We introduce two abstraction mechanisms for streamlining the process of semantic interpretation. Configurational

This paper presents a corpus-based method for extracting semantic relations between words. The method is based on two sequential procedures. First, it automatically classifies syntactic dependencies according to their selection restrictions. Those dependencies that require the same selection restrictions are put together into the same semantic group. Then, interpretation rules are applied on the classified syntactic dependencies, in order to learn the specific semantic relations underlying syntactically related words.

We introduce a framework for semantic interpretation in which dependency structures are mapped to conceptual representations based on a parsimonious set of interpretation schemata. Our focus is on the empirical evaluation of this approach to semantic interpretation, i.e., its quality in terms of recall and precision. Measurements are taken with respect to two real-world domains, viz. information technology test reports and medical finding reports, 1