Long-distance hierarchical structure transformation rules utilizing function words

Chenchen Ding, Takashi Inui, Mikio Yamamoto


Abstract
In this paper, we propose structure transformation rules for statistical machine translation which are lexicalized by only function words. Although such rules can be extracted from an aligned parallel corpus simply as original phrase pairs, their structure is hierarchical and thus can be used in a hierarchical translation system. In addition, structure transformation rules can take into account long-distance reordering, allowing for more than two phrases to be moved simultaneously. The rule set is used as a core module in our hierarchical model together with two other modules, namely, a basic reordering module and an optional gap phrase module. Our model is considerably more compact and produces slightly higher BLEU scores than the original hierarchical phrase-based model in Japanese-English translation on the parallel corpus of the NTCIR-7 patent translation task.
Anthology ID:
2011.iwslt-evaluation.21
Volume:
Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 8-9
Year:
2011
Address:
San Francisco, California
Editors:
Marcello Federico, Mei-Yuh Hwang, Margit Rödder, Sebastian Stüker
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
159–166
Language:
URL:
https://aclanthology.org/2011.iwslt-evaluation.21
DOI:
Bibkey:
Cite (ACL):
Chenchen Ding, Takashi Inui, and Mikio Yamamoto. 2011. Long-distance hierarchical structure transformation rules utilizing function words. In Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 159–166, San Francisco, California.
Cite (Informal):
Long-distance hierarchical structure transformation rules utilizing function words (Ding et al., IWSLT 2011)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2011.iwslt-evaluation.21.pdf