This paper outlines a measure of language similarity based on structural similarity of surface syntactic dependency trees. Unlike the more traditional string-based measures, this measure tries to reflect “deeper” correspondences among languages. The development of this measure has been inspired by the experience from MT of syntactically similar languages. This experience shows that the lexical ...

There is general agreement that structural similarity — a match in relational structure — is crucial in analogical processing. However, theories differ in their definitions of structural similarity: in particular, in whether there must be conceptual similarity between the relations in the two domains or whether parallel graph structure is sufficient. In two studies, we demonstrate, first, that ...

Many different measures of structural similarity have been suggested for matching chemical structures, each such measure focusing upon some particular type of molecular characteristic. The multi-faceted nature of biological activity suggests that an appropriate similarity measure should encompass many different types of characteristic, and this paper discusses the use of data fusion methods to ...

How language represents meaning remains a central topic of debate in linguistics. On some accounts, the noun phrases in a sentence are identified semantically by a list of independent atomic labels (thematic roles), ordered relative to one another depending on the position of the nouns around the verb (e.g., AGENT-THEME-GOAL). Others instead capture such interdependencies with complex, non-atom...

We present a corpus of experimental data from psychometric studies on gamut mapping and demonstrate its use to develop image similarity measures. We investigate whether similarity measures based on luminance (SSIM) can be improved when features based on chroma and hue are added. Image similarity measures can be applied to automatically select a good image from a sample of transformed images.