Softmax-Margin CRFs: Training Log-Linear Models with Cost Functions

@inproceedings{Gimpel2010SoftmaxMarginCT,
  title={Softmax-Margin CRFs: Training Log-Linear Models with Cost Functions},
  author={Kevin Gimpel and Noah A. Smith},
  booktitle={HLT-NAACL},
  year={2010}
}
We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduced in the speech recognition community, we describe the method generally for structured models, highlight connections to CLL and max-margin learning for structured prediction (Taskar et al., 2003), and show that the method optimizes a bound on risk. The approach is simple, efficient, and easy to implement, requiring… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 106 CITATIONS, ESTIMATED 30% COVERAGE

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 9 Highly Influenced Citations

  • Averaged 15 Citations per year over the last 3 years

  • 7% Increase in citations per year in 2018 over 2017

Similar Papers

Loading similar papers…