Enhanced and Portable Dependency Projection Algorithms Using Interlinear Glossed Text
Ryan Georgi, Fei Xia and William D. Lewis
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013
As most of the world's languages are under-resourced, projection algorithms offer an enticing way to bootstrap the resources available for one resource-poor language from a resource-rich language by means of parallel text and word alignment. These algorithms, however, make the strong assumption that the language pairs share common and that the parse trees will resemble one another. This assumption is useful but often leads to mistakes in projection. In this paper, we will address this shortcoming by using trees created from instances of Interlinear Glossed Text (IGT) and then hand-corrected to discover patterns of divergence between the languages. We will show that this method improves the performance of projection algorithms significantly in some languages by accounting for divergence between languages using only the partial supervision of the few corrected trees.
Conference Manager (V2.61.0 - Rev. 2792M)