An improvement of translation quality with adding key-words in parallel corpus

Abstract

In this paper, we propose a new approach to improve the translation quality by adding the Key-Words of a sentence to the parallel corpus. The main idea of the approach is to find the key-words of sentences that cannot be properly translated by the model, and then put it or them in the training corpus in a separated line as a sentence. During our experiment, we use two statistical machine translation (SMT) systems, word-based SMT (ISI-rewrite) and phrase-based SMT (Moses), and a small parallel corpus (4,000 sentences) to check our assumption. To our glad, we get a better BLEU score than the original parallel text. It can improve about 6% in word-based SMT (isi-rewrite) and 4% in phrased-based SMT (Moses). At last we build a 120,000 English-Chinese parallel corpus in this way.