Kai Du
ABSTRACT
Abstract: In recent years, with the rapid development of network information technology, network text information also presents an explosive growth trend. As an efficient information processing technology in the digital age, text summarization can bring the advantage of focusing on key information in all directions in massive text information. However, text summarization is still faced with some problems such as difficulty in extracting long text and information redundancy. Therefore, combining with the deep learning framework, this paper proposes an extractive text summarization that uses reinforcement learning to optimize the long text extraction process and uses the attention mechanism to achieve the effect of redundancy removal. On CNN/Daily Mail datasets, the automatic evaluation shows that our model outperforms the previous on ROUGE, and the ablation experiment proves the effectiveness of the de-redundant attention module.
- Ming Zhong, Pengfei Liu, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang: Extractive Summarization as Text Matching. ACL 2020: 6197-6208.Google Scholar
- Baoyu Jing, Zeyu You, Tao Yang, Wei Fan, Hanghang Tong: Multiplex Graph Neural Network for Extractive Text Summarization. EMNLP (1) 2021: 133-139.Google Scholar
- Neto J L, Freitas A A, Kaestner C A A. Automatic text summarization using a machine learning approach[C]. Brazilian symposium on artificial intelligence, 2002: 205-215.Google Scholar
- Rush A M, Chopra S, Weston J. A Neural Attention Model for Abstractive Sentence Summarization[C]. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 379-389.Google Scholar
- Mihalcea R, Tarau P. Textrank: Bringing order into text[C]. Proceedings of the 2004 conference on empirical methods in natural language processing. 2004: 404-411.Google Scholar
- Cheng J, Lapata M. Neural summarization by extracting sentences and words[J]. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016.Google ScholarCross Ref
- Nallapati R, Zhai F, Zhou B. Summarunner: A recurrent neural network based sequence model for extractive summarization of documents[C]. Thirty-first AAAI conference on artificial intelligence. 2017.Google ScholarCross Ref
- Liu Y. Fine-tune BERT for extractive summarization[J]. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pages, 2019.Google Scholar
- NOVA E. STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings[J]. ACL 2019, 2019, 1(2): 243.Google Scholar
- Banerjee S, Mitra P, Sugiyama K. Multi-document abstractive summarization using ilp based multi-sentence compression[C]. Twenty-Fourth International Joint Conference on Artificial Intelligence. 2015.Google Scholar
- Liu H, Yu H, Deng Z H. Multi-document summarization based on two-level sparse representation model[C]. Twenty-ninth AAAI conference on artificial intelligence. 2015.Google ScholarDigital Library
- Yao K, Zhang L, Luo T, Deep reinforcement learning for extractive document summarization[J]. Neurocomputing, 2018, 284: 52-62.Google ScholarCross Ref
- West P, Holtzman A, Buys J, Bottlesum: Unsupervised and self-supervised sentence summarization using the information bottleneck principle[J]. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019.Google ScholarCross Ref
- Qingyu Zhou, Nan Yang, Furu Wei, Shaohan Huang, Ming Zhou, and Tiejun Zhao. Neural document summarization by jointly learning to score and select sentences[J]. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–663, Melbourne, Australia. Association for Computational Linguistics. 2018.Google ScholarCross Ref
- Zhou Q, Wei F, Zhou M. At which level should we extract? An empirical analysis on extractive document summarization[J]. Proceedings of the 28th International Conference on Computational Linguistics, 2020.Google ScholarCross Ref
- Vaswani A, Shazeer N, Parmar N, Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.Google Scholar
- See A, Liu P J, Manning C D. Get to the point: Summarization with pointer-generator networks[J]. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017.Google Scholar
- Celikyilmaz A, Bosselut A, He X, Deep communicating agents for abstractive summarization[J]. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018.Google ScholarCross Ref
- Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.Google Scholar
Index Terms
- An Extractive Text Summarization Based on Reinforcement Learning
Recommendations
RankSum—An unsupervised extractive text summarization based on rank fusion
AbstractIn this paper, we propose Ranksum, an approach for extractive text summarization of single documents based on the rank fusion of four multi-dimensional sentence features extracted for each sentence: topic information, semantic content, ...
Graphical abstractDisplay Omitted
Highlights- A unified summarization framework with multi-dimensional sentence features.
- ...
Multi-document Hyperedge-based Ranking for Text Summarization
CIKM '14: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge ManagementIn a multi-document settings, graph-based extractive summarization approaches build a similarity graph out of sentences in each cluster of documents then use graph centrality approaches to measure the importance of sentences. The similarity is computed ...
State-of-the-art approach to extractive text summarization: a comprehensive review
AbstractWith the rapid growth of social media platforms, digitization of official records, and digital publication of articles, books, magazines, and newspapers, lots of data are generated every day. This data is a foundation of information and contains a ...
Comments