@article {18928, title = {Breaking the resource bottleneck for multilingual parsing}, year = {2005}, month = {2005///}, institution = {Instititue for Advanced Computer Studies, Univ of Maryland, College Park}, abstract = {We propose a framework that enables the acquisition of annotation-heavy resources such as syntacfic dependency tree corpora for low-resource languages by importing linguistic annotations from high-quality English resources. We present a large-scale experiment showing that Chinese dependency trees can be induced by using an English parser, a word alignment package, and a large corpus of sentence-aligned bilingual text. As a part of the experiment, we evaluate the quality of a Chinese parser trained on the induced dependency treebank. We find that a parser trained in this manner out-performs some simple baselines inspite of the noise in the induced treebank. The results suggest that projecting syntactic structures from English is a viable option for acquiring annotated syntactic structures quickly and cheaply. We expect the quality of the induced treebank to improve when more sophisticated filtering and error-correction techniques are applied.}, url = {http://oai.dtic.mil/oai/oai?verb=getRecord\&metadataPrefix=html\&identifier=ADA440432}, author = {Hwa,R. and Resnik, Philip and Weinberg, Amy} }