{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T23:53:40Z","timestamp":1768262020403,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001794","name":"The University of Queensland","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001794","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Auto-regressive extractive summarization approaches determine sentence extraction probability conditioning on previous decisions by maintaining a partial summary representation. Despite its popularity, the framework has two main drawbacks: 1) the partial summary representation is irresolutely denoted by a weighted summation of all the processed sentences without any filtering, resulting in a noisy representation and degrading the effectiveness of extracting subsequent sentences; 2) earlier sentences are biased towards a higher extraction probability due to the sequential nature of sequence tagging. To address these two problems, we propose the Auto-regressive Extractive Summarization with Replacement (AES-Rep), a novel auto-regressive extractive summarization model. In particular, the AES-Rep model consists of two main modules: the extraction decision module that determines whether a sentence should be extracted, and the replacement locater module that enables extracted deficient sentences to be replaced with latter sentences by comparing their expressiveness with respect to the main idea of the document. These modules update the partial summary with explicit actions using elaborated multidimensional guidance. We conduct extensive experiments on the benchmark CNN and DailyMail datasets. Experimental results show that AES-Rep can achieve better performance compared with various strong baselines in terms of multiple ROUGE metrics.<\/jats:p>","DOI":"10.1007\/s11280-022-01108-0","type":"journal-article","created":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T06:04:01Z","timestamp":1670565841000},"page":"2003-2026","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Auto-regressive extractive summarization with replacement"],"prefix":"10.1007","volume":"26","author":[{"given":"Tianyu","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5456-7035","authenticated-orcid":false,"given":"Wen","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saeid","family":"Hosseini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,9]]},"reference":[{"key":"1108_CR1","doi-asserted-by":"crossref","unstructured":"Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E.D., Gutierrez, J.B., Kochut, K.: Text summarization techniques: a brief survey. Int. J. Adv. Comput. Sci. Appl. 8(10) (2017)","DOI":"10.14569\/IJACSA.2017.081052"},{"key":"1108_CR2","doi-asserted-by":"crossref","unstructured":"Bae, S., Kim, T., Kim, J., Lee, S.g.: Summary level training of sentence rewriting for abstractive summarization. In: Proceedings of the 2nd Workshop on New Frontiers in Summarization, pp 10\u201320 (2019)","DOI":"10.18653\/v1\/D19-5402"},{"key":"1108_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLP (2015)"},{"key":"1108_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Wei, F., Li, W., Li, S.: Faithful to the original: Fact aware neural abstractive summarization. AAAI 32(1) (2018)","DOI":"10.1609\/aaai.v32i1.11912"},{"key":"1108_CR5","doi-asserted-by":"crossref","unstructured":"Celikyilmaz, A., Bosselut, A., He, X., Choi, Y.: Deep communicating agents for abstractive summarization. In: NAACL, pp 1662\u20131675 (2018)","DOI":"10.18653\/v1\/N18-1150"},{"key":"1108_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Bansal, M.: Fast abstractive summarization with reinforce-selected sentence rewriting. In: ACL, pp 675\u2013686 (2018)","DOI":"10.18653\/v1\/P18-1063"},{"key":"1108_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, J., Lapata, M.: Neural summarization by extracting sentences and words. In: ACL, pp 484\u2013494 (2016)","DOI":"10.18653\/v1\/P16-1046"},{"key":"1108_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp 4171\u20134186 (2019)"},{"key":"1108_CR9","doi-asserted-by":"crossref","unstructured":"Dong, Y., Shen, Y., Crawford, E., van Hoof, H., Cheung, J.C.K.: Extractive summarization as a contextual bandit. In: EMNLP, pp 3739\u20133748 (2018)","DOI":"10.18653\/v1\/D18-1409"},{"key":"1108_CR10","doi-asserted-by":"crossref","unstructured":"Gehrmann, S., Deng, Y., Rush, A.: Bottom-up abstractive summarization. In: