proactive_learning_for_building_machine_translation_systems：主动学习机器翻译系统.pdf

Proactive Learning for Building Machine Translation Systems for Minority Languages Vamshi Ambati Jaime Carbonell vamshi@ jgc@ Language Technologies Institute Language Technologies Institute Carnegie Mellon University Carnegie Mellon University Pittsburgh, PA 15213, USA Pittsburgh, PA 15213, USA Abstract based MT systems require lexicons that provide cov- erage for the target translations, synchronous gram- Building machine translation (MT) for many mar rules that define the divergences in word-order minority languages in the world is a serious across the language-pair. In case of minority lan- challenge. For many minor languages there is guages one can only expect to find meagre amount little machine readable text, few knowledge- of such data, if any. Building such resources effec- able linguists, and little money available for MT development. For these reasons, it be- tively, within a constrained budget, and deploying an comes very important for an MT system to MT system is the need of the day. make best use of its resources, both labeled We first consider ‘Active Learning’ (AL) as a and unlabeled, in building a quality system. framework for building annotated data for the task In this paper we argue that trad