Dear All, We are pleased to announce the release of our new Word-level Confidence Estimation (WCE) toolkit for Statistical Machine Translation.
This toolkit was made to be easy to use and more specifically to: - reproduce State-of-the-Art WCE evaluations within the framework of WMT Confidence Estimations shared tasks - simplify the feature processing needed in WCE for SMT which generally involves the call to many external toolkits and libraries - easily add new features or modify existing feature extractors - provide simple feature selection scripts It is now available on GitHub here: https://github.com/besacier/WCE-LIG and distributed under GPL V3. A more detailed description of the toolkit can be found in the following publication: Christophe Servan, Ngoc Tien Le, Ngoc Quang Luong, Benjamin Lecouteux and Laurent Besacier, "An Open Source Toolkit for Word-level Confidence Estimation in Machine Translation", in Proceedings of The 12th International Workshop on Spoken Language Translation (IWSLT 2015), Da Nang, Vietnam, Dec. 2015. Comments, bug reports, requests for extensions and contributions are welcome. Cheers, Christophe Servan, Ngoc Tien Le, Ngoc Quang Luong, Benjamin Lecouteux and Laurent Besacier GETALP - LIG Univ. Grenoble Alpes, France
_______________________________________________ Mt-list site list [email protected] http://lists.eamt.org/mailman/listinfo/mt-list
