MELB-MKB: Lexical substitution system based on relatives in context

Abstract

In this paper we describe the MELB-MKB system, as entered in the SemEval-2007 lexical substitution task. The core of our system was the "Relatives in Context" unsupervised approach, which ranked the candidate substitutes by web-lookup of the word sequences built combining the target context and each substitute. Our system ranked third in the final evaluation, performing close to the top-ranked system.