English

Adversarial Neural Networks for Cross-lingual Sequence Tagging

Computation and Language 2018-08-15 v1

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T03:33:33.277Z