Sciweavers

164 search results - page 1 / 33
» Improved Word Alignment with Statistics and Linguistic Heuri...
Sort
View
EMNLP
2009
13 years 2 months ago
Improved Word Alignment with Statistics and Linguistic Heuristics
We present a method to align words in a bitext that combines elements of a traditional statistical approach with linguistic knowledge. We demonstrate this approach for Arabic-Engl...
Ulf Hermjakob
ACL
2007
13 years 6 months ago
Guiding Statistical Word Alignment Models With Prior Knowledge
We present a general framework to incorporate prior knowledge such as heuristics or linguistic features in statistical generative word alignment models. Prior knowledge plays a ro...
Yonggang Deng, Yuqing Gao
AMTA
2004
Springer
13 years 10 months ago
Multi-align: Combining Linguistic and Statistical Techniques to Improve Alignments for Adaptable MT
Abstract. An adaptable statistical or hybrid MT system relies heavily on the quality of word-level alignments of real-world data. Statistical alignment approaches provide a reasona...
Necip Fazil Ayan, Bonnie J. Dorr, Nizar Habash
ACL
2010
13 years 2 months ago
Diversify and Combine: Improving Word Alignment for Machine Translation on Low-Resource Languages
We present a novel method to improve word alignment quality and eventually the translation performance by producing and combining complementary word alignments for low-resource la...
Bing Xiang, Yonggang Deng, Bowen Zhou
ACL
2010
13 years 2 months ago
Improving Statistical Machine Translation with Monolingual Collocation
This paper proposes to use monolingual collocations to improve Statistical Machine Translation (SMT). We make use of the collocation probabilities, which are estimated from monoli...
Zhan-yi Liu, Haifeng Wang, Hua Wu, Sheng Li