{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:39:00Z","timestamp":1762353540267,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T00:00:00Z","timestamp":1720483200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T00:00:00Z","timestamp":1720483200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Natural answer generation is in a very clear practical significance and strong application background, which can be widely used in the field of knowledge services such as community question answering and intelligent customer service. Traditional knowledge question answering is to provide precise answer entities and neglect the defects; namely, users hope to receive a complete natural answer. In this research, we propose a novel attention-based recurrent neural network for natural answer generation, which is enhanced with multi-level copying mechanisms and question-aware loss. To generate natural answers that conform to grammar, we leverage multi-level copying mechanisms and the prediction mechanism which can copy semantic units and predict common words. Moreover, considering the problem that the generated natural answer does not match the user question, question-aware loss is introduced to make the generated target answer sequences correspond to the question. Experiments on three response generation tasks show our model to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 0.727 BLEU on the SimpleQuestions response generation task, improving over the existing best results by over 0.007 BLEU. Our model has scored a significant enhancement on naturalness with up to 0.05 more than best performing baseline. The simulation results show that our method can generate grammatical and contextual natural answers according to user needs.<\/jats:p>","DOI":"10.1007\/s40747-024-01538-5","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T09:01:51Z","timestamp":1720515711000},"page":"7249-7264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Attention-based RNN with question-aware loss and multi-level copying mechanism for natural answer generation"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3886-0183","authenticated-orcid":false,"given":"Fen","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Huishuang","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yintong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,9]]},"reference":[{"key":"1538_CR1","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.ins.2019.12.002","volume":"514","author":"M Esposito","year":"2020","unstructured":"Esposito M, Damiano E, Minutolo A et al (2020) Hybrid query expansion using lexical resources and word embeddings for sentence retrieval in question answering. Inf Sci 514:88\u2013105","journal-title":"Inf Sci"},{"issue":"2","key":"1538_CR2","first-page":"1","volume":"19","author":"D Gupta","year":"2019","unstructured":"Gupta D, Ekbal A, Bhattacharyya P (2019) A deep neural network framework for English Hindi question answering. ACM Trans Asian Low-Resour Lang Inf Process (TALLIP) 19(2):1\u201322","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process (TALLIP)"},{"key":"1538_CR3","doi-asserted-by":"crossref","unstructured":"Saxena A, Tripathi A, Talukdar P (2020) Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 4498\u20134507","DOI":"10.18653\/v1\/2020.acl-main.412"},{"key":"1538_CR4","doi-asserted-by":"crossref","unstructured":"Raghu D, Joshi S, Joshi S (2022) Structural constraints and natural language inference for end-to-end flowchart grounded dialog response generation. In: Proceedings of the 2022 conference on empirical methods in natural language processing, pp 10763\u201310774","DOI":"10.18653\/v1\/2022.emnlp-main.739"},{"key":"1538_CR5","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.neucom.2022.10.023","volume":"515","author":"W Wu","year":"2023","unstructured":"Wu W, Zhu Z, Qi J et al (2023) A dynamic graph expansion network for multi-hop knowledge base question answering. Neurocomputing 515:37\u201347","journal-title":"Neurocomputing"},{"key":"1538_CR6","unstructured":"Koncel-Kedziorski R, Bekal D, Luan Y et al (2019) Text generation from knowledge graphs with graph transformers. arXiv preprint arXiv:1904.02342"},{"key":"1538_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108248","volume":"243","author":"Y