article · Empirical Methods in Natural Language Processing · 2018

Structured Sparsity in Structured Prediction

André F. T. Martins, Noah A. Smith, Pedro M. Q. Aguiar, Mário A. T. Figueiredo

Cited by 68Open access

Abstract

Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of endowing learners with a mechanism for feature selection is still unsolved. Common approaches employ ad hoc filtering or <em>L</em><sub>1</sub>- regularization; both ignore the structure of the feature space, preventing practicioners from encoding structural prior knowledge. We fill this gap by adopting regularizers that promote structured sparsity, along with efficient algorithms to handle them. Experiments on three tasks (chunking, entity recognition, and dependency parsing) show gains in performance, compactness, and model interpretability.

Cite this paper

APA 7

Martins, A. F. T., Smith, N. A., Aguiar, P. M. Q., & Figueiredo, M. A. T. (2018). Structured Sparsity in Structured Prediction. Empirical Methods in Natural Language Processing, 104(4), 1500–1511. https://doi.org/10.1184/r1/6473714

MLA 9

Martins, André F. T., et al. “Structured Sparsity in Structured Prediction.” Empirical Methods in Natural Language Processing, vol. 104, no. 4, 2018, pp. 1500–11, https://doi.org/10.1184/r1/6473714.

Chicago

Martins, André F. T., Noah A. Smith, Pedro M. Q. Aguiar, and Mário A. T. Figueiredo. 2018. “Structured Sparsity in Structured Prediction.” Empirical Methods in Natural Language Processing 104 (4): 1500–11. https://doi.org/10.1184/r1/6473714.

Harvard

Martins, A.F.T. et al. (2018) ‘Structured Sparsity in Structured Prediction’, Empirical Methods in Natural Language Processing, 104(4), pp. 1500–1511. Available at: https://doi.org/10.1184/r1/6473714.

BibTeX

@article{martins2018structured,
  title = {{Structured Sparsity in Structured Prediction}},
  author = {Martins, André F. T. and Smith, Noah A. and Aguiar, Pedro M. Q. and Figueiredo, Mário A. T.},
  journal = {Empirical Methods in Natural Language Processing},
  volume = {104},
  number = {4},
  pages = {1500--1511},
  year = {2018},
  doi = {10.1184/r1/6473714}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.