Text abstract generation method based on feature extraction and semantic enhancement

Abstract

The invention discloses a text abstract generation method based on feature extraction and semantic enhancement, and the method comprises the following steps: introducing a feature extractor, and obtaining a feature vector of an original text through the feature extractor; respectively connecting the feature vector with an output result of the encoder in a partial connection mode and a full connection mode, and filtering noise; acquiring long-distance dependence in the sentence by using a semantic enhancer, and further enhancing semantic association; using a convolutional neural network for carrying out feature extraction on a source sequence, enabling a feature extractor to directly act on a word vector of the source sequence, and meanwhile, keeping word vector layer parameters the same asword vector layer parameters of an encoder, so that the encoding process of the encoder and the feature extraction process of the feature extractor are ensured to act on the same semantic level. According to the method, the features of the sentence are extracted by using the feature extractor and then are further fused with the result of the encoder, so that the overall structure analysis of thesentence is facilitated, the noise in the text can be filtered, and the key information is found.

Description

technical field [0001] The invention relates to a method for generating a text abstract, in particular to a method for generating a text abstract based on feature extraction and semantic enhancement. Background technique [0002] Automatic text summarization is one of the main research tasks in the field of Natural Language Processing (NLP), which refers to compressing a relatively long article into a relatively short version containing the main content of the article. According to the way of implementation, automatic text summarization can be divided into two types: extractive and abstractive. Extractive text summarization is to directly select sentences that can express the key content of the article as a summary from the original text, while generative text summarization is to express the content of the original text by generating new sentences that have not appeared in the article. It can be seen that generative text summarization has higher requirements on the model an...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the common repetition problem of sequence-to-sequence models in the prior art, and also taking into account the problem of key information loss or capture errors in the generated text summaries, the present invention The problem to be solved is to provide a text summarization method based on feature extraction and semantic enhancement that is close to human writing

Images