Huang","year":"2022","unstructured":"Huang Y, Yang M, Yang N (2022) Flexible entity marks and a fine-grained style control for knowledge based natural answer generation. Knowl-Based Syst 243:108248","journal-title":"Knowl-Based Syst"},{"key":"1538_CR8","doi-asserted-by":"crossref","unstructured":"Cheng Z, Dong H, Wang Z et al (2022) Hitab: a hierarchical table dataset for question answering and natural language generation. In: Proceedings of the 60th annual meeting of the association for computational linguistics, pp 1094\u20131110","DOI":"10.18653\/v1\/2022.acl-long.78"},{"key":"1538_CR9","doi-asserted-by":"crossref","unstructured":"Yin J, Jiang X et al (2016) Neural generative question answering. In: Proceedings of the international joint conference on artificial intelligence, pp 1\u20137","DOI":"10.18653\/v1\/W16-0106"},{"key":"1538_CR10","doi-asserted-by":"crossref","unstructured":"Gu J, Lu Z et al (2016) Incorporating copying mechanism in sequence-to-sequence learning. In: Proceedings of the 54th annual meeting of the association for computational linguistics, pp 1631\u20131640","DOI":"10.18653\/v1\/P16-1154"},{"key":"1538_CR11","unstructured":"Kondadadi R, Howald B, Schilder F (2013) A statistical NLG framework for aggregated planning and realization. In: Proceedings of the 51st annual meeting of the association for computational linguistics, pp 1406\u20131415"},{"key":"1538_CR12","doi-asserted-by":"crossref","unstructured":"Shereen O, Vrindavan H, Abteen E, Marilyn AW et al (2019) Curate and generate: a corpus and method for joint control of semantics and style in neural NLG. In: Annual meeting of the association for computational linguistics, pp 5938\u20135951","DOI":"10.18653\/v1\/P19-1596"},{"key":"1538_CR13","doi-asserted-by":"crossref","unstructured":"Sai AB, Dixit T et al (2021) Perturbation CheckLists for evaluating NLG evaluation metrics. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 7219\u20137234","DOI":"10.18653\/v1\/2021.emnlp-main.575"},{"key":"1538_CR14","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1039\/D3FB00170A","volume":"2","author":"DS Brar","year":"2024","unstructured":"Brar DS, Aggarwal AK, Nanda V, Saxena S, Gautam S (2024) AI and CV based 2D-CNN algorithm: botanical authentication of Indian honey. Sustain Food Technol 2:373\u2013385","journal-title":"Sustain Food Technol"},{"key":"1538_CR15","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.foohum.2023.11.017","volume":"2","author":"DS Brar","year":"2024","unstructured":"Brar DS, Aggarwal AK, Nanda V, Kaur S, Saxena S, Gautam S (2024) Detection of sugar syrup adulteration in unifloral honey using deep learning framework: an effective quality analysis technique. Food Humanit 2:100\u2013109","journal-title":"Food Humanit"},{"key":"1538_CR16","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.knosys.2019.105210","volume":"191","author":"B Alshemali","year":"2020","unstructured":"Alshemali B, Kalita J (2020) Improving the reliability of deep neural networks in NLP: a review. Knowl-Based Syst 191:105\u2013130","journal-title":"Knowl-Based Syst"},{"key":"1538_CR17","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.bspc.2024.106024","volume":"91","author":"H Liu","year":"2024","unstructured":"Liu H, Ghadimi N (2024) Hybrid convolutional neural network and flexible dwarf mongoose optimization algorithm for strong kidney stone diagnosis. Biomed Signal Process Control 91:106\u2013124","journal-title":"Biomed Signal Process Control"},{"key":"1538_CR18","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.bspc.2023.105858","volume":"90","author":"L Zhang","year":"2024","unstructured":"Zhang L, Zhang J, Gao W, Bai F, Li N, Ghadimi N (2024) A deep learning outline aimed at prompt skin cancer detection utilizing gated recurrent unit networks and improved orca predation algorithm. Biomed Signal Process Control 90:105\u2013128","journal-title":"Biomed Signal Process Control"},{"key":"1538_CR19","doi-asserted-by":"crossref","unstructured":"Noraset T, Demeter D, Downey D (2018) Controlling global statistics in recurrent neural network text generation. In: Proceedings of the AAAI conference on artificial intelligence, pp 5333\u20135341","DOI":"10.1609\/aaai.v32i1.11993"},{"key":"1538_CR20","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.ins.2020.03.080","volume":"530","author":"N