Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers

TL;DR

This paper investigates how typological information impacts neural dependency parsing across languages, revealing that coarse grouping and corpus-consistent typology improve transfer, but typological similarity alone is insufficient.

Contribution

It demonstrates that coarse language clustering and corpus-aligned typology enhance neural dependency parsing transfer, challenging the assumption that detailed typological variation is always beneficial.

Findings

Coarse language clusters outperform detailed typological features.

Typology aligned with corpus statistics improves transfer.

Typological similarity is only a rough proxy for transferability.

Abstract

This paper explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in pre-neural parsing, results for neural architectures have been mixed. The aim of our investigation is to better understand this state-of-the-art. Our main findings are as follows: 1) The benefit of typological information is derived from coarsely grouping languages into syntactically-homogeneous clusters rather than from learning to leverage variations along individual typological dimensions in a compositional manner; 2) Typology consistent with the actual corpus statistics yields better transfer performance; 3) Typological similarity is only a rough proxy of cross-lingual transferability with respect to parsing.