| Autor: |
Huidan Liu, Weina Zhao, Minghua Nuo, Jinling Hong, Xin Yu, Jian Wu |
| Předmět: |
|
| Zdroj: |
Himalayan Linguistics; 2016, Vol. 15 Issue 1, p149-166, 19p |
| Abstrakt: |
This paper proposes a Chinese to Tibetan machine translation system with multiple translating strategies. The key corpora and technologies are explained in detail. Experiments show the sub-systems output the translation of each phrase in the same order as they are in the Chinese sentence rather than in a Tibetan sentence, which leads to unsatisfactory translation quality. Consequently, an order adjusting model is essential to Chinese to Tibetan translation system. The phrase recall of the SMT (MaxProb) sub-system makes an improvement of 9.71% over the popular off-the-shelf language neutral statistical machine translation programme Moses. Our translation system achieves a speed of about 0.175s per sentence on a PowerEdge R710 server with 2 4-core Intel E5620 (2.40 GHz) CPUs and 16 GB memories, which meets the requirement of a computer aided translation system. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
