Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference
This provides a faster and accurate parsing method for natural language processing applications, though it is incremental in improving efficiency over existing parsers.
The paper tackles constituency parsing by assigning labels to each word in parallel and extracting a tree in linear time, achieving 95.4 F1 on the WSJ test set with substantial speedups.
We present a constituency parsing algorithm that, like a supertagger, works by assigning labels to each word in a sentence. In order to maximally leverage current neural architectures, the model scores each word's tags in parallel, with minimal task-specific structure. After scoring, a left-to-right reconciliation phase extracts a tree in (empirically) linear time. Our parser achieves 95.4 F1 on the WSJ test set while also achieving substantial speedups compared to current state-of-the-art parsers with comparable accuracies.