vix.ing · top · new · best · stats · spec

Cross-neutralising: Probing for joint encoding of linguistic information in multilingual models

2020/10/24 by Rochelle Choenni, Ekaterina Shutova, Choenni, Rochelle +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2010.12825

openalex publication_date 2020/10/24 · openalex created_date 2020/10/29 · openalex updated_date 2026/07/28

Abstract

Multilingual sentence encoders are widely used to transfer NLP models across languages. The success of this transfer is, however, dependent on the model's ability to encode the patterns of cross-lingual similarity and variation. Yet, little is known as to how these models are able to do this. We propose a simple method to study how relationships between languages are encoded in two state-of-the-art multilingual models (i.e. M-BERT and XLM-R). The results provide insight into their information sharing mechanisms and suggest that linguistic properties are encoded jointly across typologically-similar languages in these models.

Related