@InProceedings{aghaebrahimian:2018:C18-1,
  author    = {Aghaebrahimian, Ahmad},
  title     = {Deep Neural Networks at the Service of Multilingual Parallel Sentence Extraction},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  month     = {August},
  year      = {2018},
  address   = {Santa Fe, New Mexico, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {1372--1383},
  abstract  = {Wikipedia provides an invaluable source of parallel multilingual data, which are in high demand for various sorts of linguistic inquiry, including both theoretical and practical studies. We introduce a novel end-to-end neural model for large-scale parallel data harvesting from Wikipedia. Our model is language-independent, robust, and highly scalable. We use our system for collecting parallel German-English, French-English and Persian-English sentences. Human evaluations at the end show the strong performance of this model in collecting high-quality parallel data. We also propose a statistical framework which extends the results of our human evaluation to other language pairs. Our model also obtained a state-of-the-art result on the German-English dataset of BUCC 2017 shared task on parallel sentence extraction from comparable corpora.},
  url       = {http://www.aclweb.org/anthology/C18-1116}
}