Low-Resource Text Classification using Domain-Adversarial Learning

Abstract

Deep learning techniques have recently shown to be successful in many natural language processing tasks forming state-of-the-art systems. They require, however, a large amount of annotated data which is often missing. This paper explores the use of domain-adversarial learning as a regularizer to avoid overfitting when training domain invariant features for deep, complex neural networks in low-resource and zero-resource settings in new target domains or languages. In case of new languages, we show that monolingual word vectors can be directly used for training without prealignment. Their projection into a common space can be learnt ad-hoc at training time reaching the final performance of pretrained multilingual word vectors.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Neural Machine Translation by Jointly Learning to Align and Translate
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Improving neural networks by preventing co-adaptation of feature detectors
• Natural Language Processing (almost) from Scratch
• Generative Adversarial Networks
• Thumbs up? Sentiment Classification using Machine Learning Techniques
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Improved Training of Wasserstein GANs
• Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering
• Wasserstein GAN
• Massively Multilingual Word Embeddings
• Word Translation Without Parallel Data
• Adversarial Learning for Neural Dialogue Generation
• Boundary-Seeking Generative Adversarial Networks
• Adversarial Generation of Natural Language
• Language Generation with Recurrent Generative Adversarial Networks without Pre-training
• Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
• Adversarially Regularized Autoencoders
• Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary