Better Alignments = Better Translations?

@inproceedings{Ganchev2008BetterA,
  title={Better Alignments = Better Translations?},
  author={Kuzman Ganchev and Jo{\~a}o Graça and Ben Taskar},
  booktitle={ACL},
  year={2008}
}
Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often produce little or no improvements in machine translation quality. In this work we analyze a recently proposed agreement-constrained EM algorithm for unsupervised alignment models. We attempt to tease apart the effects that this simple but effective modification has on alignment precision and recall trade-offs, and how… CONTINUE READING
Highly Influential
This paper has highly influenced 14 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 78 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 57 extracted citations

78 Citations

01020'09'11'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 78 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-3 of 3 references

Going beyond AER

  • N. F. Ayan, B. J. Dorr
  • 2006
2 Excerpts

Europarl: A multilingual corpus

  • NIPS.P. Koehn
  • 2002
2 Excerpts

Similar Papers

Loading similar papers…