Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing
This work addresses the need for more accurate parsing in natural language processing, though it is incremental as it builds on existing shift-reduce algorithms.
The authors tackled the problem of improving accuracy in shift-reduce constituent parsing by introducing dynamic oracles for training top-down and in-order parsers, resulting in a state-of-the-art accuracy of 92.0 F1 on the WSJ benchmark.
We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manage to notably increase their accuracy, in comparison to that obtained by performing classic static training. In addition, by improving the performance of the state-of-the-art in-order shift-reduce parser, we achieve the best accuracy to date (92.0 F1) obtained by a fully-supervised single-model greedy shift-reduce constituent parser on the WSJ benchmark.