Word Sense Disambiguation Using Association Rules: A Survey

Word sense disambiguation (WSD) is defined as the task of assigning the appropriate meaning (sense) to a given word in a text or discourse. The sense in which the word is used can be determined, most of the times, by the context in which the word occurs. Word sense ambiguity is a central problem for many established Human Language Technology applications (e.g., machine translation, information extraction, question answering, information retrieval, text classification, and text summarization). The context of an ambiguous word is regarded as a transaction record, the words in the context and the senses of the ambiguous word are regarded as items. If some items frequently occur together in some transactions (the context of the ambiguous word), then there must be some correlation between the items. The basic idea of the WSD algorithm based on mining association rules is: to discover the frequent item sets composed of the sense of the ambiguous word and its context by scanning its context database, which support degree is no less than the threshold of support degree; to produce the association rules X=>Y which confidence degree is no less than the threshold of the confidence degree from maximum frequent item sets; at last to determine