Combining (Second-Order) Graph-Based and Headed-Span-Based Projective Dependency Parsing

Anonymous

Abstract: Graph-based methods are popular in dependency parsing for decades, which decompose the score of a dependency tree into scores of dependency arcs. Recently, (Yang and Tu, 2021) propose a headed-span-based method that decomposes the score of a dependency tree into scores of headed spans. In this paper, we combine the two types of methods by considering both arc scores and headed-span scores, designing three scoring methods and the corresponding dynamic programming algorithms for joint inference. Experiments show the effectiveness of our proposed methods.