| Download | - View accepted manuscript: NRC systems for the 2020 Inuktitut–English news translation task (PDF, 436 KiB)
|
|---|
| Author | Search for: Knowles, Rebecca1; Search for: Stewart, Darlene1; Search for: Larkin, Samuel1; Search for: Littell, Patrick1 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), November 19-20, 2020 [Held Online] |
|---|
| Abstract | We describe the National Research Council of Canada (NRC) submissions for the 2020 Inuktitut–English shared task on news translation at the Fifth Conference on Machine Translation (WMT20). Our submissions consist of ensembled domain-specific finetuned transformer models, trained using the Nunavut Hansard and news data and, in the case of Inuktitut–English, backtranslated news and parliamentary data. In this work we explore challenges related to the relatively small amount of parallel data, morphological complexity, and domain shifts. |
|---|
| Publication date | 2020-11-19 |
|---|
| Date created | 2020-11-30 |
|---|
| Publisher | Association of Computational Linguistics |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | e06a1d9c-5574-4ea1-8b93-1ab28090e851 |
|---|
| Record created | 2020-11-30 |
|---|
| Record modified | 2020-12-02 |
|---|
