@inproceedings{d88d0032fc2044e99bc802afa9af217a,
title = "Linguistic resources for handwriting recognition and translation evaluation",
abstract = "We describe efforts to create corpora to support development and evaluation of handwriting recognition and translation technology. LDC has developed a stable pipeline and infrastructures for collecting and annotating handwriting linguistic resources to support the evaluation of MADCAT and OpenHaRT. We collect handwritten samples of pre-processed Arabic and Chinese data that has been already translated in English that is used in the GALE program. To date, LDC has recruited more than 600 scribes and collected, annotated and released more than 225,000 handwriting images. Most linguistic resources created for these programs will be made available to the larger research community by publishing in LDC's catalog. The phase 1 MADCAT corpus is now available.",
keywords = "Handwriting image, Recognition, Translation",
author = "Zhiyi Song and Safa Ismael and Steven Grimes and David Doermann and Stephanie Strassel",
year = "2012",
language = "English",
series = "Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012",
publisher = "European Language Resources Association (ELRA)",
pages = "3951--3955",
editor = "Dogan, \{Mehmet Ugur\} and Joseph Mariani and Asuncion Moreno and Sara Goggi and Khalid Choukri and Nicoletta Calzolari and Jan Odijk and Thierry Declerck and Bente Maegaard and Stelios Piperidis and Helene Mazo and Olivier Hamon",
booktitle = "Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012",
note = "8th International Conference on Language Resources and Evaluation, LREC 2012 ; Conference date: 21-05-2012 Through 27-05-2012",
}