Discontinuous Constituency and BERT: A Case Study of Dutch

03/02/2022
by   Konstantinos Kogkalidis, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/23/2019

Probing the phonetic and phonological knowledge of tones in Mandarin TTS models

This study probes the phonetic and phonological knowledge of lexical ton...
research
01/16/2019

Assessing BERT's Syntactic Abilities

I assess the extent to which the recently introduced BERT model captures...
research
09/21/2022

Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT

Both humans and neural language models are able to perform subject-verb ...
research
06/11/2019

What Does BERT Look At? An Analysis of BERT's Attention

Large pre-trained neural networks such as BERT have had great recent suc...
research
01/26/2021

CLiMP: A Benchmark for Chinese Language Model Evaluation

Linguistically informed analyses of language models (LMs) contribute to ...
research
11/02/2020

Abstracting Influence Paths for Explaining (Contextualization of) BERT Models

While "attention is all you need" may be proving true, we do not yet kno...
research
05/21/2021

A Non-Linear Structural Probe

Probes are models devised to investigate the encoding of knowledge – e.g...

Please sign up or login with your details

Forgot password? Click here to reset