|
|
 |
| |
|
|
|
Modeling Lexical Ambiguity in English Literature Using Fuzzy Logic and Equations |
|
|
|
PP: 873-889 |
|
|
|
doi:10.18576/amis/190413
|
|
|
|
Author(s) |
|
|
|
N. Yogeesh,
Suleiman Ibrahim Mohammad,
N. Raja,
N. Aravinda Reddy,
S. Rayeesul Hassan,
H. S. Kavitha,
Asokan Vasudevan,
Mohammad Faleh Ahmmad Hunitie,
Nawaf Alshdaifat,
|
|
|
|
Abstract |
|
|
| Lexical ambiguity is an essential problem in literary analysis and natural language processing(NLP) because many words have multiple meanings that are determined by how the words are used in context. The ambiguity is a challengingdilemma for traditional linguistic and computational methods and algorithms, especially in the case of literature, where polysemy, homonymy, and vagueness in context are the typical tools used by the authors to add depth to the meaning. It is from this standpoint that the present paper introduces a fuzzy logic-based model for lexical ambiguity resolution, effectively an integrated application of fuzzy entropy, fuzzy clustering, and defuzzification methods to systematically rank and interpretword meanings in various contexts. By employing a case study for uncertain words like light, cold, sharp, bright, and deep, the research illustrates theapplicability of fuzzy entropy for quantifying uncertainty, and defuzzification for identifying frequently taken meaning that matches human sense-making. Higher entropy valuesare characteristic of more ambiguous words, whereas lower entropy relates to more well-defined meaning. Fuzzy clustering also allows for a semantic grouping of words that can be applied to computational literary analysis and automated textclassification. In AI and NLP, the significant applications of fuzzy logic are in the fields of machinetranslation, sentiment analysis, chatbots, and AI in literature. Closing the gaps of mathematical modelling and linguistic analysis,this research provides a heuristic quantitative framework for firmness resolution, opening new steps for hybrid AI-fuzzy models, multilingual ambiguity analysis, and mathematical modelling of literary structures. The results confirm fuzzy logic’s potential as a method for lexical ambiguity resolution, one that facilitates not just rapid computational text analysis, but also nuancedliterary reading.
|
|
|
|
|
|
|
|
