Abstract
This paper addresses the Hierarchical Phraseóbased (HPB) models which are used in development of different Statistió cal Machine Translation (SMT) Systems for many modern languages. Any SMT System needs large parallel coró pora for accurate performance. Therefore, availability of a large parallel corpus is a preórequisite for designing a reliable, roó bust SMT system between any two lanó guages. The HPB models have shown strong capability of generalization and reó ordering, which in turn gets improved reó sults for the sparse resourced languages. This paper considers English as Source and Urdu as target language for experió ments. For this study, Hierarchical phraseó based Baseline SMT system is used for English to Urdu translation. At the end auó tomatic evaluation of system is performed by using BLEU and NIST as evaluation metrics. Average BLEU evaluation score the developed system got is 13% which is a good competitive score for any sparse reó sourced language.
| Original language | English |
|---|---|
| Pages | 72-76 |
| Number of pages | 5 |
| Publication status | Published - Oct 2013 |
| Externally published | Yes |
| Event | Proceedings of the 4th Workshop on South and Southeast Asian Natural Language Processing - Nagoya, Japan Duration: 1 Oct 2013 → … |
Conference
| Conference | Proceedings of the 4th Workshop on South and Southeast Asian Natural Language Processing |
|---|---|
| Country/Territory | Japan |
| City | Nagoya |
| Period | 1/10/13 → … |