@InProceedings{sasaki-EtAl:2018:N18-2,
  author    = {Sasaki, Shota  and  Sun, Shuo  and  Schamoni, Shigehiko  and  Duh, Kevin  and  Inui, Kentaro},
  title     = {Cross-Lingual Learning-to-Rank with Shared Representations},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {458--463},
  abstract  = {Cross-lingual information retrieval (CLIR) is a document retrieval task where the documents are written in a language different from that of the user's query. This is a challenging problem for data-driven approaches due to the general lack of labeled training data. We introduce a large-scale dataset derived from Wikipedia to support CLIR research in 25 languages. Further, we present a simple yet effective neural learning-to-rank model that shares representations across languages and reduces the data requirement. This model can exploit training data in, for example, Japanese-English CLIR to improve the results of Swahili-English CLIR.},
  url       = {http://www.aclweb.org/anthology/N18-2073}
}