{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:58Z","timestamp":1740108058601,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s00521-021-06566-7","type":"journal-article","created":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T23:55:35Z","timestamp":1633478135000},"page":"2965-2981","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-level shared-weight encoding for abstractive sentence summarization"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6407-6184","authenticated-orcid":false,"given":"Daisy Monika","family":"Lal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna Pratap","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uma Shanker","family":"Tiwary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,5]]},"reference":[{"key":"6566_CR1","doi-asserted-by":"crossref","unstructured":"Amplayo RK, Lim S, Hwang SW (2018) Entity commonsense representation for neural abstractive summarization. In: 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018, Association for Computational Linguistics (ACL), pp 697\u2013707","DOI":"10.18653\/v1\/N18-1064"},{"key":"6566_CR2","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:14090473"},{"key":"6566_CR3","unstructured":"Cao Z, Wei F, Li W, Li S (2017) Faithful to the original: fact aware neural abstractive summarization. arXiv preprint arXiv:171104434"},{"key":"6566_CR4","doi-asserted-by":"crossref","unstructured":"Cao Z, Li W, Li S, Wei F (2018) Retrieve, rerank and rewrite: Soft template based neural summarization. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 152\u2013161","DOI":"10.18653\/v1\/P18-1015"},{"key":"6566_CR5","doi-asserted-by":"crossref","unstructured":"Cheng J, Lapata M (2016) Neural summarization by extracting sentences and words. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 484\u2013494","DOI":"10.18653\/v1\/P16-1046"},{"key":"6566_CR6","doi-asserted-by":"crossref","unstructured":"Chopra S, Auli M, Rush AM (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, pp 93\u201398","DOI":"10.18653\/v1\/N16-1012"},{"key":"6566_CR7","doi-asserted-by":"crossref","unstructured":"Cohan A, Dernoncourt F, Kim DS, Bui T, Kim S, Chang W, Goharian N (2018) A discourse-aware attention model for abstractive summarization of long documents. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp 615\u2013621","DOI":"10.18653\/v1\/N18-2097"},{"key":"6566_CR8","doi-asserted-by":"crossref","unstructured":"Diao Y, Lin H, Yang L, Fan X, Chu Y, Wu D, Zhang D, Xu K (2020) Crhasum: extractive text summarization with contextualized-representation hierarchical-attention summarization network. Neural Comput Appl 1\u201313","DOI":"10.1007\/s00521-019-04638-3"},{"key":"6566_CR9","doi-asserted-by":"crossref","unstructured":"Gao Y, Wang Y, Liu L, Guo Y, Huang H (2019) Neural abstractive summarization fusing by global generative topics. Neural Comput Appl 1\u201310","DOI":"10.1007\/s00521-018-3946-7"},{"key":"6566_CR10","unstructured":"Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN (2017) Convolutional sequence to sequence learning. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp 1243\u20131252"},{"key":"6566_CR11","doi-asserted-by":"crossref","unstructured":"Gehrmann S, Deng Y, Rush AM (2018) Bottom-up abstractive summarization. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 4098\u20134109","DOI":"10.18653\/v1\/D18-1443"},{"key":"6566_CR12","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Sequence modeling: recurrent and recursive nets. Deep Learning. pp 367\u2013415"},{"issue":"1","key":"6566_CR13","first-page":"34","volume":"4","author":"D Graff","year":"2003","unstructured":"Graff D, Kong J, Chen K, Maeda K (2003) English gigaword. Linguistic Data Consortium, Philadelphia 4(1):34","journal-title":"Linguistic Data Consortium, Philadelphia"},{"key":"6566_CR14","doi-asserted-by":"crossref","unstructured":"Guo H, Pasunuru R, 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 (Volume 1: LongPapers), pp 687\u2013697","DOI":"10.18653\/v1\/P18-1064"},{"key":"6566_CR15","unstructured":"Guo Y, Yao A, Chen Y (2016) Dynamic network surgery for efficient DNNS. In: Advances in neural information processing systems, pp 1379\u20131387"},{"issue":"3","key":"6566_CR16","first-page":"258","volume":"2","author":"V Gupta","year":"2010","unstructured":"Gupta V, Lehal GS (2010) A survey of text summarization extractive techniques. J Emerg Technol Web Intell 2(3):258\u2013268","journal-title":"J Emerg Technol Web Intell"},{"key":"6566_CR17","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:151000149"},{"key":"6566_CR18","doi-asserted-by":"crossref","unstructured":"Kikuchi Y, Neubig G, Sasano R, Takamura H, Okumura M (2016) Controlling output length in neural encoder-decoders. