| Download | - View final version: Challenges in neural language identification: NRC at VarDial 2020 (PDF, 341 KiB)
|
|---|
| Author | Search for: Bernier-Colborne, Gabriel1; Search for: Goutte, Cyril1 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | VarDial 2020, December 13th, 2020, Barcelona, Spain (Online) |
|---|
| Abstract | We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2020 VarDial evaluation campaign. Although our official results were well below the baseline, we show in this paper that this was not due to the neural approach to language identification in general, but to a flaw in the function we used to sample data for training and evaluation purposes. Preliminary experiments conducted after the evaluation period suggest that our neural approach to language identification can achieve state-of-the-art results on this task, although further experimentation is required. |
|---|
| Publication date | 2020-12-13 |
|---|
| Date created | 2020-12-09 |
|---|
| Publisher | International Committee on Computational Linguistics (ICCL) |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | c82dee32-2231-490d-b134-50cb2490601d |
|---|
| Record created | 2020-12-09 |
|---|
| Record modified | 2020-12-09 |
|---|
