{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T14:03:49Z","timestamp":1768745029829,"version":"3.49.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T00:00:00Z","timestamp":1633132800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T00:00:00Z","timestamp":1633132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12171065 and 11671001"],"award-info":[{"award-number":["12171065 and 11671001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2022,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Existing text summarization methods mainly rely on the mapping between manually labeled standard summaries and the original text for feature extraction, often ignoring the internal structure and semantic feature information of the original document. Therefore, the text summary extracted by the existing model has the problems of grammatical structure errors and semantic deviation from the original text. This paper attempts to enhance the model\u2019s attention to the inherent feature information of the source text so that the model can more accurately identify the grammatical structure and semantic information of the document. Therefore, this paper proposes a model based on the multi-head self-attention mechanism and the soft attention mechanism. By introducing an improved multi-head self-attention mechanism in the model coding stage, the training model enables the correct summary syntax and semantic information to obtain higher weight, thereby making the generated summary more coherent and accurate. At the same time, the pointer network model is adopted, and the coverage mechanism is improved to solve out-of-vocabulary and repetitive problems when generating abstracts. This article uses CNN\/DailyMail dataset to verify the model proposed in this article and uses the ROUGE indicator to evaluate the model. The experimental results show that the model in this article improves the quality of the generated summary compared with other models.<\/jats:p>","DOI":"10.1007\/s40747-021-00527-2","type":"journal-article","created":{"date-parts":[[2021,10,4]],"date-time":"2021-10-04T14:17:18Z","timestamp":1633357038000},"page":"555-567","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Text summarization based on multi-head self-attention mechanism and pointer network"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4088-5371","authenticated-orcid":false,"given":"Dong","family":"Qiu","sequence":"first","affiliation":[]},{"given":"Bing","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,2]]},"reference":[{"issue":"4","key":"527_CR1","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1162\/089120102762671954","volume":"28","author":"HG Silber","year":"2002","unstructured":"Silber HG, McCoy KF (2002) Efficiently computed lexical chains as an intermediate representation for automatic text summarization. Comput Linguist 28(4):487\u2013496","journal-title":"Comput Linguist"},{"issue":"7","key":"527_CR2","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1109\/TCSVT.2018.2860797","volume":"29","author":"J Lei","year":"2019","unstructured":"Lei J, Luan Q, Song X et al (2019) Action Parsing-Driven Video Summarization Based on Reinforcement Learning. IEEE Trans Circuits Syst Video Technol 29(7):2126\u20132137","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"3","key":"527_CR3","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1109\/TMM.2003.813274","volume":"5","author":"C Hori","year":"2013","unstructured":"Hori C, Furui S (2013) A new approach to automatic speech summarization. IEEE Trans Multimedia 5(3):368\u2013378","journal-title":"IEEE Trans Multimedia"},{"issue":"6","key":"527_CR4","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1109\/TASLP.2016.2541299","volume":"24","author":"F Raposo","year":"2016","unstructured":"Raposo F, Ribeiro R, de Matos DM (2016) Using generic summarization to improve music information retrieval tasks. IEEE\/ACM Trans Audio Speech Lang Process 24(6):1119\u20131128","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"4","key":"527_CR5","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1109\/TSE.2013.2297712","volume":"40","author":"S Rastkar","year":"2014","unstructured":"Rastkar S, Murphy GC, Murray G (2014) Automatic summarization of bug reports. IEEE Trans Software Eng 40(4):366\u2013380","journal-title":"IEEE Trans Software Eng"},{"issue":"6","key":"527_CR6","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1109\/TASLP.2015.2414820","volume":"23","author":"SH Liu","year":"2015","unstructured":"Liu SH, Chen KY, Chen B et al (2015) Combining relevance language modeling and clarity measure for extractive speech summarization. IEEE\/ACM Trans Audio Speech Lang Process 23(6):957\u2013969","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"6","key":"527_CR7","doi-asserted-by":"publisher","first-page":"102341","DOI":"10.1016\/j.ipm.2020.102341","volume":"57","author":"M Bidoki","year":"2020","unstructured":"Bidoki M, Moosavi MR, Fakhrahmad M (2020) A semantic approach to extractive multi-document summarization: Applying sentence expansion for tuning of conceptual densities. Inf Process Manag 57(6):102341","journal-title":"Inf Process Manag"},{"issue":"4","key":"527_CR8","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1111\/j.1467-8640.2012.00417.x","volume":"29","author":"G Carenini","year":"2013","unstructured":"Carenini G, Cheung JCK, Pauls A (2013) Multi-document summarization of