Language Identification (State of the art)
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.
"Standard" measure:
"Standard" datasets:
System Name | Short Description | Main Publications | Software (if available) | Results | Comments (i.e. extra resources used, train/test times, ...) |
---|---|---|---|---|---|
SystemName | How does it work? | Author and Article [1] | Software? | 98% according to... | Any extra comments? |
textcat | n-gram matching | Ted Dunning (1994) "Statistical Identification of Language" | Yes | - | - |