Colloquial word identification and semantic identification method and device

Abstract

The invention provides a colloquial word identification and semantic identification method and device. The colloquial word identification method includes the steps: acquiring first trained language model; extracting contextual features of words in statements to be identified; identifying the contextual features of words by the first trained language model; determining whether the words are colloquial words or not. The first language model learns the contextual features of the colloquial words in the statements in advance, the identification accuracy of colloquial words in ask questions are improved, the first language model is completed by training, the contextual features of the words in statements to be identified are extracted and identified, so that the method can determine whether thewords are the colloquial words or not, the identification efficiency and the identification accuracy of the colloquial words are improved, and the method solves the technical problems of more colloquial words in the ask questions of the user and low identification efficiency and identification accuracy in the prior art.

Description

technical field [0001] The invention relates to the technical field of intelligent responses, in particular to a spoken word recognition and semantic recognition method and device thereof. Background technique [0002] As an important scene of artificial intelligence, the general dialogue system has received more and more attention. The general dialogue system provides information services for users intelligently through human-computer interaction in a question-and-answer manner. In intelligent question and answer, people often use colloquial words in the questions that people say casually, and the dialogue system often makes it difficult to recognize because the questions contain colloquial words. As the proportion of voice in the input questions increases, Identifying colloquial words in asking questions becomes a practical problem. [0003] In the prior art, through a simple general spoken vocabulary, the words belonging to the spoken vocabulary in the question are ignor...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, through a simple general spoken vocabulary, the words belonging to the spoken vocabulary in the question are ignored, but the words in the general spoken vocabulary generally cannot recognize the rich spoken vocabulary, so that the spoken words in the question The words cannot be fully recognized, and the recognition accuracy is low

Images