Jiang","year":"2020","unstructured":"Jiang N, Chen J, Zhou R, Wu C, Chen H et al (2020) PAN: pipeline assisted neural networks model for data-to-text generation in social Internet of Things. Inf Sci 530:167\u2013179","journal-title":"Inf Sci"},{"issue":"6","key":"1538_CR21","doi-asserted-by":"publisher","first-page":"3115","DOI":"10.1109\/TCYB.2020.2979930","volume":"51","author":"Y Tian","year":"2020","unstructured":"Tian Y, Lu C et al (2020) Solving large-scale multiobjective optimization problems with sparse optimal solutions via unsupervised neural networks. IEEE Trans Cybern 51(6):3115\u20133128","journal-title":"IEEE Trans Cybern"},{"issue":"1","key":"1538_CR22","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1515\/med-2020-0131","volume":"15","author":"Z Xu","year":"2020","unstructured":"Xu Z, Sheykhahmad FR, Ghadimi N, Razmjooy N (2020) Computer-aided diagnosis of skin cancer based on soft computing techniques. Open Med 15(1):860\u2013871","journal-title":"Open Med"},{"issue":"1","key":"1538_CR23","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1515\/med-2018-0002","volume":"13","author":"Navid Razmjooy","year":"2018","unstructured":"Razmjooy Navid, Fatima RS, Noradin G (2018) A hybrid neural network-world cup optimization algorithm for melanoma detection. Open Med 13(1):9\u201316","journal-title":"Open Med"},{"issue":"11","key":"1538_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3512467","volume":"54","author":"W Yu","year":"2022","unstructured":"Yu W, Zhu C et al (2022) A survey of knowledge-enhanced text generation. ACM Comput Surv 54(11):1\u201338","journal-title":"ACM Comput Surv"},{"key":"1538_CR25","doi-asserted-by":"crossref","unstructured":"Madotto A, Wu CS, Fung P (2018) Mem2Seq: effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. In: Proceedings of the 56th annual meeting of the association for computational linguistics, pp 1468\u20131478","DOI":"10.18653\/v1\/P18-1136"},{"key":"1538_CR26","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.ins.2020.07.077","volume":"545","author":"Y Wu","year":"2021","unstructured":"Wu Y, Zhao S (2021) Community answer generation based on knowledge graph. Inf Sci 545:132\u2013152","journal-title":"Inf Sci"},{"key":"1538_CR27","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.knosys.2019.02.006","volume":"171","author":"M Yang","year":"2019","unstructured":"Yang M, Tu W, Qu Q et al (2019) Advanced community question answering by leveraging external knowledge and multi-task learning. Knowl-Based Syst 171:106\u2013119","journal-title":"Knowl-Based Syst"},{"key":"1538_CR28","doi-asserted-by":"crossref","unstructured":"Liu C, Liu K, He S et al (2019) generating questions for knowledge bases via incorporating diversified contexts and answer-aware loss. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 2431\u20132441","DOI":"10.18653\/v1\/D19-1247"},{"key":"1538_CR29","doi-asserted-by":"crossref","unstructured":"He S, Liu C, Liu K et al (2017) Generating natural answers by incorporating copying and retrieving mechanisms in sequence-to-sequence learning. In: Proceedings of the 55th annual meeting of the association for computational linguistics, pp 199\u2013208","DOI":"10.18653\/v1\/P17-1019"},{"key":"1538_CR30","doi-asserted-by":"crossref","unstructured":"Hazarika D, Namazifar M, Hakkani-Tr D (2022) Attention biasing and context augmentation for zero-shot control of encoder\u2013decoder transformers for natural language generation. In: Proceedings of the AAAI conference on artificial intelligence, pp 10738\u201310748","DOI":"10.1609\/aaai.v36i10.21319"},{"issue":"3","key":"1538_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617680","volume":"56","author":"H Zhang","year":"2023","unstructured":"Zhang H, Song H, Li S et al (2023) A survey of controllable text generation using transformer-based pre-trained language models. ACM Comput Surv 56(3):1\u201337","journal-title":"ACM Comput Surv"},{"issue":"2","key":"1538_CR32","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.ipm.2022.103227","volume":"60","author":"M Bani-Almarjeh","year":"2023","unstructured":"Bani-Almarjeh M, Mohamad-Bassam K (2023) Arabic abstractive text summarization using RNN-based and transformer-based architectures. Inf Process Manag 60(2):103\u2013127","journal-title":"Inf Process Manag"},{"key":"1538_CR33","doi-asserted-by":"crossref","unstructured":"Rush A, 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":"1538_CR34","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: 31st conference on neural information processing systems, pp 1\u201311"},{"key":"1538_CR35","doi-asserted-by":"crossref","unstructured":"Nguyen DQ, Nguyen TD, Nguyen DQ et al (2018) A novel embedding model for knowledge base completion based on convolutional neural network. