의미 변화의 양적 추정 - 말뭉치를 이용한 의미 변화 연구 -

Abstract

This study introduces methods that can objectively and scientifically capture and describe changes in meaning using corpus data through studies applying statistical methods that have been conducted recently. For statistical inference on the change in meaning, historically recorded data must be quantified and used through a specific calculation method. A representative method of numerically analyzing language data is to use the Semantic Vector Space(SVM), which is also commonly used in the language data analysis method that has been very active in recent years. Recently, a great progress has been made in capturing and explaining semantic changes using these methods. Quantitative estimation of semantic change using computational statistics is based on frequency-based, similarity-based, and network-based methods depending on the representation of meaning can be divided into. The difference between the use of meaning in the present and the use of meaning in the past can be confirmed by comparing the context similarity of the text. If there is a large change in usage compared to the present, the context similarity will be lower, and if there is no change, the context similarity will be high. In order to grasp a detailed and specific change in meaning, a method of comparing a list of key expressions or words that well reveals the meaning of the context can be used by calculating the similarity between expressions or words in the corpus by period. Meaning expansion and reduction, which are representative results of meaning change, can be grasped by measuring the change in the scope of use, and the rise and fall of meaning can be grasped through sentiment analysis. By statistically analyzing the historical corpus in this way, it is possible to statistically grasp the historical changes in the meaning of the Korean language, and suggest implications on how to identify and analyze the change in language meaning.