ACL 2022long11 citations
Headed-Span-Based Projective Dependency Parsing
Abstract
We propose a new method for projective dependency parsing based on headed spans. In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i.e., a span) in the surface order. We call such a span marked by a root word headed span. A projective dependency tree can be represented as a collection of headed spans. We decompose the score of a dependency tree into the scores of the headed spans and design a novel O(n3) dynamic programming algorithm to enable global training and exact inference. Our model achieves state-of-the-art or competitive results on PTB, CTB, and UD
BibTeX
@inproceedings{yang-tu-2022-headed,
title = "Headed-Span-Based Projective Dependency Parsing",
author = "Yang, Songlin and
Tu, Kewei",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.155/",
doi = "10.18653/v1/2022.acl-long.155",
pages = "2188--2200"
}