Estimating the conceptual distance between unknown words using machine learning
Yuya Sakai, Mitsuharu Matsumoto · 2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · 2022
Measuring the distance between words has many applications in natural language processing. By using the conceptual distance using the thesaurus dictionary, it is possible to obtain a distance scale different from the word similarity using the cosine similarity. However, the distance cannot be measured except for the words listed in the thesaurus dictionary. To solve the problem, this study aims to estimate the conceptual distance between unknown words using machine learning. Through some experiments, the conceptual distance of an unknown word could be estimated with the same level of accuracy as that of a known word.