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.
@article{arxiv.1808.04736,
title = {Adversarial Neural Networks for Cross-lingual Sequence Tagging},
author = {Heike Adel and Anton Bryl and David Weiss and Aliaksei Severyn},
journal= {arXiv preprint arXiv:1808.04736},
year = {2018}
}