| 1 |
Does BERT agree? Evaluating knowledge of structure dependence through agreement relations ...
|
|
|
|
Abstract:
Learning representations that accurately model semantics is an important goal of natural language processing research. Many semantic phenomena depend on syntactic structure. Recent work examines the extent to which state-of-the-art models for pre-training representations, such as BERT, capture such structure-dependent phenomena, but is largely restricted to one phenomenon in English: number agreement between subjects and verbs. We evaluate BERT's sensitivity to four types of structure-dependent agreement relations in a new semi-automatically curated dataset across 26 languages. We show that both the single-language and multilingual BERT models capture syntax-sensitive agreement patterns well in general, but we also highlight the specific linguistic contexts in which their performance degrades. ... : 6 pages ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1908.09892
https://dx.doi.org/10.48550/arxiv.1908.09892
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Bayesian phylogenetics, sequence alignment and the genetic structure of the Kainji languages. ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
