摘要：In this paper, a finite state machine approach is followed in order to find the semantic similarity of two sentences. The approach exploits the concept of bi-directional logic along with a semantic ordering approach. The core part of this approach is bi-directional logic of artificial intelligence. The bi-directional logic is implemented using Finite State Machine algorithm with slight modification. For finding the semantic similarity, keyword has played climactic importance. With the help of the keyword approach, it can be found easily at the sentence level according to this algorithm. The algorithm is proposed especially for Nepali texts. With the polarity of the individual keywords, the finite state machine is made and its final state determines its polarity. If two sentences are negatively polarized, they are said to be coherent, otherwise not. Similarly, if two sentences are of a positive nature, they are said to be coherence. For measuring the coherence (similarity), contextual concept is taken into consideration. The semantic approach, in this research, is a totally contextual based method. Two sentences are said to be semantically similar if they bear the same context. The total accuracy obtained in this algorithm is 90.16%.
关键词：Artificial Intelligence; Natural Language Processing; Text Mining; Semantic Similarity; Finite State Machine
