Concrete Models and Empirical Evaluations for the Categorical Compositional Distributional Model of Meaning
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 16230
- 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
- Solving the long-standing challenge of compositionally in distributional semantics in Natural Language Processing, this paper developed concrete models for constructing compositional phrase/sentence representations using statistical data & grammatical structure. It evaluated the models on data and provided experimental validations. The datasets of the paper are now widely used by the community, the paper is the most cited paper of the setting. The developments led to an EPSRC Career Acceleration Fellowship and an EPSRC multi-site grant. Soon after the paper, one author moved to Google DeepMind. The findings featured in an article in London Mathematical Society NewsLetter and article in NewScientist.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -