SEMANTIC DISAMBIGUATION WITH USING A LANGUAGE-INDEPENDENT SEMANTIC STRUCTURE

摘要

An unknown word is received by a computing device. A plurality of potential semantic classes to assign to the unknown word are determined using a processor. A classifier for the unknown word using a text corpora is built using the processor. Based at least in part on the built classifier, the unknown word is classified with at least one semantic class from the plurality of potential semantic classes. The unknown word is added to a semantic hierarchy as an instance of the at least one semantic class.