Vietnamese transition-based dependency parsing with supertag features

TL;DR

This paper improves Vietnamese dependency parsing by incorporating supertag features into a transition-based approach, achieving significant accuracy gains with both gold and automatic supertags.

Contribution

It introduces the use of supertag features in transition-based dependency parsing specifically for Vietnamese, enhancing parsing accuracy.

Findings

18.92% improvement with gold supertags

3.57% improvement with automatic supertags

Effective enhancement of Vietnamese dependency parsing

Abstract

In recent years, dependency parsing is a fascinating research topic and has a lot of applications in natural language processing. In this paper, we present an effective approach to improve dependency parsing by utilizing supertag features. We performed experiments with the transition-based dependency parsing approach because it can take advantage of rich features. Empirical evaluation on Vietnamese Dependency Treebank showed that, we achieved an improvement of 18.92% in labeled attachment score with gold supertags and an improvement of 3.57% with automatic supertags.