| Summary: | The object of text summarization is to cut down the extent of the text into a summary containing key data. Abstract methods are challenging tasks, it is necessary to devise a machine-processed to pick up the message from the text with advantage, and after that make a summary. However, most of the existing abstract approaches are difficult to capture global semantics, ignoring the impact of global information on obtaining important content. To solve this difficulty, this paper suggests a Graph-Based Topic Aware abstract Text Summarization (GTASum) framework. Specifically, GTASum seamlessly incorporates a neural topic model to find potential topic information, which can maintain document-level characteristics for generating summaries. In addition, the model integrates the graph neural network which can effectively capture the relationship between sentences through the document representation of graph structure, and simultaneously update the local and global information. The further discussion showed that latent topics can help the model capture salient content. We practiced experiments on two datasets, and the result shows that GTASum is superior to many extractive and abstract approaches in terms of ROUGE measurement. The result of the ablation study proves that the model has the ability to capture the original subject and the correct information and improve the factual accuracy of the summarization. © 2022, Kauno Technologijos Universitetas. All rights reserved.
|
|---|
