Discovering Latent Concepts Learned in BERT

Understand

A large number of studies that analyze deep neural network models and their ability to encode various linguistic and non-linguistic concepts provide an interpretation of the inner mechanics of these models.

• The scope of the analyses is limited to pre-defined concepts that reinforce the traditional linguistic knowledge and do not reflect on how novel concepts are learned by the model.
• We address this limitation by discovering and analyzing latent concepts learned in neural network models in an unsupervised fashion and provide interpretations from the model's perspective.
• In this work, we study: i) what latent concepts exist in the pre-trained BERT model, ii) how the discovered latent concepts align or diverge from classical linguistic hierarchy and iii) how the latent concepts evolve across layers.