Adversarial Neural Networks for Cross-lingual Sequence Tagging
This addresses the problem of token-level prediction in low-resource languages for NLP applications, but it is incremental as it extends prior adversarial methods from sentence-level to token-level tasks.
The paper tackles cross-lingual sequence tagging with limited labeled data in the target language, showing that adversarial training consistently improves performance on dependency parsing and sentence compression tasks compared to a baseline.
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.