Download | - View final version: NRC Machine Translation System for WMT 2017 (PDF, 298 KiB)
|
---|
DOI | Resolve DOI: https://doi.org/10.18653/v1/W17-4732 |
---|
Author | Search for: Lo, Chi-kiu1; Search for: Chen, Boxing1; Search for: Cherry, Colin1; Search for: Foster, George1; Search for: Larkin, Samuel1; Search for: Stewart, Darlene1; Search for: Kuhn, Roland1 |
---|
Affiliation | - National Research Council of Canada. Information and Communication Technologies
|
---|
Format | Text, Article |
---|
Conference | Second Conference on Machine Translation (WMT 2017), September 7-8, 2017, Copenhagen, Denmark |
---|
Abstract | We describe the machine translation systems developed at the National Research Council of Canada (NRC) for the RussianEnglish and Chinese-English news translation tasks of the Second Conference on Machine Translation (WMT 2017). We conducted several experiments to explore the best baseline settings for neural machine translation (NMT). In the RussianEnglish task, to our surprise, our bestperforming system is one that rescores phrase-based statistical machine translation outputs using NMT rescoring features. On the other hand, in the ChineseEnglish task, which has far more parallel training data, NMT is able to outperform SMT significantly. The NRC MT systems is the best constrained system in Russian-English (out of nine participants) and the fourth best constrained system in Chinese-English (out of twenty participants) in WMT 2017 human evaluati |
---|
Publication date | 2017-09 |
---|
Publisher | Association for Computational Linguistics |
---|
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 | 54b9b979-0894-4faa-a4bf-a5a24eadca92 |
---|
Record created | 2024-04-29 |
---|
Record modified | 2024-04-29 |
---|