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp 1328\u20131338","DOI":"10.18653\/v1\/D16-1140"},{"key":"6566_CR19","doi-asserted-by":"crossref","unstructured":"Klein G, Kim Y, Deng Y, Senellart J, Rush AM (2017) Opennmt: Open-source toolkit for neural machine translation. In: Proceedings of ACL 2017, System Demonstrations, pp 67\u201372","DOI":"10.18653\/v1\/P17-4012"},{"key":"6566_CR20","unstructured":"Lamb AM, Goyal AGAP, Zhang Y, Zhang S, Courville AC, Bengio Y (2016) Professor forcing: A new algorithm for training recurrent networks. In: Advances in neural information processing systems, pp 4601\u20134609"},{"key":"6566_CR21","doi-asserted-by":"crossref","unstructured":"Lebanoff L, Song K, Liu F (2018) Adapting the neural encoder-decoder framework from single to multi-document summarization. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 4131\u20134141","DOI":"10.18653\/v1\/D18-1446"},{"key":"6566_CR22","first-page":"143","volume":"19","author":"Y LeCun","year":"1989","unstructured":"LeCun Y et al (1989) Generalization and network design strategies. Connect Perspect 19:143\u2013155","journal-title":"Connect Perspect"},{"key":"6566_CR23","unstructured":"Li H, Zhu J, Zhang J, Zong C (2018) Ensure the correctness of the summary: Incorporate entailment knowledge into abstractive sentence summarization. In: Proceedings of the 27th International Conference on Computational Linguistics, pp 1430\u20131441"},{"key":"6566_CR24","doi-asserted-by":"crossref","unstructured":"Li P, Lam W, Bing L, Wang Z (2017) Deep recurrent generative decoder for abstractive text summarization. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp 2091\u20132100","DOI":"10.18653\/v1\/D17-1222"},{"key":"6566_CR25","unstructured":"Lin CY (2004) Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out, pp 74\u201381"},{"key":"6566_CR26","doi-asserted-by":"crossref","unstructured":"Lin J, Sun X, Ma S, Su Q (2018) Global encoding for abstractive summarization. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp 163\u2013169","DOI":"10.18653\/v1\/P18-2027"},{"key":"6566_CR27","doi-asserted-by":"crossref","unstructured":"Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp 1412\u20131421","DOI":"10.18653\/v1\/D15-1166"},{"key":"6566_CR28","doi-asserted-by":"crossref","unstructured":"Nallapati R, Zhou B, Gulcehre C, Xiang B et al (2016) Abstractive text summarization using sequence-to-sequence rnns and beyond. In: Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pp 280\u2013290","DOI":"10.18653\/v1\/K16-1028"},{"key":"6566_CR29","unstructured":"Napoles C, Gormley MR, Van\u00a0Durme B (2012) Annotated gigaword. In: Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX), pp 95\u2013100"},{"key":"6566_CR30","doi-asserted-by":"crossref","unstructured":"Nenkova A, McKeown K (2012) A survey of text summarization techniques. In: Mining text data, Springer, pp 43\u201376","DOI":"10.1007\/978-1-4614-3223-4_3"},{"issue":"4","key":"6566_CR31","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1162\/neco.1992.4.4.473","volume":"4","author":"SJ Nowlan","year":"1992","unstructured":"Nowlan SJ, Hinton GE (1992) Simplifying neural networks by soft weight-sharing. Neural Comput 4(4):473\u2013493","journal-title":"Neural Comput"},{"key":"6566_CR32","unstructured":"Paulus R, Xiong C, Socher R (2018) A deep reinforced model for abstractive summarization. In: International Conference on Learning Representations"},{"key":"6566_CR33","unstructured":"Pham H, Guan M, Zoph B, Le Q, Dean J (2018) Efficient neural architecture search via parameters sharing. In: International Conference on Machine Learning, pp 4095\u20134104"},{"key":"6566_CR34","unstructured":"Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:170605098"},{"key":"6566_CR35","doi-asserted-by":"crossref","unstructured":"Rush AM, Chopra S, Weston J (2015) A neural attention model for abstractive sentence summarization. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp 379\u2013389","DOI":"10.18653\/v1\/D15-1044"},{"key":"6566_CR36","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.21437\/Interspeech.2017-1705","volume":"8","author":"H Sak","year":"2017","unstructured":"Sak H, Shannon M, Rao K, Beaufays F (2017) Recurrent neural aligner: an encoder-decoder neural network model for sequence to sequence mapping. Interspeech 8:1298\u20131302","journal-title":"Interspeech"},{"key":"6566_CR37","unstructured":"Savarese P, Maire M (2018) Learning implicitly recurrent cnns through parameter sharing. In: International Conference on Learning Representations"},{"issue":"11","key":"6566_CR38","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673\u20132681","journal-title":"IEEE Trans Signal Process"},{"key":"6566_CR39","doi-asserted-by":"crossref","unstructured":"See A, Liu PJ, Manning CD (2017) Get to the point: Summarization with pointer-generator networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 1073\u20131083","DOI":"10.18653\/v1\/P17-1099"},{"key":"6566_CR40","unstructured":"Shi T, Keneshloo Y, Ramakrishnan N, Reddy CK (2018) Neural abstractive text summarization with sequence-to-sequence models: A survey. arXiv pp arXiv\u20131812"},{"key":"6566_CR41","doi-asserted-by":"crossref","unstructured":"Singh