A text representation method and device based on a hierarchical neural network

Abstract

The invention discloses a text representation method and device based on a hierarchical neural network. The method comprises: converting each word forming a sentence into a vector; Inputting vectors corresponding to all words in the sentence into a neural network for aggregation, and outputting sentence representation corresponding to the sentence; Inputting all the sentence representations into aneural network to be aggregated, and generating document representations corresponding to all the sentence representations; And converting the document representation into a document classification vector through a full connection network, and obtaining prediction probability distribution of document classification based on the document classification vector. According to the method and a device,A hierarchical mechanism is introduced into a neural network model to solve a document representation problem for text classification; Interoperability of different tasks is better improved, a hierarchical neural system structure is fused into a neural network method, a new neural network model based on layering is caused, accuracy, performance and the like are obviously superior to those of an existing neural network model, and consumption is lower.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a text representation method and device based on a layered neural network. Background technique [0002] The learning of text representation is a challenging task for natural language processing (NLP). Transforming the text space into real-valued vectors or matrices is the key to machine understanding of text semantics. For the text generation framework (for words to generate sentences and sentences to generate text), the text representation can be divided into the following levels, word representation, phrase representation, sentence representation and document-level representation. Document representation has broad application prospects, such as sentiment classification, text retrieval, text sorting, etc. The usual text representation methods are bag-of-words model BoW with inverse text frequency TF-IDF and N-gram model N-gram. However, this statistics...

AI Technical Summary

Problems solved by technology

However, the existing text representation models are based on neural networks trained according to specific tasks, ignoring the internal structural characteristics of the text itself.

Images