Log In Sign Up

Domain Adversarial Fine-Tuning as an Effective Regularizer

by   Giorgos Vernikos, et al.

In Natural Language Processing (NLP), pre-trained language models (LMs) that are transferred to downstream tasks have been recently shown to achieve state-of-the-art results. In this work, we extend the standard fine-tuning process of pretrained LMs by introducing a new regularization technique, AFTER; domain Adversarial Fine-Tuning as an Effective Regularizer. Specifically, we complement the task-specific loss used during fine-tuning with an adversarial objective. This additional loss term is related to an adversarial classifier, that aims to discriminate between in-domain and out-of-domain text representations. In-domain refers to the labeled dataset of the task at hand while out-of-domain refers to unlabeled data from a different domain. Intuitively, the adversarial classifier acts as a regularizer which prevents the model from overfitting to the task-specific domain. Empirical results on sentiment analysis, linguistic acceptability, and paraphrase detection show that AFTERleads to improved performance compared to standard fine-tuning.


How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

The fine-tuning of pre-trained language models has a great success in ma...

Using Selective Masking as a Bridge between Pre-training and Fine-tuning

Pre-training a language model and then fine-tuning it for downstream tas...

Task-guided Disentangled Tuning for Pretrained Language Models

Pretrained language models (PLMs) trained on large-scale unlabeled corpu...

Robust Fine-tuning via Perturbation and Interpolation from In-batch Instances

Fine-tuning pretrained language models (PLMs) on downstream tasks has be...

Pseudo-task Regularization for ConvNet Transfer Learning

This paper is about regularizing deep convolutional networks (ConvNets) ...

How Many Data Points is a Prompt Worth?

When fine-tuning pretrained models for classification, researchers eithe...

AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning

Fine-tuning large pre-trained language models on downstream tasks is apt...