TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Constituency Parsing	Penn Treebank	Tetra Tagging	F1 score	95.44	# 12

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/tetra-tagging-word-synchronous-parsing-with/constituency-parsing-on-penn-treebank)](https://paperswithcode.com/sota/constituency-parsing-on-penn-treebank?p=tetra-tagging-word-synchronous-parsing-with)`

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.