Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference

ACL 2020  ·  Nikita Kitaev, Dan Klein ·

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.

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Constituency Parsing Penn Treebank Tetra Tagging F1 score 95.44 # 14

Methods


No methods listed for this paper. Add relevant methods here