Abstract
Problem statement: This study attempts to present an object-net method for word sense disambiguation. It is proposed to model the elementary meanings which assist the machine to autonomously undertake the analysis and synthesis processes of meaning. Approach: In the proposed methodology, the disambiguation process was performed in context manner. Starting from natural text, the context of the sentence was identified, then the actual meaning identified using correlation of elementary object meanings existed in object-net database. It was because even ambiguous word will have only one meaning based on the context or object or domain on which the sentence was written. Results: This object-net approach disambiguates original text with high precision of 96% of the verbs and 97% of nouns for data extraction from the database and reporting in terms of graphs. Conclusion: The accuracy of finding the sense of a word and extracting data from the database and projecting into graphs was based on number of trained objects in object-net database. Due to this object-net database plays a major role in this proposed method.
Highlights
A body of knowledge does not exist in a computerreadable format, outside of very limited domains
Word Sense Disambiguation (WSD) is the process of identifying which sense of a meaning is used in any given sentence, when the word has a number of distinct senses (Carpuat and Wu, 2005)
Shallow approaches: These approaches are not concerned of learning the text instead they deal with the surrounding words of the ambiguous word and try to
Summary
A body of knowledge does not exist in a computerreadable format, outside of very limited domains. For a long time the WSD is an open problem in natural language processing (NLP). The solution of this problem impacts other tasks such as discourse, engines, anaphora resolution, coherence, inference, information retrieval, machine translation and others. Is a long tradition in computational linguistics (Abney, 2004), of trying such approaches in terms of coded knowledge and in some cases; it is hard to say clearly whether the knowledge involved is linguistic or world knowledge. There are two main types of approach for WSD in natural language processing called as deep approaches and shallow approaches. Shallow approaches: These approaches are not concerned of learning the text instead they deal with the surrounding words of the ambiguous word and try to
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
