Semantic recognition model training method and device based on comparative learning and medium

Abstract

The invention relates to the technical field of deep learning, and provides a semantic recognition model training method and device based on comparative learning and a medium, and the method comprises the steps: carrying out the synonym replacement of each first target vocabulary in an original sentence text, and obtaining a first processed sentence text; carrying out antonym replacement on each second target vocabulary in the original sentence text to obtain a second processed sentence text; and training an initial semantic recognition model through the original sentence text, the first processed sentence text and the second processed sentence text to obtain a target semantic recognition model. The objective of the embodiment of the invention is to provide a comparative learning method capable of identifying small semantic changes, and the problem that positive and negative samples are well distinguished in the prior art is improved, so that the model can learn richer knowledge, and the model training effect is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a method, system, electronic device and computer-readable storage medium for training a semantic recognition model based on contrastive learning. Background technique [0002] Contrastive Learning is a commonly used self-supervised learning method. The core idea is to reduce the distance from positive samples, expand the distance from negative samples, and learn data sets without labels by training the model which data points are similar or different. general characteristics. [0003] However, when applying contrastive learning to a semantic recognition model to train a semantic recognition model to distinguish between semantically similar or different text sentences, many difficulties are encountered. The main difficulties are: First, the negative sample pairs of text contrastive learning are relatively easy Recognition, the semantic difference of...

AI Technical Summary

Problems solved by technology

[0003] However, when applying contrastive learning to the semantic recognition model to train the semantic recognition model to distinguish text sentences with similar or different semantics, there are many difficulties encountered. The main difficulties are: first, the negative sample pairs of text contrastive learning are relatively easy Recognition, the semantic differences of different text representations are relatively large, and negative sample pairs can be distinguished only by the length of the text; secondly, false positive examples may appear in the process of constructing positive sample pairs through data enhancement, because one or more of the text is often changed The meaning of the word may change

Based on the above, the effect of training sentence-level semantic recognition models through comparative learning is not good

Images