A Unifying Theory of Transition-based and Sequence Labeling Parsing

TL;DR

This paper establishes a theoretical link between transition-based and sequence labeling parsing, enabling the creation of new, efficient encodings for dependency parsing that perform comparably to existing methods.

Contribution

It introduces a unifying framework that maps transition-based parsing algorithms to sequence labeling encodings, facilitating faster and simpler parsing methods.

Findings

Sequence labeling versions are learnable.

Comparable performance to existing encodings.

New encodings enable faster parsing.

Abstract

We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-based parsing and sequence-labeling parsing, but also provides a method to obtain new encodings for fast and simple sequence labeling parsing from the many existing transition-based parsers for different formalisms. Applying it to dependency parsing, we implement sequence labeling versions of four algorithms, showing that they are learnable and obtain comparable performance to existing encodings.