Can BERT eat RuCoLA? Topological Data Analysis to Explain

Abstract

This paper investigates how Transformer language models (LMs) fine-tuned for acceptability classification capture linguistic features. Our approach uses the best practices of topological data analysis (TDA) in NLP: we construct directed attention graphs from attention matrices, derive topological features from them, and feed them to linear classifiers. We introduce two novel features, chordality, and the matching number, and show that TDA-based classifiers outperform fine-tuning baselines. We experiment with two datasets, CoLA and RuCoLA in English and Russian, typologically different languages. On top of that, we propose several black-box introspection techniques aimed at detecting changes in the attention mode of the LMs during fine-tuning, defining the LM's prediction confidences, and associating individual heads with fine-grained grammar phenomena. Our results contribute to understanding the behavior of monolingual LMs in the acceptability classification task, provide insights into the functional roles of attention heads, and highlight the advantages of TDA-based approaches for analyzing LMs. We release the code and the experimental results for further uptake.

arXiv commentAccepted to the Workshop on Slavic NLP @ EACL 2023

References in corpus (6)

• A Survey of the State of Explainable AI for Natural Language Processing
• Artificial Text Detection via Examining the Topology of Attention Maps
• Linguistic Analysis of Pretrained Sentence Encoders with Acceptability Judgments
• RuCoLA: Russian Corpus of Linguistic Acceptability
• Acceptability Judgements via Examining the Topology of Attention Maps
• Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations