Concrete Models and Empirical Evaluations for the Categorical Compositional Distributional Model of Meaning
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2555
- Type
- D - Journal article
- DOI
-
10.1162/coli_a_00209
- Title of journal
- Computational Linguistics
- Article number
- 1
- First page
- 71
- Volume
- 41
- Issue
- 1
- ISSN
- 0891-2017
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2015
- 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)
-
-
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Implements a unified higher order theory of logical and statistical models of meaning and develops concrete models for constructing sentence representations from large scale statistical word representations, evaluates the models and demonstrates the better performance of tensor-based models over vector-based ones. Introduces three new datasets annotated with human judgements. Led to EPSRC CAF EP/J002607/2 (?381k, 2013-16) for Sadrzadeh, multi-site EPSRC EP/I037512/1 (?345k, 2012-16) for Grefenstette, 1m$ Air Force Office of Scientific Research International Collaboration grant FA9550-14-1-0079, Grefenstette moving to Google DeepMind, feature article in London Mathematical Society NewsLetter, feature article in NewScientist.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -