Show simple item record

Evaluating Translational Correspondence using Annotation Projection

dc.contributor.authorHwa, Rebeccaen_US
dc.contributor.authorResnik, Philipen_US
dc.contributor.authorWeinberg, Amyen_US
dc.contributor.authorKolak, Okanen_US
dc.description.abstractRecently, 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 ,en_US
dc.format.extent191455 bytes
dc.relation.ispartofseriesUM Computer Science Department; CS-TR-4455en_US
dc.relation.ispartofseriesUMIACS; UMIACS-TR-2003-25en_US
dc.titleEvaluating Translational Correspondence using Annotation Projectionen_US
dc.typeTechnical Reporten_US
dc.relation.isAvailableAtDigital Repository at the University of Marylanden_US
dc.relation.isAvailableAtUniversity of Maryland (College Park, Md.)en_US
dc.relation.isAvailableAtTech Reports in Computer Science and Engineeringen_US
dc.relation.isAvailableAtUMIACS Technical Reportsen_US

Files in this item


This item appears in the following Collection(s)

Show simple item record