Polyhedral characterization of discrete dynamic programming
Operations Research
Network flows: theory, algorithms, and applications
Network flows: theory, algorithms, and applications
A parsing: fast exact Viterbi parse selection
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Online large-margin training of dependency parsers
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Non-projective dependency parsing using spanning tree algorithms
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
A fast finite-state relaxation method for enforcing global constraints on sequence decoding
HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Selected Topics in Column Generation
Operations Research
CoNLL-X shared task on multilingual dependency parsing
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Incremental integer linear programming for non-projective dependency parsing
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Dependency parsing by belief propagation
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Joint inference in information extraction
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Concise integer linear programming formulations for dependency parsing
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Relaxed marginal inference and its application to dependency parsing
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Efficient third-order dependency parsers
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
On dual decomposition and linear programming relaxations for natural language processing
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Dual decomposition for parsing with non-projective head automata
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Dual decomposition with many overlapping components
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Vine pruning for efficient multi-pass dependency parsing
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
| Hi-index | 0.00 |
Graph-based dependency parsers suffer from the sheer number of higher order edges they need to (a) score and (b) consider during optimization. Here we show that when working with LP relaxations, large fractions of these edges can be pruned before they are fully scored---without any loss of optimality guarantees and, hence, accuracy. This is achieved by iteratively parsing with a subset of higherorder edges, adding higher-order edges that may improve the score of the current solution, and adding higher-order edges that are implied by the current best first order edges. This amounts to delayed column and row generation in the LP relaxation and is guaranteed to provide the optimal LP solution. For second order grandparent models, our method considers, or scores, no more than 6--13% of the second order edges of the full model. This yields up to an eightfold parsing speedup, while providing the same empirical accuracy and certificates of optimality as working with the full LP relaxation. We also provide a tighter LP formulation for grandparent models that leads to a smaller integrality gap and higher speed.