papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-04-22
Nikita Kitaev, Dan Klein

Abstract

We present a constituency parsing algorithm that maps from word-aligned contextualized feature vectors to parse trees. Our algorithm proceeds strictly left-to-right, processing one word at a time by assigning it a label from a small vocabulary. We show that, with mild assumptions, our inference procedure requires constant computation time per word. Our method gets 95.4 F1 on the WSJ test set.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.09745

PDF

http://arxiv.org/pdf/1904.09745


Comments