| Download | - View accepted manuscript: Stabilizing Minimum Error Rate Training (PDF, 541 KiB)
|
|---|
| Author | Search for: Foster, George1; Search for: Kuhn, Roland1 |
|---|
| Affiliation | - National Research Council Canada. NRC Institute for Information Technology
|
|---|
| Format | Text, Article |
|---|
| Conference | The 4th Workshop on Statistical Machine Translation (EACL 2009), Athens, Greece, March 30-31, 2009 |
|---|
| Abstract | The most commonly used method for training feature weights in statistical machine translation (SMT) systems is Och’s minimum error rate training (MERT) procedure. A well-known problem with Och’s procedure is that it tends to be sensitive to small changes in the system, particularly when the number of features is large. In this paper, we quantify the stability of Och’s procedure by supplying different random seeds to a core component of the procedure (Powell’s algorithm). We show that for systems with many features, there is extensive variation in outcomes, both on the development data and on the test data. We analyze the causes of this variation and propose modifications to the MERT procedure that improve stability while helping performance on test data. |
|---|
| Date published | 2009 |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NRC number | NRCC 50757 |
|---|
| NPARC number | 16335066 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | fffb669c-87f6-4a2c-8bba-e292e723abe8 |
|---|
| Record created | 2010-11-10 |
|---|
| Record modified | 2020-04-16 |
|---|
