Non-projective Dependency Parsing using Spanning Tree Algorithms
McDonald et al., 2005, Non-projective Dependency Parsing using Spanning Tree Algorithms (Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005))
Subscriber deck — free during early access
1 cards in “3.1 Single-best MIRA” · whole deck
3.1 Single-best MIRA
- What is single-best MIRA, and why was it used with Chu-Liu-Edmonds?It keeps only one margin constraint, for the current highest-scoring tree \(y' = \arg\max_{y'} s(x_t, y')\), instead of exponentially many. Earlier projective work used the \(k\) best trees, but \(k\)-best extensions of Chu-Liu-Edmonds are too inefficient. Unlike the perceptron, MIRA updates aggressively to maximize the margin.
- McDonald et al., 2005, Non-projective Dependency Parsing using Spanning Tree Algorithms (Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005)), §3.1, pp. 527–528
Source
- Ryan McDonald, Fernando Pereira, Kiril Ribarov and Jan Hajič. 2005. Non-projective Dependency Parsing using Spanning Tree Algorithms. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005), pp. 523–530. https://aclanthology.org/H05-1066/