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 327\u2013333","DOI":"10.18653\/v1\/N18-2053"},{"key":"1538_CR36","doi-asserted-by":"crossref","unstructured":"Deng Y, Xie Y, Li Y et al (2019) Multi-task learning with multi-view attention for answer selection and knowledge base question answering. In: Proceedings of the AAAI conference on artificial intelligence, pp 6318\u20136325","DOI":"10.1609\/aaai.v33i01.33016318"},{"issue":"5","key":"1538_CR37","doi-asserted-by":"publisher","first-page":"565","DOI":"10.14778\/3055540.3055549","volume":"10","author":"W Cui","year":"2019","unstructured":"Cui W, Xiao Y, Wang H et al (2019) KBQA: learning question answering over QA Corpora and knowledge bases. Proc VLDB Endow 10(5):565\u2013576","journal-title":"Proc VLDB Endow"},{"key":"1538_CR38","doi-asserted-by":"crossref","unstructured":"Su Y, Sun H, Sadler B et al (2016) On generating characteristic-rich question sets for QA evaluation. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 562\u2013572","DOI":"10.18653\/v1\/D16-1054"},{"issue":"1","key":"1538_CR39","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"1538_CR40","doi-asserted-by":"crossref","unstructured":"Elsahar H, Gravier C, Laforest F (2018) Zero-shot question generation from knowledge graphs for unseen predicates and entity types. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 1\u201311","DOI":"10.18653\/v1\/N18-1020"},{"key":"1538_CR41","doi-asserted-by":"crossref","unstructured":"Serban I, Sordoni A, Lowe R et al (2017) A hierarchical latent variable encoder\u2013decoder model for generating dialogues. In: Proceedings of the AAAI conference on artificial intelligence, pp 1\u20137","DOI":"10.1609\/aaai.v31i1.10983"},{"key":"1538_CR42","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.ins.2018.12.032","volume":"481","author":"W Zheng","year":"2019","unstructured":"Zheng W, Cheng H, Yu JX et al (2019) Interactive natural language question answering over knowledge graphs. Inf Sci 481:141\u2013159","journal-title":"Inf Sci"},{"key":"1538_CR43","doi-asserted-by":"crossref","unstructured":"Lu X, Pramanik S, Saha Roy R et al (2019) Answering complex questions by joining multi-document evidence with quasi knowledge graphs. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, pp 105\u2013114","DOI":"10.1145\/3331184.3331252"},{"key":"1538_CR44","first-page":"1","volume":"2020","author":"Y Wang","year":"2020","unstructured":"Wang Y, Rong W, Zhang J et al (2020) Knowledge grounded pre-trained model for dialogue response generation. Int Jt Conf Neural Netw 2020:1\u20138","journal-title":"Int Jt Conf Neural Netw"},{"key":"1538_CR45","doi-asserted-by":"crossref","unstructured":"Hazarika D, Namazifar M, Hakkani-T\u00fcr D (2022) Attention biasing and context augmentation for zero-shot control of encoder-decoder transformers for natural language generation. In; Proceedings of the AAAI conference on artificial intelligence, pp 10738\u201310748","DOI":"10.1609\/aaai.v36i10.21319"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01538-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01538-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01538-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T15:25:16Z","timestamp":1726327516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01538-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,9]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1538"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01538-5","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2024,7,9]]},"assertion":[{"value":"19 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no potential Conflict of interest in our paper. And all authors have seen the manuscript and approved to submit to your journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}