Log-Linear Models for Word Alignment

  title={Log-Linear Models for Word Alignment},
  author={Yang Liu and Qun Liu and Shouxun Lin},
We present a framework for word alignment based on log-linear models. All knowledge sources are treated as feature functions, which depend on the source langauge sentence, the target language sentence and possible additional variables. Log-linear models allow statistical alignment models to be easily extended by incorporating syntactic information. In this paper, we use IBM Model 3 alignment probabilities, POS correspondence, and bilingual dictionary coverage as features. Our experiments show… CONTINUE READING
Highly Cited
This paper has 120 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 86 extracted citations

120 Citations

Citations per Year
Semantic Scholar estimates that this publication has 120 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…