Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models

Alejo Lopez-Avila, Víctor Suárez-Paniagua

Submission Type: Regular Long Paper

Submission Track: Efficient Methods for NLP

Keywords: transfer learning, contrastive learning, denoising autoencoders, NLU

TL;DR: New technique for transfer learning combining contrastive learning with autoencoders and data augmentation

Abstract:

Recently, using large pre-trained Transformer models for transfer learning tasks has evolved to the point where they have become one of the
flagship trends in the Natural Language Processing (NLP) community, giving rise to various outlooks such as prompt-based, adapters, or combinations with unsupervised approaches, among many others. In this work, we propose a 3-Phase technique to adjust a base model for a classification task. First, we adapt the model’s signal to the data distribution by performing further training with a Denoising Autoencoder (DAE). Second, we adjust the representation space of the output to the corresponding classes by clustering through a Contrastive Learning (CL) method. In addition, we introduce a new data augmentation approach for Supervised Contrastive Learning to correct the unbalanced datasets. Third, we apply fine-tuning to delimit the predefined categories. These different phases provide relevant and complementary knowledge to the model to learn the final task. We supply extensive experimental results on several datasets to demonstrate these claims. Moreover, we include an ablation study and compare the proposed method against other ways of combining these techniques.

Submission Number: 4575