One of the main challenges in the applica- tions (i.e.: text summarization, question an- swering, information retrieval, etc.) of Natural Language Processing is to deter- mine which of the several senses of a word is used in a given context. The problem is phrased as “Word Sense Disambiguation (WSD)” in the NLP community. This paper presents the dictionary based disambigua- tion technique that adopts the assumption of one sense per discourse in the context of SemEval-2007 Task 7: “Coarse-grained English all-words”.