Method and device for calculating semantic text similarity

The invention discloses a method and a device for calculating the semantic text similarity, relating to the technical field of natural language processing, and solving the problem of relatively low accuracy of an existing text similarity calculating method. The method comprises the following steps: combining a first word bag corresponding to first text and a second word bag corresponding to second text to obtain a dimensional word bag; vectorizing the first word bag and the second word bag according to a semantic-based word transformation vector tool to obtain a first vector and a second vector which have dimensions in one-to-one correspondence with words in the dimensional word bag; and calculating the similarity values of the first vector and the second vector according to a vector similarity calculation algorithm to obtain a similarity result of the first text and the second text. The method and the device are applied to a text similarity calculating process. 本发明公开了种文本语义相似度计算的方法及装置，涉及自然语言处理技术领域，解决了现有文本相似度计