Exploiting Non-Parallel Corpora for Statistical Machine Translation

Abstract

Constructing a corpus of parallel sentence pairs is an important work in building a Statistical Machine Translation system. It impacts deeply how the quality of a Statistical Machine Translation could achieve. The more parallel sentence pairs we use to train the system, the better translation's quality it is. Nowadays, comparable non-parallel corpora become important resources to alleviate scarcity of parallel corpora. The problem here is how to extract parallel sentence pairs automatically but accurately from comparable non-parallel corpora, which are usually very "noisy". This paper presents how we can apply the reinforcement-learning scheme with our new proposed algorithm for detecting parallel sentence pairs. We specify that from an initial set of parallel sentences in a domain, the proposed model can extract a large number of new parallel sentence pairs from non-parallel corpora resources in different domains, concurrently increasing the system's translation ability gradually.