EMNLP, pp 4098\u20134109 (2018a)","DOI":"10.18653\/v1\/D18-1443"},{"key":"1108_CR11","doi-asserted-by":"crossref","unstructured":"Gehrmann, S., Deng, Y., Rush, A.: Bottom-up abstractive summarization. In: EMNLP, pp 4098\u20134109 (2018b)","DOI":"10.18653\/v1\/D18-1443"},{"key":"1108_CR12","doi-asserted-by":"crossref","unstructured":"Grenander, M., Dong, Y., Cheung, J.C.K., Louis, A.: Countering the effects of lead bias in news summarization via multi-stage training and auxiliary losses. In: EMNLP-IJCNLP, pp 6019\u20136024 (2019)","DOI":"10.18653\/v1\/D19-1620"},{"key":"1108_CR13","doi-asserted-by":"crossref","unstructured":"Gu, J., Lu, Z., Li, H., Li, V.O.: Incorporating copying mechanism in sequence-to-sequence learning. In: ACL, pp 1631\u20131640 (2016)","DOI":"10.18653\/v1\/P16-1154"},{"key":"1108_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1108_CR15","doi-asserted-by":"crossref","unstructured":"Hsu, W.T., Lin, C.K., Lee, M.Y., Min, K., Tang, J., Sun, M.: A unified model for extractive and abstractive summarization using inconsistency loss. In: ACL, pp 132\u2013141 (2018)","DOI":"10.18653\/v1\/P18-1013"},{"key":"1108_CR16","doi-asserted-by":"crossref","unstructured":"Huang, L., Wu, L., Wang, L.: Knowledge graph-augmented abstractive summarization with semantic-driven cloze reward. In: ACL, pp 5094\u20135107 (2020)","DOI":"10.18653\/v1\/2020.acl-main.457"},{"key":"1108_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: ICLP (2015)"},{"key":"1108_CR18","unstructured":"Koupaee, M., Wang, W.Y.: Wikihow: A large scale text summarization dataset. arXiv:181009305 (2018)"},{"key":"1108_CR19","doi-asserted-by":"crossref","unstructured":"Lebanoff, L., Song, K., Dernoncourt, F., Kim, D.S., Kim, S., Chang, W., Liu, F.: Scoring sentence singletons and pairs for abstractive summarization. In: ACL, pp 2175\u20132189 (2019)","DOI":"10.18653\/v1\/P19-1209"},{"key":"1108_CR20","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp 74\u201381 (2004)"},{"key":"1108_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lapata, M.: Text summarization with pretrained encoders. In: EMNLP-IJCNLP, pp 3721\u20133731 (2019a)","DOI":"10.18653\/v1\/D19-1387"},{"key":"1108_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lapata, M.: Text summarization with pretrained encoders. In: EMNLP-IJCNLP, pp 3730\u20133740 (2019b)","DOI":"10.18653\/v1\/D19-1387"},{"key":"1108_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Titov, I., Lapata, M.: Single document summarization as tree induction. In: NAACL, pp 1745\u20131755 (2019)","DOI":"10.18653\/v1\/N19-1173"},{"key":"1108_CR24","doi-asserted-by":"crossref","unstructured":"Luo, L., Ao, X., Song, Y., Pan, F., Yang, M., He, Q.: Reading like HER: Human reading inspired extractive summarization. In: EMNLP-IJCNLP, pp 3033\u20133043 (2019)","DOI":"10.18653\/v1\/D19-1300"},{"key":"1108_CR25","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP, pp 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"1108_CR26","doi-asserted-by":"crossref","unstructured":"Moratanch, N., Chitrakala, S.: A survey on extractive text summarization. In: 2017 International Conference on Computer, Communication and Signal Processing, pp 1\u20136. IEEE (2017)","DOI":"10.1109\/ICCCSP.2017.7944061"},{"key":"1108_CR27","doi-asserted-by":"crossref","unstructured":"Nallapati, R., Zhou, B., dos, Santos C.N., G\u00fcl\u00e7ehre, \u00c7., Xiang, B.: 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 (2016)","DOI":"10.18653\/v1\/K16-1028"},{"key":"1108_CR28","doi-asserted-by":"crossref","unstructured":"Nallapati, R., Zhai, F., Zhou, B.: Summarunner: A recurrent neural network based sequence model for extractive summarization of documents. In: AAAI, pp 3075\u20133081 (2017)","DOI":"10.1609\/aaai.v31i1.10958"},{"key":"1108_CR29","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., Lapata, M.: Ranking sentences for extractive summarization with reinforcement learning. In: NAACL, pp 1747\u20131759 (2018)","DOI":"10.18653\/v1\/N18-1158"},{"key":"1108_CR30","unstructured":"Paulus, R., Xiong, C., Socher, R.: A deep reinforced model for abstractive summarization. In: ICLP. vol abs\/1705.04304 (2018)"},{"key":"1108_CR31","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: EMNLP, pp 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1108_CR32","doi-asserted-by":"crossref","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: