cSMTiser: word standardisation
- Authors
- Ljubešić, Nikola ; Perovšek, Matic and Erjavec, Tomaž
- Item identifier
- http://hdl.handle.net/11356/1169
- Project URL
- https://github.com/clarinsi/csmtiser
- Date issued
- 2017-11-27
- Type
- toolService
- Language(s)
- Slovenian
- Description
- Word standardisation of non-standard language as found in user-generated content, using cSMTiser (https://github.com/clarinsi/csmtiser), a tool for text normalisation via character-level machine translation. The tool has been trained on the Janes-Norm dataset (http://hdl.handle.net/11356/1084) and background resources.
- Publisher
- Jožef Stefan Institute
- Acknowledgement
- ARRS (Slovenian Research Agency) J6-6842 "JANES: Resources, Tools and Methods for the Research of Nonstandard Internet Slovene" Swiss National Science Foundation 160501 "ReLDI" ARRS (Slovenian Research Agency) P2-103 "Knowledge Technologies"
- Subject(s)
- word normalisation
- Collection(s)
-