{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:16:26Z","timestamp":1780578986210,"version":"3.54.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T00:00:00Z","timestamp":1666915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T00:00:00Z","timestamp":1666915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["No.61806101"],"award-info":[{"award-number":["No.61806101"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s10844-022-00757-x","type":"journal-article","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T05:03:23Z","timestamp":1666933403000},"page":"325-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Extractive text-image summarization with relation-enhanced graph attention network"],"prefix":"10.1007","volume":"61","author":[{"given":"Feng","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kejia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"issue":"1","key":"757_CR1","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s10844-021-00690-5","volume":"59","author":"ST Al-Amin","year":"2022","unstructured":"Al-Amin, S. T., & Ordonez, C. (2022). Incremental and accurate computation of machine learning models with smart data summarization. Journal of Intelligent Information Systems, 59(1), 149\u2013172. https:\/\/doi.org\/10.1007\/s10844-021-00690-5","journal-title":"Journal of Intelligent Information Systems"},{"key":"757_CR2","doi-asserted-by":"publisher","unstructured":"Calixto, I., Liu, Q., & Campbell, N. (2017). Doubly-attentive decoder for multi-modal neural machine translation. In Proceedings of the 55th annual meeting of the association for computational linguistics (Vol. 1: Long Papers, pp. 1913\u20131924). Association for Computational Linguistics, Vancouver, Canada. https:\/\/doi.org\/10.18653\/v1\/P17-1175","DOI":"10.18653\/v1\/P17-1175"},{"key":"757_CR3","doi-asserted-by":"publisher","unstructured":"Chen, J., & Zhuge, H. (2018). Abstractive text-image summarization using multi-modal attentional hierarchical RNN. In Proceedings of the 2018 conference on empirical methods in natural language processing, (pp. 4046\u20134056). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D18-1438","DOI":"10.18653\/v1\/D18-1438"},{"key":"757_CR4","doi-asserted-by":"publisher","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 (Vol. 1: Long Papers, pp. 484\u2013494). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/P16-1046","DOI":"10.18653\/v1\/P16-1046"},{"key":"757_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., et al. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Vol. 1 Long and Short Papers, pp. 4171\u20134186). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"issue":"1","key":"757_CR6","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1613\/jair.1523","volume":"22","author":"G Erkan","year":"2004","unstructured":"Erkan, G., & Radev, D. R. (2004). Lexrank: Graph-based lexical centrality as salience in text summarization. Journal of Artificial Intelligence Research, 22(1), 457\u2013479.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"757_CR7","unstructured":"Faghri, F., et al. (2018). Vse++: Improving visual-semantic embeddings with hard negatives. In Proceedings of the British machine vision conference (BMVC). https:\/\/github.com\/fartashf\/vsepp"},{"key":"757_CR8","doi-asserted-by":"publisher","unstructured":"He, K., et al. (2016). Deep residual learning for image recognition. In 2016 IEEE conference on computer vision and pattern recognition (CVPR), (pp. 770\u2013778). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"757_CR9","unstructured":"Kipf, T.N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International conference on learning representations. https:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"757_CR10","unstructured":"Li, Y., et al. (2016). Gated graph sequence neural networks. In 4th international conference on learning representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings. arXiv:1511.05493"},{"key":"757_CR11","doi-asserted-by":"publisher","unstructured":"Li, H., et al. (2018). Multi-modal sentence summarization with modality attention and image filtering. In Proceedings of the 27th international joint conference on artificial intelligence IJCAI-18, (pp. 4152\u20134158). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2018\/577","DOI":"10.24963\/ijcai.2018\/577"},{"key":"757_CR12","doi-asserted-by":"publisher","unstructured":"Li, M., et al. (2020). VMSMO: Learning to generate multimodal summary for video-based news articles. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), (pp. 9360\u20139369). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.752","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"issue":"05","key":"757_CR13","doi-asserted-by":"publisher","first-page":"8188","DOI":"10.1609\/aaai.v34i05.6332","volume":"34","author":"H Li","year":"2020","unstructured":"Li, H., et al. (2020). Aspect-aware multimodal summarization for Chinese e-commerce products. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 8188\u20138195. https:\/\/doi.org\/10.1609\/aaai.v34i05.6332.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"757_CR14","doi-asserted-by":"publisher","unstructured":"Liu, Y., & Lapata, M. (2019). Text summarization with pretrained encoders. 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. 3730\u20133740). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D19-1387","DOI":"10.18653\/v1\/D19-1387"},{"key":"757_CR15","unstructured":"Mihalcea, R., & Tarau, P. (2004) TextRank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing, (pp. 404\u2013411). Association for Computational Linguistics, Barcelona, Spain. https:\/\/aclanthology.org\/W04-3252"},{"key":"757_CR16","doi-asserted-by":"publisher","unstructured":"Nallapati, R., 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). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/K16-1028","DOI":"10.18653\/v1\/K16-1028"},{"issue":"1","key":"757_CR17","doi-asserted-by":"publisher","first-page":"3075","DOI":"10.1609\/aaai.v31i1.10958","volume":"31","author":"R Nallapati","year":"2017","unstructured":"Nallapati, R., Zhai, F., & Zhou, B. (2017). Summarunner: A recurrent neural network based sequence model for extractive summarization of documents. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1), 3075\u20133081. https:\/\/doi.org\/10.1609\/aaai.v31i1.10958.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"757_CR18","doi-asserted-by":"publisher","unstructured":"Narayan, S., Cohen, S.B., & Lapata, M. (2018). Ranking sentences for extractive summarization with reinforcement learning. In Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: Human language technologies, (Vol. 1: Long Papers, pp. 1747\u20131759). