Abstract—Word sense disambiguation is the process of determining which sense of a word is used in a given context. Due to its importance in understanding semantics and many real-world applications, word sense disambiguation has been extensively studied in Natural Language Processing and Computational Linguistics. However, existing methods either narrowly focus on a few specific words due to their reliance on expensive manually annotated training text, or give only mediocre performance in real-world settings. Broad coverage and disambiguation quality are critical for real-world natural language processing applications. In this paper we present a fully automatic disambiguation method that utilizes two readily available knowledge sources: a dictionary and knowledge extracted from unannotated text. Such an automatic approach overcomes the knowledge acquisition bottleneck and makes broad-coverage word sense disambiguation feasible in practice. Evaluated with two large scale WSD evaluation corpora, our system significantly outperforms the best unsupervised system and achieves the similar performance as the top-performing supervised systems.