evaluative text. Comput Intell 29(4):545\u2013576","journal-title":"Comput Intell"},{"key":"527_CR9","doi-asserted-by":"crossref","unstructured":"Liu T, Wei B, Chang B (2017) Large-scale simple question generation by template-based seq2seq learning. In National CCF Conference on Natural Language Processing and Chinese Computing. Springer, Cham, pp 75-87","DOI":"10.1007\/978-3-319-73618-1_7"},{"issue":"4","key":"527_CR10","doi-asserted-by":"publisher","first-page":"455","DOI":"10.4218\/etrij.17.0116.0074","volume":"39","author":"E Chung","year":"2017","unstructured":"Chung E, Park JG (2017) Sentence-chain based Seq2seq model for corpus expansion. ETRI J 39(4):455\u2013466","journal-title":"ETRI J"},{"issue":"11","key":"527_CR11","doi-asserted-by":"publisher","first-page":"e75","DOI":"10.1093\/nar\/gkv213","volume":"43","author":"Y Chu","year":"2015","unstructured":"Chu Y, Wang T, Dodd D (2015) Intramolecular circularization increases efficiency of RNA sequencing and enables CLIP-Seq of nuclear RNA from human cells. Nucleic Acids Res 43(11):e75\u2013e75","journal-title":"Nucleic Acids Res"},{"key":"527_CR12","first-page":"1724","volume":"2","author":"K Cho","year":"2014","unstructured":"Cho K, Gulcehre C (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. Empirical Methods in Natural Language Processing. Stroudsburg 2:1724\u20131734","journal-title":"Stroudsburg"},{"key":"527_CR13","unstructured":"Sutskever I, Vinyals O, Le Q V (2014) Sequence to sequence learning with neural networks. Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press:3104\u20133112"},{"key":"527_CR14","first-page":"1","volume":"2","author":"D Bahdanau","year":"2014","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. Comput Sci 2:1\u20138","journal-title":"Comput Sci"},{"issue":"1","key":"527_CR15","first-page":"379","volume":"8","author":"AM Rush","year":"2015","unstructured":"Rush AM, Chopra S, Weston J (2015) A neural attention model for abstractive sentence summarization. Empirical Methods Nat Lang Process 8(1):379\u2013389","journal-title":"Empirical Methods Nat Lang Process"},{"issue":"6","key":"527_CR16","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1016\/j.ipm.2007.01.019","volume":"43","author":"P Over","year":"2007","unstructured":"Over P, Dang H, Harman D (2007) DUC in context. Inf Process Manag 43(6):1506\u20131520","journal-title":"Inf Process Manag"},{"key":"527_CR17","doi-asserted-by":"crossref","unstructured":"Chopra S, Auli M, and Rush A M (2016) Abstractive sentence summarization with attentive recurrent neural networks. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies:93\u201398","DOI":"10.18653\/v1\/N16-1012"},{"key":"527_CR18","doi-asserted-by":"crossref","unstructured":"Nallapati R, Zhou B, Santos C (2016) Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning:280\u2013290","DOI":"10.18653\/v1\/K16-1028"},{"key":"527_CR19","doi-asserted-by":"crossref","unstructured":"Zhou Q, Yang N, Wei F, Zhou M (2017) Selective encoding for abstractive sentence summarization. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics 1:1095\u20131104","DOI":"10.18653\/v1\/P17-1101"},{"key":"527_CR20","doi-asserted-by":"crossref","unstructured":"Gu J, Lu Z, Li H et al (2016) Incorporating copying mechanism in sequence-to-sequence learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics 1:1631\u20131640","DOI":"10.18653\/v1\/P16-1154"},{"key":"527_CR21","doi-asserted-by":"crossref","unstructured":"See A, Liu P J et al (2017) Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics 1:1073\u20131083","DOI":"10.18653\/v1\/P17-1099"},{"key":"527_CR22","unstructured":"Vinyals O, Fortunato M and Jaitly N (2015) Pointer networks. In Advances in Neural Information Processing Systems:2692\u20132700"},{"key":"527_CR23","doi-asserted-by":"crossref","unstructured":"Chen Y C, Bansal M (2018) Fast abstractive summarization with reinforce-selected sentence rewriting. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics 1:10\u201327","DOI":"10.18653\/v1\/P18-1063"},{"key":"527_CR24","doi-asserted-by":"crossref","unstructured":"Guo H, Pasunuru R, and Bansal M (2018) Soft layer-specific multi-task summarization with entailment and question generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics 1:687\u2013697","DOI":"10.18653\/v1\/P18-1064"},{"key":"527_CR25","doi-asserted-by":"crossref","unstructured":"Sun F, Jiang P, Sun H, Pei C, Ou W, and Wang X (2018) Multi-source pointer network for product title summarization. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management:7\u201316","DOI":"10.1145\/3269206.3271722"},{"key":"527_CR26","doi-asserted-by":"crossref","unstructured":"Zhou Q, Yang N, Wei F, Zhou M (2018) Sequential copying networks. