A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages

Abstract

This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete linguistic structure, in the form of morphological features and feature values, presents itself in the vector representations and attention distributions of pre-trained language models for five European languages. The experiments contained herein show that (i) Transformer architectures largely partition their embedding space into convex sub-regions highly correlated with morphological feature value, (ii) the contextualized nature of transformer embeddings allows models to distinguish ambiguous morphological forms in many, but not all cases, and (iii) very specific attention head/layer combinations appear to hone in on subject-verb agreement.

References in corpus (4)

• Assessing BERT's Syntactic Abilities
• Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language
• Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
• Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction

Cited by in corpus (1)

• Are pre-trained text representations useful for multilingual and multi-dimensional language proficiency modeling?