| Download | - View final version: Some tradeoffs in continual learning for Parliamentary neural machine translation systems (PDF, 2.0 MiB)
|
|---|
| Link | https://aclanthology.org/2024.amta-research.10/ |
|---|
| Author | Search for: Knowles, Rebecca1ORCID identifier: https://orcid.org/0000-0002-1647-584X; Search for: Larkin, Samuel J. C. F.1ORCID identifier: https://orcid.org/0009-0000-6147-9631; Search for: Simard, Michel1ORCID identifier: https://orcid.org/0009-0002-5317-3063; Search for: Tessier, Marc A.1ORCID identifier: https://orcid.org/0009-0009-1413-2892; Search for: Bernier-Colborne, Gabriel1; Search for: Goutte, Cyril1; Search for: Lo, Chi-kiu1ORCID identifier: https://orcid.org/0000-0001-8714-7846 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 16th Conference of the Association for Machine Translation in the Americas (AMTA), September 30 - October 02, 2024, Chicago, Illinois, USA |
|---|
| Abstract | In long-term translation projects, like Parliamentary text, there is a desire to build machine translation systems that can adapt to changes over time. We implement and examine a simple approach to continual learning for neural machine translation, exploring tradeoffs between consistency, the model’s ability to learn from incoming data, and the time a client would need to wait to obtain a newly trained translation system. |
|---|
| Publication date | 2024-09-30 |
|---|
| Publisher | Association for Machine Translation in the Americas |
|---|
| 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 | 5612a8e3-8cf4-4703-9fd5-bf1a881202eb |
|---|
| Record created | 2024-11-07 |
|---|
| Record modified | 2024-11-08 |
|---|
