Word sense disambiguation algorithms by artificial intelligence

The existence of words with the same spelling and different meanings in a sentence causes problems in understanding the meaning and machine translation of that sentence, and in special circumstances, in intelligent systems and semantic web applications and search engines, it is necessary to disambiguate these words. Word sense disambiguation is a core research problem in computational linguistics, which was recognized at the beginning of the scientific interest in machine translation and artificial intelligent .In the field of computational linguistics, the problem is generally called word sense disambiguation (WSD), and is defined as the problem of computationally determining which “sense” of a word is activated by the use of the word in a particular context. WSD is essentially a task of classification: word senses are the classes, the context provides the evidence, and each occurrence of a word is assigned to one or more of its possible classes based on the evidence. Words are assumed to have a finite and discrete set of senses from a dictionary, a lexical knowledge base, or an ontology (in the latter, senses correspond to concepts that a word lexicalizes). Application-specific inventories can also be used. For instance, in a machine translation (MT) setting, one can treat word translations as word senses, an approach that is becoming increasingly feasible because of the availability of large multi-lingual parallel corpora that can serve as training data. The fixed inventory of traditional WSD reduces the complexity of the problem and making it tractable.In this article, an innovative method is presented in order to resolve the semantic ambiguity of ambiguous words in a sentence. This method is based on using the knowledge available in the dictionary and using fuzzy logic, the ambiguous and non-ambiguous word or words of the sentence are identified and categorized by the dictionary. Then, in the next step, disambiguation of ambiguous words is done by having a suitable dictionary. Fuzzy logic is also used to increase accuracy in choosing the correct meaning of ambiguous word . The effectiveness of the proposed method has been evaluated using data collected from authoritative sources.

کلیدواژه ها:

natural language processing ، disambiguation ، artificial intelligence ، fuzzy logic.