Convolutional 2D knowledge graph embeddings
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14289
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- 32nd AAAI Conference on Artificial Intelligence (AAAI-2018)
- First page
- 1811
- Volume
- -
- Issue
- -
- ISSN
- 2374-3468
- Open access status
- Exception within 3 months of publication
- Month of publication
- February
- 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
-
3
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Introduced a new state-of-the-art method for the well-established task of knowledge base completion by building on methods from computer vision – two seemingly very distant fields. Furthermore, our work critically analysed the empirical underpinnings of the task at the time and found serious flaws with work dating back nearly a decade. This has lead to the empirical setup of the paper becoming the standard of the field. Accepted at a tier-A conference, it is currently its 5th most cited paper for 2018 and the 27th most cited paper of all time.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -