Word vector generation method and device and electronic equipment

Abstract

The invention provides a word vector generation method and device and electronic equipment, and relates to the technical field of natural language processing. The method comprises the steps: obtaininga to-be-processed statement, and obtaining a target word in the to-be-processed statement; obtaining context information of the target word; determining a context-independent word vector corresponding to the target word according to a preset mapping relation between segmented words and word vectors; determining a context semantic vector corresponding to the context information according to a preset mapping relation between characters and word vectors; and generating a target word vector corresponding to the target word according to the context-independent word vector and the context semanticvector. Therefore, through the word vector generation method, the reliability and universality of natural language understanding are improved, and the calculation complexity of word vector generationis reduced.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to the field of natural language processing technology, and proposes a word vector generation method, device and electronic equipment. Background technique [0002] In the field of Natural Language Processing (NLP for short), a deep language model with contextual semantic expression ability usually has good language expression ability. For example, the Bidirectional Encoder Representation from Transformers (BERT) model from the converter uses the self-attention mechanism to fully interact and build a complete context, so that each word in the text can be based on the context. Different words have different semantics, which improves the reliability of natural language understanding by fusing the context of words. [0003] However, deep language models with contextual semantic expression capabilities often have complex network structures. For example, the BERT basic model...

AI Technical Summary

Problems solved by technology

[0004] The word vector generation method, device and electronic equipment proposed in this application are used to solve the problem of related technologies. Deep language models with contextual semantic expression capabilities often have complex network structure, the huge amount of parameters leads to a huge amount of calculation of the model, and the problem of long inference time

Images