Headed-Span-Based Projective Dependency Parsing
Songlin Yang, Kewei Tu · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
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(n 3 ) 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 1 .