next up previous
次へ: Appendix: Experiments with Parameter 上へ: Statistical Machine Translation adding 戻る: Grammatical Correctness

Conclusion

We have developed a two-stage machine translation system. The first stage is a rule-based machine translation system. The second stage is a statistical machine translation system. Our goal with this system was to obtain fewer unknown words and fewer ungrammatical sentences. However, the results we obtained in experiments were not so good.

We did not optimize parameters nor did we use a reordering model. In future experiments, we will try these techniques, which we expect will enable our system to perform better.



Jin'ichi Murakami 平成22年2月26日