Fast and Adaptive Online Training of Feature-Rich Translation Models

@inproceedings{Green2013FastAA,
  title={Fast and Adaptive Online Training of Feature-Rich Translation Models},
  author={Spence Green and Sida I. Wang and Daniel M. Cer and Christopher D. Manning},
  booktitle={ACL},
  year={2013}
}
We present a fast and scalable online method for tuning statistical machine translation models with large feature sets. The standard tuning algorithm—MERT—only scales to tens of features. Recent discriminative algorithms that accommodate sparse features have produced smaller than expected translation quality gains in large systems. Our method, which is based on stochastic gradient descent with an adaptive learning rate, scales to millions of features and tuning sets with tens of thousands of… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS
31 Citations
49 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 31 extracted citations

Similar Papers

Loading similar papers…