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

Nikita Kitaev, Dan Klein


Abstract
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.
Anthology ID:
2020.acl-main.557
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6255–6261
Language:
URL:
https://aclanthology.org/2020.acl-main.557
DOI:
10.18653/v1/2020.acl-main.557
Bibkey:
Cite (ACL):
Nikita Kitaev and Dan Klein. 2020. Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6255–6261, Online. Association for Computational Linguistics.
Cite (Informal):
Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference (Kitaev & Klein, ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2020.acl-main.557.pdf
Video:
 http://slideslive.com/38929445
Code
 nikitakit/tetra-tagging +  additional community code
Data
Penn Treebank