Searching for musical features using natural language queries: the C@merata evaluations at MediaEval
- Submitting institution
-
Goldsmiths' College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2040
- Type
- D - Journal article
- DOI
-
10.1007/s10579-018-9422-2
- Title of journal
- Language Resources and Evaluation
- Article number
- -
- First page
- 87
- Volume
- 53
- Issue
- 1
- ISSN
- 1574-020X
- Open access status
- Not compliant
- Month of publication
- March
- Year of publication
- 2018
- URL
-
http://research.gold.ac.uk/id/eprint/24146/
- 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
-
5
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This article describes in detail the multidisciplinary challenges addressed in a series of increasingly sophisticated evaluations over several years at MediaEval concerned with the highly problematic task of using natural language for queries within a music information retrieval system. Based on experience of the various authors in the fields of information retrieval, natural language processing and musicology, this ground-breaking multidisciplinary work analyses many of the difficulties encountered, defining a comprehensive taxonomy of query- and answer-types and describing the consistent experimental setup used for the evaluations, together with discussion of the evolving results.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -