Automatic Generation of Typicality Measures for Spatial Language in Grounded Settings
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-331
- Type
- E - Conference contribution
- DOI
-
10.3233/FAIA200341
- Title of conference / published proceedings
- ECAI 2020: 24th European Conference on Artificial Intelligence
- First page
- 2164
- Volume
- 325
- Issue
- -
- ISSN
- 0922-6389
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
https://doi.org/10.5518/764
- 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
-
2
- Research group(s)
-
B - AI (Artificial Intelligence)
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The meta review for the paper said “This paper was acknowledged by all reviewers for its high relevance, strong novelty, and technical quality”. One issue identified in the paper is the difficulties in modelling polysemy; this has been followed up in a paper at KR-20 (https://doi.org/10.24963/kr.2020/72), and at SPLU-20 (“Categorisation, Typicality and Object-Specific Features in Spatial Referring Expressions”)which also built heavily on the environment and modelling presented here. These three papers form the core of the first author’s submitted PhD thesis. Code and data are open sourced.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
