Adversarial Neural Networks for Cross-lingual Sequence Tagging

2018/08/14 by Adel, Heike, Bryl, Anton, Weiss, David +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1808.04736

Abstract

We study cross-lingual sequence tagging with little or no labeled data in the target language. Adversarial training has previously been shown to be effective for training cross-lingual sentence classifiers. However, it is not clear if language-agnostic representations enforced by an adversarial language discriminator will also enable effective transfer for token-level prediction tasks. Therefore, we experiment with different types of adversarial training on two tasks: dependency parsing and sentence compression. We show that adversarial training consistently leads to improved cross-lingual performance on each task compared to a conventionally trained baseline.

Related

• Multi-Task Cross-Lingual Sequence Tagging from Scratch
• Robust Multilingual Part-of-Speech Tagging via Adversarial Training
• Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification
• Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks
• Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings