Latent Topic Text Representation Learning on Statistical Manifolds
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-159
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2018.2808332
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 5643
- Volume
- 29
- Issue
- 11
- ISSN
- 2162-237X
- Open access status
- Compliant
- Month of publication
- March
- 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
-
3
- Research group(s)
-
B - AI (Artificial Intelligence)
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Potentially significant since it presents a novel and efficient framework for topic learning in text with higher topic coherency(PMI) than competing methods (CNN/word2vec), across 3 real-life news corpora, allowing better clustering of similar texts. Formed part of first author’s PhD who subsequently was awarded a Chinese Academy of Sciences Presidential Scholarship (Special Prize), one of only 50 awards annually for all research areas. Also one of the key publications in a successful application for “Knowledge Engineering With Big Data”, 54-Month, RMB45m, 15-Institution National Grand Project (No.2016YFB1000900), obtained by the third author. More than 700 full-text-views on IEEE.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
