@InProceedings{gaspers-karanasou-chatterjee:2018:N18-3,
  author    = {Gaspers, Judith  and  Karanasou, Penny  and  Chatterjee, Rajen},
  title     = {Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans - Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {137--144},
  abstract  = {This paper investigates the use of Machine Translation (MT) to bootstrap a Natural Language Understanding (NLU) system for a new language for the use case of a large-scale voice-controlled device. The goal is to decrease the cost and time needed to get an annotated corpus for the new language, while still having a large enough coverage of user requests. Different methods of filtering MT data in order to keep utterances that improve NLU performance and language-specific post-processing methods are investigated. These methods are tested in a large-scale NLU task with translating around 10 millions training utterances from English to German. The results show a large improvement for using MT data over a grammar-based and over an in-house data collection baseline, while reducing the manual effort greatly. Both filtering and post-processing approaches improve results further.},
  url       = {http://www.aclweb.org/anthology/N18-3017}
}