Automatic Evaluation of the Fluency of English-to-Japanese Machine Translation Using Word Alignment

DOI Web Site Web Site 21 References

Bibliographic Information

Other Title
  • 単語アライメントを用いた英日機械翻訳文の流暢さの自動評価
  • タンゴ アライメント オ モチイタ エイニチ キカイ ホンヤクブン ノ リュウチョウサ ノ ジドウ ヒョウカ

Search this article

Abstract

This paper presents a method of automatically evaluating the fluency of machine-translated sentences. We constructed a classifier that would distinguish machine translations from human translations, using Support Vector Machines as machine learning algorithms. In order to obtain a clue to the distinction, we focused on literal translations (word-for-word translations). The classifier was constructed based on features derived from word alignment distributions between source sentences and human/machine translations. Our method employed parallel corpora to construct the classifier but required neither manually labeled training examples nor multiple reference translations to evaluate new sentences. We confirmed that our method could assist evaluation on system level. We also found that this method could identify the qualitative characteristics of machine translations, which would greatly help improve the translation quality.

Journal

References(21)*help

See more

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top