Method for establishing word vector improved model based on semantic embedding

Abstract

The invention discloses a method for establishing word vector improved model based on semantic embedding. The method comprises the following steps: 1) a bidirectional long-short-term memory network training stage; 2) a context vector calculation stage: inputting a sentence and a target word t into the bidirectional long-short-term memory network trained in the step 1) to obtain a context vector; 3) a context vector semantic clustering stage: a, calculating the current context vector and the similarity of each semantic cluster center of the word t by using cosine similarity; b, calculating theprobability P of the class cluster to which the current context vector belongs by using a Bayesian non-parametric statistical model; c, maximizing a P value and solving a class cluster corresponding to the value; c, offsetting the class cluster center to which the current context vector belongs. According to the method, the neural network and the Bayesian non-parametric statistical method are utilized to solve the problem that a current word vector model cannot solve the problem that one word has multiple meanings.

Description

technical field [0001] The invention relates to an improved method for establishing a word vector model. The model established by the method solves multiple semantic problems that the currently used word vector model cannot represent polysemous words. Background technique [0002] At present, the Internet has become an important way for people to obtain and distribute information. The information on the network platform often contains huge value. How to extract valuable content from the massive text information is one of the key issues of computer science. The development of deep learning technology has improved the ability of computers to process data and also promoted the development of natural language learning. When using deep learning for natural language processing, an indispensable process is the vectorized representation of words. In terms of word representation, the most widely used word2vec word vector model. The model has two structures, Skip-Gram and CBOW. The...

AI Technical Summary

Problems solved by technology

When people read, their judgment on the semantics of polysemous words depends on their own knowledge reserve and reasoning ability, but for machines, it is difficult to distinguish the meanings represented by polysemous words in specific contexts

Images