Abstract
Many applications in natural language processing require semantic relatedness between words to be quantified. Existing WordNet-based approaches fail in the case of non-dictionary words, jargons, or some proper nouns. Meaning of terms evolves over the years which have not been reflected in WordNet. However, WordNet cannot be ignored as it considers the semantics of the language along with its contextual meaning. Hence, we propose a method which uses data from Wikipedia and WordNet’s Brown corpus to calculate semantic relatedness using modified form of Normalized Google Distance (NGD). NGD incorporates word sense derived from WordNet and occurrence over the data from Wikipedia. Through experiments, we performed on a set of selected word pairs, and we found that the proposed method calculates relatedness that significantly correlates human intuition.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
