A Survey of Unsupervised Dependency Parsing

TL;DR

This survey reviews methods for unsupervised dependency parsing, highlighting two main approaches, recent trends, and emphasizing its importance for low-resource language processing and leveraging unannotated text data.

Contribution

It categorizes existing unsupervised dependency parsing methods, discusses recent developments, and offers insights to guide future research in the field.

Findings

Identifies two major classes of approaches

Discusses recent trends in unsupervised parsing

Highlights importance for low-resource languages

Abstract

Syntactic dependency parsing is an important task in natural language processing. Unsupervised dependency parsing aims to learn a dependency parser from sentences that have no annotation of their correct parse trees. Despite its difficulty, unsupervised parsing is an interesting research direction because of its capability of utilizing almost unlimited unannotated text data. It also serves as the basis for other research in low-resource parsing. In this paper, we survey existing approaches to unsupervised dependency parsing, identify two major classes of approaches, and discuss recent trends. We hope that our survey can provide insights for researchers and facilitate future research on this topic.