Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction

by   Ningyu Zhang, et al.

Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks. However, the resultant model generalizability remains poorly understood. We do not know, for example, how excellent performance can lead to the perfection of generalization models. In this study, we analyze a fine-tuned BERT model from different perspectives using relation extraction. We also characterize the differences in generalization techniques according to our proposed improvements. From empirical experimentation, we find that BERT suffers a bottleneck in terms of robustness by way of randomizations, adversarial and counterfactual tests, and biases (i.e., selection and semantic). These findings highlight opportunities for future improvements. Our open-sourced testbed DiagnoseRE is available in


page 1

page 2

page 3

page 4


On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines

Fine-tuning pre-trained transformer-based language models such as BERT h...

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

Gigantic pre-trained models have become central to natural language proc...

Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction?

Recently many studies have been conducted on the topic of relation extra...

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

The conventional recipe for maximizing model accuracy is to (1) train mu...

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

Pretrained models from self-supervision are prevalently used in fine-tun...

It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations

Training on only perfect Standard English corpora predisposes pre-traine...

MSnet: A BERT-based Network for Gendered Pronoun Resolution

The pre-trained BERT model achieves a remarkable state of the art across...