Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition

TL;DR

This paper introduces a novel joint learning approach combining generative and discriminative models for unsupervised dependency parsing, leveraging dual decomposition to improve performance across multiple languages.

Contribution

It presents a simple, general method that jointly learns generative and discriminative models using dual decomposition, enhancing unsupervised dependency parsing.

Findings

Achieved state-of-the-art results on the UD treebank for thirty languages.

Effectively captures advantages of both generative and discriminative models.

Improves learning outcomes in unsupervised dependency parsing.

Abstract

Unsupervised dependency parsing aims to learn a dependency parser from unannotated sentences. Existing work focuses on either learning generative models using the expectation-maximization algorithm and its variants, or learning discriminative models using the discriminative clustering algorithm. In this paper, we propose a new learning strategy that learns a generative model and a discriminative model jointly based on the dual decomposition method. Our method is simple and general, yet effective to capture the advantages of both models and improve their learning results. We tested our method on the UD treebank and achieved a state-of-the-art performance on thirty languages.