@InProceedings{mei-EtAl:2018:S18-2,
  author    = {Mei, Hongyuan  and  Zhang, Sheng  and  Duh, Kevin  and  Van Durme, Benjamin},
  title     = {Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction},
  booktitle = {Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {142--147},
  abstract  = {Cross-lingual information extraction (CLIE) is an important and challenging task, especially in low resource scenarios. To tackle this challenge, we propose a training method, called {\em Halo}, which enforces the local region of each hidden state of a neural model to only generate target tokens with the same semantic structure tag. This simple but powerful technique enables a neural model to learn semantics-aware representations that are robust to noise, without introducing any extra parameter, thus yielding better generalization in both high and low resource settings.},
  url       = {http://www.aclweb.org/anthology/S18-2017}
}