
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2018
- URL
-
https://kar.kent.ac.uk/65147/
- 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)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In neural networks where outputs have many values, probability distributions take a long time to compute. This paper is significant because it proposes a new method to approximating such probability distributions quickly. This shortens the training time for language tasks and improves overall solution quality. Our techniques are widely applicable to any problem involving approximation of a large-scale probability distribution.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
