Context awareness-based fine-grained emotion classification method of hybrid neural network

Abstract

The invention discloses a context awareness-based fine-grained emotion classification method for a hybrid neural network, and the method comprises the steps of introducing a context vector into a word-level attention mechanism through employing a bidirectional Bi-LSTM during the coding of a word in each clause; on the clause level, using a convolution layer to extract local features from clauses,gathering all the local features through maximum pool operation, and obtaining a sentence vector with a fixed size; and inputting the sentence vector into a softmax classifier for classification to obtain a label with the highest probability to represent the predicted aspect sentiment polarity. According to the fine-grained emotion classification method of the hybrid neural network based on context awareness, context vectors are introduced into a word-level attention mechanism, so that the representation of each obtained clause vector fully considers context information. According to the invention, the convolutional neural network is used at the clause level to achieve the same function, but the calculation cost is greatly reduced.

Description

technical field [0001] The invention belongs to the technical field of language processing, and in particular relates to a fine-grained emotion classification method based on a context-aware hybrid neural network. Background technique [0002] In recent years, sentiment classification has attracted more and more attention from researchers in the fields of natural language processing and data mining due to its inherent challenges and wide application. Aspect sentiment classification is a finer-grained sentiment classification task. Given a sentence and certain aspects appearing in the sentence, its purpose is to analyze the sentiment polarity (positive, neutral, negative). For example, the sentence: "The clothes are beautiful, but the price is too high", the sentiment polarity is "positive" for "clothes", and "negative" for "price". It can be seen that analyzing the same sentence from different aspects may have different emotional polarities. [0003] Aspect sentiment clas...

AI Technical Summary

Problems solved by technology

[0007] State-of-the-art attention mechanisms for specific aspects at the word level, when multiple Bi-LSTMs are used to encode all clauses at the same time, each clause is encoded independently without considering contextual information

In addition, the attention mechanism for specific aspects at the clause level uses the same method as the attention mechanism for specific aspects at the word level. Bi-LSTM is used to encode words and clauses separately. Due to the large number of parameters of Bi-LSTM, the structure is complex , so the computational cost is high

Images