Improving translation models by applying asymmetric learning

Setsuo Yamada, Masaaki Nagata, Kenji Yamada


Abstract
The statistical Machine Translation Model has two components: a language model and a translation model. This paper describes how to improve the quality of the translation model by using the common word pairs extracted by two asymmetric learning approaches. One set of word pairs is extracted by Viterbi alignment using a translation model, the other set is extracted by Viterbi alignment using another translation model created by reversing the languages. The common word pairs are extracted as the same word pairs in the two sets of word pairs. We conducted experiments using English and Japanese. Our method improves the quality of a original translation model by 5.7%. The experiments also show that the proposed learning method improves the word alignment quality independent of the training domain and the translation model. Moreover, we show that common word pairs are almost as useful as regular dictionary entries for training purposes.
Anthology ID:
2003.mtsummit-papers.56
Volume:
Proceedings of Machine Translation Summit IX: Papers
Month:
September 23-27
Year:
2003
Address:
New Orleans, USA
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
Language:
URL:
https://aclanthology.org/2003.mtsummit-papers.56
DOI:
Bibkey:
Cite (ACL):
Setsuo Yamada, Masaaki Nagata, and Kenji Yamada. 2003. Improving translation models by applying asymmetric learning. In Proceedings of Machine Translation Summit IX: Papers, New Orleans, USA.
Cite (Informal):
Improving translation models by applying asymmetric learning (Yamada et al., MTSummit 2003)
Copy Citation:
PDF:
https://aclanthology.org/2003.mtsummit-papers.56.pdf