A Maximum Entropy Word Aligner for Arabic-English Machine Translation

  title={A Maximum Entropy Word Aligner for Arabic-English Machine Translation},
  author={Abraham Ittycheriah and Salim Roukos},
This paper presents a maximum entropy word alignment algorithm for ArabicEnglish based on supervised training data. We demonstrate that it is feasible to create training material for problems in machine translation and that a mixture of supervised and unsupervised methods yields superior performance. The probabilistic model used in the alignment directly models the link decisions. Significant improvement over traditional word alignment techniques is shown as well as improvement on several… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 134 citations. REVIEW CITATIONS
95 Citations
16 References
Similar Papers


Publications citing this paper.

134 Citations

Citations per Year
Semantic Scholar estimates that this publication has 134 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 16 references

Wordnet: An on-line lexical database

  • G. Miller.
  • International Journal of Lexicography, 3(4):235…
  • 1990
Highly Influential
5 Excerpts

Improvement in Word Alignments

  • Niyu Ge.
  • Presentation given at DARPA/TIDES MT workshop.
  • 2004
1 Excerpt

Della Pietra , Stephen A . Della Pietra , and Robert L . Mercer . 1993 . The Mathematics of Statistical Machine Translation : Parameter Estimation

  • Dekang Lin
  • Computational Linguistics
  • 2003
3 Excerpts

Similar Papers

Loading similar papers…