@inproceedings{SisLab114,
       booktitle = {2012 IEEE RIVF International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF)},
           month = {March},
           title = {Exploiting Non-Parallel Corpora for Statistical Machine Translation},
          author = {Cuong Hoang and Anh Cuong Le and Phuong Thai Nguyen and Tu Bao Ho},
            year = {2012},
           pages = {1--6},
        keywords = {Electronic publishing;Encyclopedias;Error analysis;Internet;Length measurement;Training;language translation;learning (artificial intelligence);nonparallel corpora;parallel sentence pair detection;reinforcement learning scheme;statistical machine translation system;},
             url = {https://eprints.uet.vnu.edu.vn/eprints/id/eprint/114/},
        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.}
}