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N18-1158","DOI":"10.18653\/v1\/N18-1158"},{"issue":"1","key":"757_CR19","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s10844-022-00694-9","volume":"59","author":"M Peal","year":"2022","unstructured":"Peal, M., Hossain, M. S., & Chen, J. (2022). Summarizing consumer reviews. Journal of Intelligent Information Systems, 59(1), 193\u2013212. https:\/\/doi.org\/10.1007\/s10844-022-00694-9","journal-title":"Journal of Intelligent Information Systems"},{"key":"757_CR20","doi-asserted-by":"publisher","unstructured":"Pennington, J., Socher, R., & Manning, C. (2014). GloVe: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), (pp. 1532\u20131543). Association for Computational Linguistics. https:\/\/doi.org\/10.3115\/v1\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"757_CR21","doi-asserted-by":"publisher","unstructured":"Rush, A.M., 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). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D15-1044","DOI":"10.18653\/v1\/D15-1044"},{"issue":"1","key":"757_CR22","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s10844-021-00650-z","volume":"58","author":"JAP Sacenti","year":"2022","unstructured":"Sacenti, J. A. P., Fileto, R., & Willrich, R. (2022). Knowledge graph summarization impacts on movie recommendations. Journal of Intelligent Information Systems, 58(1), 43\u201366. https:\/\/doi.org\/10.1007\/s10844-021-00650-z","journal-title":"Journal of Intelligent Information Systems"},{"key":"757_CR23","doi-asserted-by":"publisher","unstructured":"See, A., Liu, P.J., & Manning, C.D. (2017). Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th annual meeting of the association for computational linguistics (Vol. 1: Long Papers, pp. 1073\u20131083). Association for Computational Linguistics, Vancouver, Canada. https:\/\/doi.org\/10.18653\/v1\/P17-1099","DOI":"10.18653\/v1\/P17-1099"},{"key":"757_CR24","doi-asserted-by":"publisher","unstructured":"Shen, X., et al. (2019). Improving latent alignment in text summarization by generalizing the pointer generator. 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. 3762\u20133773). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D19-1390","DOI":"10.18653\/v1\/D19-1390"},{"key":"757_CR25","doi-asserted-by":"publisher","unstructured":"Song, L., et al. (2018). A graph-to-sequence model for AMR-to-text generation. In Proceedings of the 56th annual meeting of the association for computational linguistics, (Vol. 1: Long Papers, pp. 1616\u20131626). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/P18-1150","DOI":"10.18653\/v1\/P18-1150"},{"key":"757_CR26","doi-asserted-by":"crossref","unstructured":"Tran, A., Mathews, A., & Xie, L. (2020). Transform and tell: Entity-aware news image captioning. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.01305"},{"key":"757_CR27","unstructured":"Veli\u010dkovi\u0107, P., et al. (2018). Graph attention networks. Accepted as poster. https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"757_CR28","doi-asserted-by":"publisher","unstructured":"Wang, D., et al. (2020). Heterogeneous graph neural networks for extractive document summarization. In Proceedings of the 58th annual meeting of the association for computational linguistics, (pp. 6209\u20136219). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.553","DOI":"10.18653\/v1\/2020.acl-main.553"},{"key":"757_CR29","doi-asserted-by":"publisher","unstructured":"Xu, J., & Durrett, G. (2019). Neural extractive text summarization with syntactic compression. 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. 3292\u20133303). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D19-1324","DOI":"10.18653\/v1\/D19-1324"},{"key":"757_CR30","doi-asserted-by":"publisher","unstructured":"Xue, M., et al. (2019). Neural collective entity linking based on recurrent random walk network learning. In Proceedings of the 28th international joint conference on artificial intelligence, IJCAI-19, (pp. 5327\u20135333). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2019\/740","DOI":"10.24963\/ijcai.2019\/740"},{"issue":"01","key":"757_CR31","doi-asserted-by":"publisher","first-page":"7370","DOI":"10.1609\/aaai.v33i01.33017370","volume":"33","author":"L Yao","year":"2019","unstructured":"Yao, L., Mao, C., & Luo, Y. (2019). Graph convolutional networks for text classification. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7370\u20137377. https:\/\/doi.org\/10.1609\/aaai.v33i01.33017370","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"757_CR32","doi-asserted-by":"publisher","unstructured":"Zhou, Q., et al. (2018). Neural document summarization by jointly learning to score and select sentences. In Proceedings of the 56th annual meeting of the association for computational linguistics (Vol. 1: Long Papers, pp. 654\u2013663). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/P18-1061","DOI":"10.18653\/v1\/P18-1061"},{"key":"757_CR33","doi-asserted-by":"publisher","unstructured":"Zhu, J., et al. (2018). MSMO: Multimodal summarization with multimodal output. In Proceedings of the 2018 conference on empirical methods in natural language processing, (pp. 4154\u20134164). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D18-1448","DOI":"10.18653\/v1\/D18-1448"},{"issue":"05","key":"757_CR34","doi-asserted-by":"publisher","first-page":"9749","DOI":"10.1609\/aaai.v34i05.6525","volume":"34","author":"J Zhu","year":"2020","unstructured":"Zhu, J., et al. (2020). Multimodal summarization with guidance of multimodal reference. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9749\u20139756. https:\/\/doi.org\/10.1609\/aaai.v34i05.6525","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-022-00757-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-022-00757-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-022-00757-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T09:06:12Z","timestamp":1698051972000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-022-00757-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,28]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["757"],"URL":"https:\/\/doi.org\/10.1007\/s10844-022-00757-x","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,28]]},"assertion":[{"value":"25 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval and Consent to participate"}},{"value":"The authors declare that they consent for publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not Applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and Animal Ethics"}},{"value":"The authors declare that they have no conflict of interest.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}