Paper: Dynamic Feature Selection for Dependency Parsing

ACL ID D13-1152
Title Dynamic Feature Selection for Dependency Parsing
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013

Feature computation and exhaustive search have significantly restricted the speed of graph-based dependency parsing. We propose a faster framework of dynamic feature selec- tion, where features are added sequentially as needed, edges are pruned early, and decisions are made online for each sentence. We model this as a sequential decision-making problem and solve it by imitation learning techniques. We test our method on 7 languages. Our dy- namic parser can achieve accuracies compara- ble or even superior to parsers using a full set of features, while computing fewer than 30% of the feature templates.