International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 176 - Number 4 |
Year of Publication: 2017 |
Authors: Ketakee Nimavat, Tushar Champaneria |
10.5120/ijca2017915572 |
Ketakee Nimavat, Tushar Champaneria . Estimation of Lexical Complexity using Language Semantics. International Journal of Computer Applications. 176, 4 ( Oct 2017), 24-28. DOI=10.5120/ijca2017915572
Word complexity is a quite complex and subjective issue. However, it is also intuitive. Here the topic is explored and an intuitive method is proposed to judge the complexity where the intuition is based on the genesis and development of a language. The proposed technique is analogous to a tree structure where in each word is made up of its child nodes where child nodes signify simpler words. The algorithm hence takes into account the definition of the word and finds the complexity score based on the basic words present in the definition. The method is then judged using Flesch Reading ease and tested on separate sets of simple and difficult words. It is observed that this helps judge the complexity of a text as whole and works fairly well for individual words as well.