Semantic question-answering method and device, electronic equipment and storage medium

Abstract

The invention discloses a semantic question-answering method. The semantic question-answering method comprises the steps of creating an inverted sorting index library corresponding to preset questiondata in a question library; generating question pair sample data by utilizing the inverted sorting index library, and converting the question pair sample data into a character coding sequence; determining a loss function of a neural network model according to the character coding sequence and a part-of-speech coding sequence; determining a preset question vector corresponding to the preset question data by using the neural network model; determining a set of candidate question data similar to user question data in the question library according to the inverted sorting index library; calculating text vector similarity between the user question data and the candidate question data; and setting the candidate question data with the highest vector similarity as target question data, and outputting preset answer data corresponding to the target question data. According to the invention, the semantic question-answering accuracy can be improved. The invention further discloses a semantic question-answering device, electronic equipment and a storage medium, and the device has the above beneficial effects.

Description

technical field [0001] The present application relates to the technical field of pattern recognition and machine learning, in particular to a method and device for semantic question answering, an electronic device and a storage medium. Background technique [0002] With the vigorous development of artificial intelligence technology, neural network models have achieved great success in question answering tasks. The continuous innovation of question answering technology has prompted this technology to receive extensive attention in the fields of information retrieval, text matching, and search-based dialogue. [0003] Question answering algorithms can generally be divided into generative-based methods and retrieval-based methods. Generative-based methods aim to learn the connections between question-answer pairs from large-scale corpora, and use the above information to predict the following content. Retrieval-based methods aim to learn the correlation between texts and retr...

AI Technical Summary

Problems solved by technology

However, in the transfer learning process of the above question-answering algorithm, there are problems such as obvious differences in text semantic representation, poor text semantic recognition ability in professional fields, and underfitting of small data sample sets in deep models.

Images