| Download | - View accepted manuscript: Integration of an Arabic Transliteration Module into a Statistical Machine Translation System (PDF, 272 KiB)
|
|---|
| Author | Search for: Kashani, M.; Search for: Joanis, Eric; Search for: Kuhn, Roland; Search for: Foster, George; Search for: Popowich, F. |
|---|
| Format | Text, Article |
|---|
| Conference | Association for Computational Linguistics (ACL) Second Workshop on Statistical Machine Translation (WMT07), June 23, 2007, Prague, Czech Republic |
|---|
| Abstract | We provide an in-depth analysis of the integration of an Arabic-to-English transliteration system into a general-purpose phrase-based statistical machine translation system. We study the integration from different aspects and evaluate the improvement that can be attributed to the integration using the BLEU metric. Our experiments show that a transliteration module can help significantly in the situation where the test data is rich with previously unseen named entities. We obtain 70% and 53% of the theoretical maximum improvement we could achieve, as measured by an oracle on development and test sets respectively for OOV words (out of vocabulary source words not appearing in the phrase table). |
|---|
| Publication date | 2007 |
|---|
| In | |
|---|
| Language | English |
|---|
| NRC number | NRCC 50332 |
|---|
| NPARC number | 8913876 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 764bce6d-2c60-429b-9216-390c0ab3a2cd |
|---|
| Record created | 2009-04-22 |
|---|
| Record modified | 2020-08-12 |
|---|