Summarization with pointer-generator networks. In: ACL, pp 1073\u20131083 (2017)","DOI":"10.18653\/v1\/P17-1099"},{"key":"1108_CR33","doi-asserted-by":"crossref","unstructured":"Sharma, E., Huang, L., Hu, Z., Wang, L.: An entity-driven framework for abstractive summarization. In: EMNLP-IJCNLP, pp 3280\u20133291 (2019)","DOI":"10.18653\/v1\/D19-1323"},{"key":"1108_CR34","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"1108_CR35","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: NIPS, pp 6000\u20136010 (2017)"},{"key":"1108_CR36","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: ICLP (2018)"},{"key":"1108_CR37","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: NIPS, pp 2692\u20132700 (2015)"},{"key":"1108_CR38","doi-asserted-by":"crossref","unstructured":"Wang, D., Liu, P., Zheng, Y., Qiu, X., Huang, X.: Heterogeneous graph neural networks for extractive document summarization. In: ACL, pp 6209\u20136219 (2020)","DOI":"10.18653\/v1\/2020.acl-main.553"},{"key":"1108_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, X., Xiong, W., Yu, M., Guo, X., Chang, S., Wang, W.Y.: Self-supervised learning for contextualized extractive summarization. In: ACL, pp 2221\u20132227 (2019)","DOI":"10.18653\/v1\/P19-1214"},{"key":"1108_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Y., Hu, B.: Learning to extract coherent summary via deep reinforcement learning. In: AAAI, pp 5602\u20135609 (2018)","DOI":"10.1609\/aaai.v32i1.11987"},{"key":"1108_CR41","doi-asserted-by":"crossref","unstructured":"Xu, J., Gan, Z., Cheng, Y., Liu, J.: Discourse-aware neural extractive text summarization. In: ACL, pp 5021\u20135031 (2020)","DOI":"10.18653\/v1\/2020.acl-main.451"},{"key":"1108_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., Hovy, E.: Hierarchical attention networks for document classification. In: NAACL, pp 1480\u20131489 (2016)","DOI":"10.18653\/v1\/N16-1174"},{"key":"1108_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, X., Lapata, M., Wei, F., Zhou, M.: Neural latent extractive document summarization. In: EMNLP, pp 779\u2013784 (2018)","DOI":"10.18653\/v1\/D18-1088"},{"key":"1108_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, F., Zhou, M.: Hibert: Document level pre-training of hierarchical bidirectional transformers for document summarization. In: ACL, pp 5059\u20135069 (2019)","DOI":"10.18653\/v1\/P19-1499"},{"key":"1108_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, H., Lapata, M.: Sentence centrality revisited for unsupervised summarization. In: ACL, pp 6236\u20136247 (2019)","DOI":"10.18653\/v1\/P19-1628"},{"key":"1108_CR46","doi-asserted-by":"crossref","unstructured":"Zhong, M., Liu, P., Wang, D., Qiu, X., Huang, X.J.: Searching for effective neural extractive summarization: What works and what\u2019s next. In: ACL, pp 1049\u20131058 (2019)","DOI":"10.18653\/v1\/P19-1100"},{"key":"1108_CR47","doi-asserted-by":"crossref","unstructured":"Zhong, M., Liu, P., Chen, Y., Wang, D., Qiu, X., Huang, X.: Extractive summarization as text matching. In: ACL, pp 6197\u20136208 (2020)","DOI":"10.18653\/v1\/2020.acl-main.552"},{"key":"1108_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Yang, N., Wei, F., Huang, S., Zhou, M., Zhao, T.: Neural document summarization by jointly learning to score and select sentences. In: ACL, pp 654\u2013663 (2018)","DOI":"10.18653\/v1\/P18-1061"},{"key":"1108_CR49","doi-asserted-by":"crossref","unstructured":"\u00c7elikyilmaz, A., Bosselut, A., He, X., Choi, Y.: Deep communicating agents for abstractive summarization. In: NAACL, pp 1662\u20131675 (2018)","DOI":"10.18653\/v1\/N18-1150"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-022-01108-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-022-01108-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-022-01108-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T14:44:26Z","timestamp":1690382666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-022-01108-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,9]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["1108"],"URL":"https:\/\/doi.org\/10.1007\/s11280-022-01108-0","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,9]]},"assertion":[{"value":"5 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 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":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interests"}}]}}