RK, Khetarpaul S, Gorantla R, Allada SG (2020) Sheg: summarization and headline generation of news articles using deep learning. Neural Comput Appl 1\u201315","DOI":"10.1007\/s00521-020-05188-9"},{"key":"6566_CR42","unstructured":"Song K, Zhao L, Liu F (2018) Structure-infused copy mechanisms for abstractive summarization. In: Proceedings of the 27th International Conference on Computational Linguistics, pp 1717\u20131729"},{"key":"6566_CR43","first-page":"8894","volume":"34","author":"K Song","year":"2020","unstructured":"Song K, Lebanoff L, Guo Q, Qiu X, Xue X, Li C, Yu D, Liu F (2020) Joint parsing and generation for abstractive summarization. Proc AAAI Conf Artif Intell 34:8894\u20138901","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"6566_CR44","unstructured":"Sutskever I, Vinyals O, Le QV (2014a) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104\u20133112"},{"key":"6566_CR45","unstructured":"Sutskever I, Vinyals O, Le QV (2014b) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104\u20133112"},{"key":"6566_CR46","doi-asserted-by":"crossref","unstructured":"Suzuki J, Nagata M (2017) Cutting-off redundant repeating generations for neural abstractive summarization. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp 291\u2013297","DOI":"10.18653\/v1\/E17-2047"},{"key":"6566_CR47","doi-asserted-by":"crossref","unstructured":"Wang K, Quan X, Wang R (2019) BiSET: Bi-directional selective encoding with template for abstractive summarization. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Florence, Italy, pp 2153\u20132162","DOI":"10.18653\/v1\/P19-1207"},{"key":"6566_CR48","doi-asserted-by":"crossref","unstructured":"Wang L, Yao J, Tao Y, Zhong L, Liu W, Du Q (2018) A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp 4453\u20134460","DOI":"10.24963\/ijcai.2018\/619"},{"key":"6566_CR49","doi-asserted-by":"crossref","unstructured":"Warrens MJ (2015) Five ways to look at cohen\u2019s kappa. J Psychol Psychother 5(4):1","DOI":"10.4172\/2161-0487.1000197"},{"issue":"1","key":"6566_CR50","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s11634-020-00394-8","volume":"15","author":"MJ Warrens","year":"2021","unstructured":"Warrens MJ (2021) Kappa coefficients for dichotomous-nominal classifications. Adv Data Anal Classif 15(1):193\u2013208","journal-title":"Adv Data Anal Classif"},{"issue":"11","key":"6566_CR51","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.1007\/s00521-018-3825-2","volume":"32","author":"M Yang","year":"2020","unstructured":"Yang M, Qu Q, Shen Y, Lei K, Zhu J (2020) Cross-domain aspect\/sentiment-aware abstractive review summarization by combining topic modeling and deep reinforcement learning. Neural Comput Appl 32(11):6421\u20136433","journal-title":"Neural Comput Appl"},{"key":"6566_CR52","doi-asserted-by":"crossref","unstructured":"Yao K, Zweig G, Hwang MY, Shi Y, Yu D (2013) Recurrent neural networks for language understanding. In: Interspeech, pp 2524\u20132528","DOI":"10.21437\/Interspeech.2013-569"},{"key":"6566_CR53","doi-asserted-by":"crossref","unstructured":"Yao K, Zhang L, Du D, Luo T, Tao L, Wu Y (2020) Dual encoding for abstractive text summarization. IEEE Trans Cybern 50(3)","DOI":"10.1109\/TCYB.2018.2876317"},{"key":"6566_CR54","unstructured":"Zajic D, Dorr B, Schwartz R (2004) Bbn\/umd at duc-2004: Topiary. In: Proceedings of the HLT-NAACL 2004 Document Understanding Workshop, Boston, pp 112\u2013119"},{"key":"6566_CR55","unstructured":"Zeng W, Luo W, Fidler S, Urtasun R (2016) Efficient summarization with read-again and copy mechanism. arXiv preprint arXiv:161103382"},{"key":"6566_CR56","unstructured":"Zhang B, Xiong D, Su J (2017) A gru-gated attention model for neural machine translation. arXiv preprint arXiv:170408430"},{"issue":"8","key":"6566_CR57","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.3390\/app9081665","volume":"9","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Li D, Wang Y, Fang Y, Xiao W (2019) Abstract text summarization with a convolutional seq2seq model. Appl Sci 9(8):1665","journal-title":"Appl Sci"},{"key":"6566_CR58","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 (Volume 1: Long Papers), pp 1095\u20131104","DOI":"10.18653\/v1\/P17-1101"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06566-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06566-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06566-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T09:16:40Z","timestamp":1644225400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06566-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,5]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["6566"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06566-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,10,5]]},"assertion":[{"value":"25 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 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":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}