Language and Chronology : Text dating by machine learning
- Submitting institution
-
Queen's University of Belfast
- Unit of assessment
- 26 - Modern Languages and Linguistics
- Output identifier
- 167465719
- Type
- A - Authored book
- DOI
-
10.1163/9789004410046
- Publisher
- Brill
- ISBN
- 978-90-04-41004-6
- Open access status
- -
- Month of publication
- September
- 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
-
1
- Research group(s)
-
-
- Proposed double-weighted
- Yes
- Double-weighted statement
- This monograph is the main output resulting from a three-year Leverhulme project. It presents the most extensive consideration to date of traditional methods of establishing the chronology of early Irish texts. A corpus of closely-dated texts was compiled from a wide-ranging and complex examination of primary texts traditionally dated to c.700-c.1500. New machine-learning algorithms were developed based on extensive, iterative trials on the Irish annals to produce a robust dating model. The results were subjected to protracted and multifaceted examination in order to determine the most efficient and robust algorithms, and to investigate the advantages and disadvantages of machine-learning methods.
- Reserve for an output with double weighting
- No
- Additional information
- -
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -