English

Discontinuous Constituency and BERT: A Case Study of Dutch

Computation and Language 2022-03-09 v2 Machine Learning

Abstract

In this paper, we set out to quantify the syntactic capacity of BERT in the evaluation regime of non-context free patterns, as occurring in Dutch. We devise a test suite based on a mildly context-sensitive formalism, from which we derive grammars that capture the linguistic phenomena of control verb nesting and verb raising. The grammars, paired with a small lexicon, provide us with a large collection of naturalistic utterances, annotated with verb-subject pairings, that serve as the evaluation test bed for an attention-based span selection probe. Our results, backed by extensive analysis, suggest that the models investigated fail in the implicit acquisition of the dependencies examined.

Cite

@article{arxiv.2203.01063,
  title  = {Discontinuous Constituency and BERT: A Case Study of Dutch},
  author = {Konstantinos Kogkalidis and Gijs Wijnholds},
  journal= {arXiv preprint arXiv:2203.01063},
  year   = {2022}
}

Comments

8 pages plus references. To appear in Findings of the Association for Computational Linguistics 2022

R2 v1 2026-06-24T09:59:13.451Z