Learning to search better than your teacher

32nd International Conference on Machine Learning, ICML 2015

Volumn 3, Issue , 2015, Pages 2058-2066

  Chang, Kai Wei ^a   Krishnamurthy, Akshay ^b   Agarwal, Alekh ^c   Daumé, Hal ^d   Langford, John ^c  

^a UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN   (United States)

^b CARNEGIE MELLON UNIVERSITY   (United States)

^c MICROSOFT RESEARCH   (United States)

^d UNIVERSITY OF MARYLAND   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 84969951377     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Abbott, H.L and Katchalski, M. On the snake in the box problem. Journal of Combinatorial Theory, Series B, 45 (1):13-24, 1988.
2. Cesa-Bianchi, N. and Lugosi, G. Prediction, Learning, and Games. Cambridge University Press, 2006.
3. Collins, Michael and Roark, Brian. Incremental parsing with the perceptron algorithm. In Proceedings of the Conference of the Association for Computational Linguistics (ACL), 2004.
4. Daumé III, Hal and Marcu, Daniel. Learning as search optimization: Approximate large margin methods for structured prediction. In Proceedings of the International Conference on Machine Learning (ICML), 2005.
5. Daumé III, Hal, Langford, John, and Marcu, Daniel. Search-based structured prediction. Machine Learning Journal, 2009.
6. Daumé III, Hal, Langford, John, and Ross, Stephane. Efficient programmable learning to search. arXiv: 1406.1837, 2014.
7. Doppa, Janardhan Rao, Fern, Alan, and Tadepalli, Prasad. HC-Search: A learning framework for search-based structured prediction. Journal of Artificial Intelligence Research (JAIR), 50, 2014.
8. Goldberg, Yoav and Nivre, Joakim. Training deterministic parsers with non-deterministic oracles. Transactions of the ACL, 1, 2013.
9. Goldberg, Yoav, Sartorio, Francesco, and Satta, Giorgio. A tabular method for dynamic oracles in transition-based parsing. Transactions of the ACL, 2, 2014.
10. He, He, Daumé III, Hal, and Eisner, Jason. Imitation learning by coaching. In Neural Information Processing Systems (NIPS), 2012.
11. Kuhlmann, Marco, Gomez-Rodriguez, Carlos, and Satta, Giorgio. Dynamic programming algorithms for transition-based dependency parsers. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume I, pp. 673-682. Association for Computational Linguistics, 2011.
12. Langford, John and Beygelzimer, Alina. Sensitive error correcting output codes. In Learning Theory, pp. 158-172. Springer, 2005.
13. Marcus, Mitch, Marcinkiewicz, Mary Ann, and Santorini, Beatrice. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2): 313-330, 1993.
14. McDonald, Ryan, Pereira, Fernando, Ribarov, Kiril, and Hajic, Jan. Non-projective dependency parsing using spanning tree algorithms. In Proceedings of the Joint Conference on Human Language Technology Conference and Empirical Methods in Natural Language Processing (HLT/EMNLP), 2005.
15. Nivre, Joakim. An efficient algorithm for projective dependency parsing. In International Workshop on Parsing Technologies (IWPT), pp. 149-160, 2003.
16. Ross, Stéphane and Bagnell, J. Andrew. Efficient reductions for imitation learning. In Proceedings of the Workshop on Artificial Intelligence and Statistics (Al-Stats), 2010.
17. Ross, Stéphane and Bagnell, J. Andrew. Reinforcement and imitation learning via interactive no-regret learning. arXiv: 1406.5979, 2014.
18. Ross, Stéphane, Gordon, Geoff J., and Bagnell, J. Andrew. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the Workshop on Artificial Intelligence and Statistics (AI-Stats), 2011.
19. Zinkevich, Martin. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the International Conference on Machine Learning (ICML), 2003.