An Example-Based Machine Translation System Using DP-Matching Between Word Sequences

We propose a new approach to the example-based machine translation paradigm. First, the proposed approach retrieves the most similar example by carrying out DP-matching of the input sentence and source sentences in an example database while measuring the semantic distances of the words. Second, the approach adjusts the gap between the input and the most similar example by using a bilingual dictionary. We demonstrate its high coverage and accuracy through a computational experiment for a limited domain.