Study of practical effectiveness for machine translation using recursive chain-link-type learning

Abstract

A number of machine translation systems based on the learning algorithms are presented. These methods acquire translation rules from pairs of similar sentences in a bilingual text corpora. This means that it is difficult for the systems to acquire the translation rules from sparse data. As a result, these methods require large amounts of training data in order to acquire high-quality translation rules. To overcome this problem, we propose a method of machine translation using a Recursive Chain-linktype Learning. In our new method, the system can acquire many new high-quality translation rules from sparse translation examples based on already acquired translation rules. Therefore, acquisition of new translation rules results in the generation of more new translation rules. Such a process of acquisition of translation rules is like a linked chain. From the results of evaluation experiments, we confirmed the effectiveness of Recursive Chain-link-type Learning.

Learning Method for Automatic Acquisition of Translation Knowledge

“…In function (2), f ST is the number of pieces in which both the SL word W S and the TL word W T are found, f S is the number of pieces in which the W S are found, and f T is the number of pieces in which the W T are found. In the process based on two bilingual sentence pairs, the system obtains bilingual word pairs and new templates from two bilingual sentence pairs.…”

“…In the process based on two bilingual sentence pairs, the system obtains bilingual word pairs and new templates from two bilingual sentence pairs. Similarity values in all acquired templates are also assigned by function (2). Moreover, during the decision process of bilingual word pairs, the system chooses the most suitable bilingual word pairs using their similarity values when several candidates of bilingual word pairs exist.…”