Back to Search Start Over

Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages

Authors :
Ruzzetti, Elena Sofia
Ranaldi, Federico
Logozzo, Felicia
Mastromattei, Michele
Ranaldi, Leonardo
Zanzotto, Fabio Massimo
Source :
Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics, 2023, pages 14447 - 14461
Publication Year :
2023

Abstract

The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language. In this paper, we propose a novel standpoint to investigate the above issue: using typological similarities among languages to observe how their respective monolingual models encode structural information. We aim to layer-wise compare transformers for typologically similar languages to observe whether these similarities emerge for particular layers. For this investigation, we propose to use Centered Kernel Alignment to measure similarity among weight matrices. We found that syntactic typological similarity is consistent with the similarity between the weights in the middle layers, which are the pretrained BERT layers to which syntax encoding is generally attributed. Moreover, we observe that a domain adaptation on semantically equivalent texts enhances this similarity among weight matrices.

Details

Database :
arXiv
Journal :
Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics, 2023, pages 14447 - 14461
Publication Type :
Report
Accession number :
edsarx.2305.02215
Document Type :
Working Paper
Full Text :
https://doi.org/10.18653/v1/2023.findings-emnlp.963