Unsupervised method of word sense disambiguation for real time associated word identification in human-robot interaction

This paper presents a system architecture and algorithm for the disambiguation problem in human-robot interaction. Currently, when we have a communication with robot, there are ambiguity problems which lead to a misunderstanding. Conventional methods only identify ambiguity in limited ways and in few contexts due to the cost of doing so. The proposed method using real Hangul input object (RHINO) cloud identifies ambiguous words, phrases and sentences in many contexts and suggests appropriate alternatives. And by calculating the frequency of an ambiguous word, an associated word and the theme we can obtain the associated strength. The theme which has the biggest strength is the meaning of the ambiguous word. This process reflects the fluctuation of associated words' social cultures because it searches words in real time.