Integration of example-based transfer and rule-based generation

When we speak a foreign language, we use not only grammatical rules but also memorized expressions. Namely, translations are sometimes produced by mimicking translation examples. Example-Based Machine Translation(EBMT) adopts this strategy as follows: 1) Retrieves the translation example whose Source Expression (SE) is the same as or most similar to the input sentence, 2) Translates the input sentence using the Target Expression (TE) of the retrieved translation example. Since it is impossible to memorize all possible sentence patterns, the "chunking + best-matching + recombination" method is practical from the point of view of coverage. It provides translation examples at various linguistic levels, and decomposes an input sentence into chunks. For each chunk, the translation example is retrieved by best-matching. The output sentence is obtained by recombining the TE parts of the retrieved translation examples. However, this method suffers from translation quality lapses at the boundaries of the recombined chunks. These lapses are caused by serious gaps between languages, such as between English and Japanese, that differ widely in their syntactic features. This paper proposes a method to solve the problem of the structural gap by introducing a new generation module to the model of (Furuse, 92), that is able to handle the entire translation process within the example-based framework. This integrated method has been implemented in a prototype English-to-Japanese translation system. Figure 1 shows the proposed integrated method between example-based transfer and rule-based generation. The transfer module decomposes an input sentence using the SE(English) part of translation examples, and converts each piece of the input sentence into the equivalent piece in the TE(Japanese) using translation examples. The rule-based generation part of the integrated method consists of a composition module and an adjustment module. The composition module composes a structure from fragmentary examples by using Japanese grammatical constraint, and checks whether the structure is grammatically appropriate or not. The adjustment module refines the sentence output of the composition module so that the final output is as natural as colloquial Japanese.