Evaluating Translational Correspondence using Annotation Projection

Thumbnail Image
Files
CS-TR-4455.ps(186.97 KB)
No. of downloads: 158
CS-TR-4455.pdf(210.65 KB)
No. of downloads: 642
Publication or External Link
Date
2003-04-04
Authors
Hwa, Rebecca
Resnik, Philip
Weinberg, Amy
Kolak, Okan
Advisor
Citation
DRUM DOI
Abstract
Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependencies. Underlying these models is an assumption about the directness of translational correspondence between sentences in the two languages; however, the extent to which this assumption is valid and useful is not well understood. In this paper, we present an empirical study that quantifies the degree to which syntactic dependencies are preserved when parses are projected directly from English to Chinese. Our results show that although the direct correspondence assumption is often too restrictive, a small set of principled, elementary linguistic transformations can boost the quality of the projected Chinese parses by 76\% relative to the unimproved baseline. UMIACS-TR-2003-25 LAMP-TR-100 ,
Notes
Rights