MBT2: a method for combining fragments of examples in example-based translation

摘要

Example-Based Translation is a new approach to machine translation. The basic idea of this approach is very simple: it is to translate a sentence by using translation examples of similar sentences. One of the major issues of Example-Based Translation is to study the utilization of more than one translation example when translating one source sentence. This paper proposes MBT2, which is a method of translating complete sentences by using multiple examples. The representation, matching expression, is introduced, which represents the combination of fragments of translation examples. The translation process of MBT2 consists of three stages: 1.(1) Making a source-matching expression from a source sentence.2.(2) Transferring a source-matching expression into a target-matching expression.3.(3) Constructing a target sentence from a target-matching expression. This mechanism generates several translation candidates and the score of a translation is defined to select the best translation out of them.