A Minimal Span-Based Neural Constituency Parser
This work addresses parsing efficiency and accuracy for natural language processing tasks, offering a competitive but incremental improvement over existing methods.
The authors tackled constituency parsing by proposing a minimal neural model that scores labels and spans independently, achieving state-of-the-art single-model performance with 91.79 F1 on the Penn Treebank and 82.23 F1 on the French Treebank.
In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with classical dynamic programming techniques, but also admits a novel greedy top-down inference algorithm based on recursive partitioning of the input. We demonstrate empirically that both prediction schemes are competitive with recent work, and when combined with basic extensions to the scoring model are capable of achieving state-of-the-art single-model performance on the Penn Treebank (91.79 F1) and strong performance on the French Treebank (82.23 F1).