A hybrid approach for text summarization using semantic latent Dirichlet allocation and sentence concept mapping with transformer
Open Access
- 1 December 2023
- journal article
- research article
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (6) , 6663-6672
Abstract
Automatic text summarization generates a summary that contains sentences reflecting the essential and relevant information of the original documents. Extractive summarization requires semantic understanding, while abstractive summarization requires a better intermediate text representation. This paper proposes a hybrid approach for generating text summaries that combine extractive and abstractive methods. To improve the semantic understanding of the model, we propose two novel extractive methods: semantic latent Dirichlet allocation (semantic LDA) and sentence concept mapping. We then generate an intermediate summary by applying our proposed sentence ranking algorithm over the sentence concept mapping. This intermediate summary is input to a transformer-based abstractive model fine-tuned with a multi-head attention mechanism. Our experimental results demonstrate that the proposed hybrid model generates coherent summaries using the intermediate extractive summary covering semantics. As we increase the concepts and number of words in the summary the rouge scores are improved for precision and F1 scores in our proposed model.Keywords
This publication has 27 references indexed in Scilit:
- Lattice abstraction-based content summarization using baseline abstractive lexical chaining progressInternational Journal of Information Technology, 2022
- Two-Phase Multidocument Summarization Through Content-Attention-Based Subtopic DetectionIEEE Transactions on Computational Social Systems, 2021
- T-BERTSum: Topic-Aware Text Summarization Based on BERTIEEE Transactions on Computational Social Systems, 2021
- Automatic text summarization: A comprehensive surveyExpert Systems with Applications, 2021
- Extractive summarization using supervised and unsupervised learningExpert Systems with Applications, 2019
- Deep Learning Based Extractive Text Summarization: Approaches, Datasets and Evaluation Measures2019
- Extractive summarization of documents with images based on multi-modal RNNFuture Generation Computer Systems, 2019
- A hybrid approach for automatic document summarization2017
- Multiview Convolutional Neural Networks for Multidocument Extractive SummarizationIEEE Transactions on Cybernetics, 2016
- A survey on abstractive text summarization2016