Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
This addresses parsing efficiency and error compounding for NLP researchers, though it appears incremental as it builds on existing parsing paradigms.
The authors tackled constituency parsing by proposing a novel scheme that predicts syntactic distances to recursively partition sentences top-down, achieving competitive performance on PTB and outperforming previous models on CTB.
In this work, we propose a novel constituency parsing scheme. The model predicts a vector of real-valued scalars, named syntactic distances, for each split position in the input sentence. The syntactic distances specify the order in which the split points will be selected, recursively partitioning the input, in a top-down fashion. Compared to traditional shift-reduce parsing schemes, our approach is free from the potential problem of compounding errors, while being faster and easier to parallelize. Our model achieves competitive performance amongst single model, discriminative parsers in the PTB dataset and outperforms previous models in the CTB dataset.