Discriminative Word Alignment Over Multiple Word Segmentations

Ning Xi, Xinyu Dai, Shujian Huang, Jiajun ChenChinese 2014 · DOI

Abstract

Conventional bilingual word alignment is conducted on sentence pairs with single word segmentation for languages such as Chinese, viz. Single-segmentation-based word alignment (SSWA). However, SSWA may run the risk of losing optimal word segmentation granularities or causing data sparseness in word alignment. This paper proposes Multiple-segmentation-based word alignment (MSWA). In MSWA, diverse and complementary knowledge in multiple word segmentations can be employed to lower the above risks in word alignment. Given <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> word segmentations of a Chinese sentence, a skeleton segmentation is firstly constructed. The alignment between the skele-ton segmentation and the parallel English sentence is log-linearly modeled, where various features defined over multiple word segmentations are incorporated. The Viterbi alignment, the alignment with the highest score, is mapped back to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> word alignments based on <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> segmentations respectively. Experimentally, MSWA outperformed SSWA on all <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> segmentations in both alignment quality and translation performance.
BibTeX
@inproceedings{xi2014discriminative,
  author = {Ning Xi and Xinyu Dai and Shujian Huang and Jiajun Chen},
  title = {{Discriminative Word Alignment Over Multiple Word Segmentations}},
  booktitle = {Chinese},
  year = {2014},
  doi = {10.23919/cje.2014.10851872},
}

Loading related content...

Figure