Full Program »
Hybrid Machine Translation oriented to Cross-Language Information Retrieval: English-Spanish error analysis
The main objective of this study focuses on analysing the automatic transla-tion of questions (intended as query inputs to a Cross-Language Information Retrieval System) and on the creation of a taxonomy of translation errors present in hybrid machine translation systems (HMT). An analysis of translations by HMT systems was carried out. From these, there is a proposal of a type 1, 2 or 3 error taxonomy weighted according to their level of importance. Results indicate that post-editing is an essential task in the automatic translation process.