Tuning as Ranking

@inproceedings{Hopkins2011TuningAR,
  title={Tuning as Ranking},
  author={Mark Hopkins and Jonathan May},
  booktitle={EMNLP},
  year={2011}
}
We offer a simple, effective, and scalable method for statistical machine translation parameter tuning based on the pairwise approach to ranking (Herbrich et al., 1999). Unlike the popular MERT algorithm (Och, 2003), our pairwise ranking optimization (PRO) method is not limited to a handful of parameters and can easily handle systems with thousands of features. Moreover, unlike recent approaches built upon the MIRA algorithm of Crammer and Singer (2003) (Watanabe et al., 2007; Chiang et al… CONTINUE READING
Highly Influential
This paper has highly influenced 57 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 258 citations. REVIEW CITATIONS

Citations

Publications citing this paper.

258 Citations

020406080'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 258 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 35 references

Similar Papers

Loading similar papers…