Work

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

Year: 2020

Type: conference-paper

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.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2020.acl-main.557

Authors: Nikita Kitaev, Dan Klein

Institution: University of California, Berkeley

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, Defense Advanced Research Projects Agency

Award: RI: Small: Collaborative Research: Unsupervised Transcription of Early Modern Documents