Chinese word sense disambiguation method based on fusion of graph convolutional neural network and support vector machine

Abstract

The invention relates to a Chinese word sense disambiguation method based on a graph convolutional neural network (GCN) fused with a support vector machine (SVM), in particular to a Chinese word sense disambiguation method based on the graph convolutional neural network (GCN) fused with the support vector machine (SVM) and a Chinese word sense disambiguation method based on the graph convolutional neural network (GCN) fused with the Chinese word sense disambiguation method based on the graph convolutional neural network (GCN) fused with the support vector machine (SVM). The method comprises the steps of firstly preprocessing corpora; and performing word segmentation, part-of-speech tagging and semantic tagging processing on statements of the training and testing corpora. A word sense disambiguation graph is constructed by taking sentences where ambiguous words are located and word forms, part-of-speech and semantic classes of vocabulary units on two sides of the ambiguous words as disambiguation features and taking the disambiguation features as nodes. Weights of nodes and edges in the graph are calculated by using Word2Vec, a Doc2Vec tool, point-by-point mutual information (PMI) and a TF-IDF algorithm. And training the GCN model by the training corpus, and optimizing the model. And calculating disambiguation features of training and testing corpora by using the optimized GCN model, inputting the calculated disambiguation features of the training corpora into an SVM classifier, optimizing the SVM classifier, and classifying the testing corpora to obtain classification conditions of ambiguous vocabularies under semantic categories. The method has a good word sense disambiguation effect, and the real meaning of the ambiguous vocabulary is accurately judged.

Description

Technical field: [0001] The invention relates to a Chinese word sense disambiguation method based on a graph convolutional neural network fusion support vector machine, and the method can be well applied in the field of natural language processing. Background technique: [0002] When it comes to natural language processing, it often involves the phenomenon of polysemy in language, which affects natural language processing such as machine translation with text understanding capabilities, automatic summarization, question answering systems, public opinion analysis, machine writing, information retrieval, and text classification. field application. In order to make the above application fields have better accuracy or obtain results more in line with people's expectations. It is necessary to disambiguate words with multiple semantics, that is, word meaning disambiguation, and find out the true semantics of ambiguous words according to the specific language environment of the co...

AI Technical Summary

Problems solved by technology

[0004] In view of this, in order to solve the phenomenon of polysemy in Chinese in the field of natural language processing, the present invention discloses a Chinese word sense disambiguation method based on graph convolutional neural network fusion support vector machine

Images