Parsing linearizations appreciate PoS tags - but some are fussy about errors

TL;DR

This paper investigates the role of PoS tags in different syntactic parsing paradigms, revealing that their usefulness varies with parser type, encoding method, and tagging accuracy, especially in sequence labeling models.

Contribution

It provides the first detailed analysis of PoS tags' impact on sequence labeling parsers, highlighting their dependency on encoding strategies and accuracy levels.

Findings

PoS tags are more beneficial for sequence labeling parsers.

The impact of PoS accuracy depends on the encoding method used.

PoS-based head-selection encoding performs best only with high accuracy and resources.

Abstract

PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning. Recent work on the impact of PoS tags on graph- and transition-based parsers suggests that they are only useful when tagging accuracy is prohibitively high, or in low-resource scenarios. However, such an analysis is lacking for the emerging sequence labeling parsing paradigm, where it is especially relevant as some models explicitly use PoS tags for encoding and decoding. We undertake a study and uncover some trends. Among them, PoS tags are generally more useful for sequence labeling parsers than for other paradigms, but the impact of their accuracy is highly encoding-dependent, with the PoS-based head-selection encoding being best only when both tagging accuracy and resource availability are high.