← Back to OpenAI updates ← Terug naar OpenAI-updates
OpenAI ARTICLE ARTIKEL 25 May 2016 25 mei 2016

Adversarial training methods for semi-supervised text classification Adversarial training methods for semi-supervised text classification

Read paper(opens in a new window) Read paper(opens in a new window)

Article details Artikelgegevens
AI maker AI-maker OpenAI Type Type Article Artikel Published Gepubliceerd 25 May 2016 25 mei 2016 Updates Updates Videos Video's View original article Bekijk origineel artikel

Abstract

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriate for sparse high-dimensional inputs such as one-hot word representations. We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself. The proposed method achieves state of the art results on multiple benchmark semi-supervised and purely supervised tasks. We provide visualizations and analysis showing that the learned word embeddings have improved in quality and that while training, the model is less prone to overfitting. Code is available atthis https URL⁠(opens in a new window).

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriate for sparse high-dimensional inputs such as one-hot word representations. We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself. The proposed method achieves state of the art results on multiple benchmark semi-supervised and purely supervised tasks. We provide visualizations and analysis showing that the learned word embeddings have improved in quality and that while training, the model is less prone to overfitting. Code is available atthis https URL⁠(opens in a new window).

Authors

Takeru Miyato, Andrew M. Dai, Ian Goodfellow

Related articles

View all

Disrupting malicious uses of AI by state-affiliated threat actors Security Feb 14, 2024

Building an early warning system for LLM-aided biological threat creation Publication Jan 31, 2024

Democratic inputs to AI grant program: lessons learned and implementation plans Safety Jan 16, 2024

Democratic inputs to AI grant program: lessons learned and implementation plans Safety Jan 16, 2024

More from OpenAI Meer van OpenAI

All updates Alle updates

Gemini komt eraan