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence 32(1):4987\u20134995","DOI":"10.1609\/aaai.v32i1.11915"},{"key":"527_CR27","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s40747-019-0115-2","volume":"6","author":"N Rahman","year":"2020","unstructured":"Rahman N, Borah B (2020) Improvement of query-based text summarization using word sense disambiguation. Complex Intell Syst 6:75\u201385","journal-title":"Complex Intell Syst"},{"key":"527_CR28","doi-asserted-by":"crossref","unstructured":"Wang L, Yao J, Tao Y et al (2018) A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization. Proceedings of the Twenty-Seventh International Joint Conference on Artificial (Intelligence:4453\u20134460)","DOI":"10.24963\/ijcai.2018\/619"},{"key":"527_CR29","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1016\/j.neucom.2020.04.137","volume":"410","author":"Z Liang","year":"2020","unstructured":"Liang Z, Du J, Li C (2020) Abstractive social media text summarization using selective reinforced Seq2Seq attention model. Neurocomputing 410:432\u2013440","journal-title":"Neurocomputing"},{"issue":"3","key":"527_CR30","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TCYB.2018.2876317","volume":"50","author":"K Yao","year":"2018","unstructured":"Yao K, Zhang L, Du D et al (2018) Dual encoding for abstractive text summarization. IEEE Trans Cybern 50(3):985\u2013996","journal-title":"IEEE Trans Cybern"},{"issue":"3","key":"527_CR31","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1109\/TASLP.2018.2883740","volume":"27","author":"J Zhang","year":"2018","unstructured":"Zhang J, Zhao Y, Li H et al (2018) Attention with sparsity regularization for neural machine translation and summarization. IEEE\/ACM Trans Audio Speech Lang Process 27(3):507\u2013518","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"527_CR32","first-page":"5998","volume":"2","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N (2017) Attention is all you need. Adv Neural Inf Process Syst 2:5998\u20136008","journal-title":"Adv Neural Inf Process Syst"},{"key":"527_CR33","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.neunet.2020.02.013","volume":"125","author":"X Xiao","year":"2020","unstructured":"Xiao X, Zhang D, Hu G (2020) CNN-MHSA: A convolutional neural network and multi-head self-attention combined approach for detecting phishing websites. Neural Netw 125:303\u2013312","journal-title":"Neural Netw"},{"key":"527_CR34","doi-asserted-by":"publisher","first-page":"107486","DOI":"10.1016\/j.patcog.2020.107486","volume":"107","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Gong Y, Zhu H et al (2020) Multi-head enhanced self-attention network for novelty detection. Pattern Recogn 107:107486","journal-title":"Pattern Recogn"},{"key":"527_CR35","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1109\/TASLP.2021.3071667","volume":"29","author":"P Wei","year":"2021","unstructured":"Wei P, Zhao J, Mao W (2021) A graph-to-sequence learning framework for summarizing opinionated texts. IEEE\/ACM Trans Audio Speech Lang Process 29:1650\u20131660","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"4","key":"527_CR36","doi-asserted-by":"publisher","first-page":"1258","DOI":"10.1080\/00207543.2020.1722325","volume":"59","author":"BK Dey","year":"2020","unstructured":"Dey BK, Pareek S, Tayyab M et al (2020) Autonomation policy to control work-in-process inventory in a smart production system. Int J Prod Res 59(4):1258\u20131280","journal-title":"Int J Prod Res"},{"key":"527_CR37","unstructured":"Hermann K M, Kocisky T et al (2015) Teaching machines to read and comprehend. In Proceedings of Neural Information Processing Systems (NIPS):1\u201314"},{"key":"527_CR38","unstructured":"Barrios F, L\u00f3pez F, Argerich L, Wachenchauzer R (2016) Variations of the similarity function of textrank for automated summarization. arXiv preprint arXiv:1602.03606"},{"key":"527_CR39","doi-asserted-by":"crossref","unstructured":"Grusky M, Naaman M, Artzi Y (2018) Newsroom: A dataset of 1.3 million summaries with diverse extractive strategies. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:708\u2013719","DOI":"10.18653\/v1\/N18-1065"},{"key":"527_CR40","doi-asserted-by":"crossref","unstructured":"Li J, Zhang C, Chen X (2019) Abstractive Text Summarization with Multi-Head Attention. In 2019 International Joint Conference on Neural Networks:1\u20138","DOI":"10.1109\/IJCNN.2019.8851885"},{"key":"527_CR41","doi-asserted-by":"crossref","unstructured":"Lebanoff L, Song K, Chang W and Liu F (2019) Scoring sentence singletons and pairs for abstractive summarization. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics:1\u201315","DOI":"10.18653\/v1\/P19-1209"},{"key":"527_CR42","doi-asserted-by":"crossref","unstructured":"Fan Z, Gong Y, Liu D (2021) Mask Attention Networks: Rethinking and Strengthen Transformer. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies:1692\u20131701","DOI":"10.18653\/v1\/2021.naacl-main.135"},{"key":"527_CR43","unstructured":"Devlin J, Chang M W, Lee K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies(1):4171\u20134186"},{"key":"527_CR44","doi-asserted-by":"publisher","first-page":"107867","DOI":"10.1016\/j.ijpe.2020.107867","volume":"231","author":"B Sarkar","year":"2021","unstructured":"Sarkar B, Sarkar M, Ganguly B (2021) Combined effects of carbon emission and production quality improvement for fixed lifetime products in a sustainable supply chain management. Int J Prod Econ 231:107867","journal-title":"Int J Prod Econ"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00527-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-021-00527-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00527-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T01:07:29Z","timestamp":1673399249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-021-00527-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,2]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["527"],"URL":"https:\/\/doi.org\/10.1007\/s40747-021-00527-2","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,2]]},"assertion":[{"value":"4 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}