On Parsing as Tagging

TL;DR

This paper unifies various constituency parsing-as-tagging methods into a three-step pipeline and empirically evaluates how different choices affect parsing accuracy across multiple languages.

Contribution

It introduces a unifying framework for parsing-as-tagging approaches and demonstrates the importance of linearization and alignment in achieving high accuracy.

Findings

Linearization and alignment are critical for accurate tagging-based parsing.

Tetratagging can be reduced to shift-reduce parsing with grammar transformation.

Empirical results across diverse languages highlight key factors for success.

Abstract

There have been many proposals to reduce constituency parsing to tagging in the literature. To better understand what these approaches have in common, we cast several existing proposals into a unifying pipeline consisting of three steps: linearization, learning, and decoding. In particular, we show how to reduce tetratagging, a state-of-the-art constituency tagger, to shift--reduce parsing by performing a right-corner transformation on the grammar and making a specific independence assumption. Furthermore, we empirically evaluate our taxonomy of tagging pipelines with different choices of linearizers, learners, and decoders. Based on the results in English and a set of 8 typologically diverse languages, we conclude that the linearization of the derivation tree and its alignment with the input sequence is the most critical factor in achieving accurate taggers.