| Autor: |
Kuhn, Roland, Senellart, Jean, Ma, Jeff, Rosti, Antti-Veikko, Zbib, Rabih, Chalabi, Achraf, Dugast, Loic, Foster, George, Makhoul, John, Matsoukas, Spyros, Matusov, Evgeny, Nader, Hazerm, Safadi, Rami, Schwartz, Richard, Stephan, Jens, Ueffing, Nicola, Yang, Jin |
| Jazyk: |
angličtina |
| Rok vydání: |
2010 |
| Popis: |
With the recent remarkable success of statistical machine translation (SMT) systems, the question arises: how can the linguistic knowledge locked up in older, rule-based machine translation (RBMT) systems most conveniently be incorporated in these systems? In many cases, RBMT systems represent an investment of several man-years of applied expertise; even if one is an ardent proponent of the SMT approach, it makes sense to capitalize on this investment. Inside the GALE project, two teams looked at the problem of incorporating RBMT systems into SMT ones. Surprisingly, though the teams were working completely independently and on two different language pairs (Chinese-English and Arabic-English), they reached almost identical conclusions as to the best approach to pursue, and attained remarkably good experimental results with this approach. This section describes the work of these two teams. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
