GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples

Danilo Croce, Giuseppe Castellucci, Roberto Basili


Abstract
Recent Transformer-based architectures, e.g., BERT, provide impressive results in many Natural Language Processing tasks. However, most of the adopted benchmarks are made of (sometimes hundreds of) thousands of examples. In many real scenarios, obtaining high- quality annotated data is expensive and time consuming; in contrast, unlabeled examples characterizing the target task can be, in general, easily collected. One promising method to enable semi-supervised learning has been proposed in image processing, based on Semi- Supervised Generative Adversarial Networks. In this paper, we propose GAN-BERT that ex- tends the fine-tuning of BERT-like architectures with unlabeled data in a generative adversarial setting. Experimental results show that the requirement for annotated examples can be drastically reduced (up to only 50-100 annotated examples), still obtaining good performances in several sentence classification tasks.
Anthology ID:
2020.acl-main.191
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2114–2119
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.191
DOI:
10.18653/v1/2020.acl-main.191
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.191.pdf
Video:
 http://slideslive.com/38928799