{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T22:11:12Z","timestamp":1783462272347,"version":"3.55.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2022,3,19]],"date-time":"2022-03-19T00:00:00Z","timestamp":1647648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,19]],"date-time":"2022-03-19T00:00:00Z","timestamp":1647648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["61773229"],"award-info":[{"award-number":["61773229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"natural science foundation of beijing municipality","doi-asserted-by":"publisher","award":["KZ201710015010"],"award-info":[{"award-number":["KZ201710015010"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1007\/s10489-022-03190-3","type":"journal-article","created":{"date-parts":[[2022,3,19]],"date-time":"2022-03-19T01:03:46Z","timestamp":1647651826000},"page":"15929-15937","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["AP-BERT: enhanced pre-trained model through average pooling"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5174-5182","authenticated-orcid":false,"given":"Shuai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Man","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fucheng","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,3,19]]},"reference":[{"key":"3190_CR1","unstructured":"Liu X, Cheng H, He P, Chen W, Wang Y, Poon H, Gao J (2020) Adversarial training for large neural language models. arXiv:2004.08994"},{"key":"3190_CR2","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training"},{"key":"3190_CR3","doi-asserted-by":"crossref","unstructured":"Gu Y, Yang M, Lin P (2020) Lightweight Multiple Perspective Fusion with Information Enriching for BERT-based Answer Selection International Conference on Natural Language Processing and Chinese Computing. Springer, Cham","DOI":"10.1007\/978-3-030-60450-9_43"},{"key":"3190_CR4","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. Inproceedings of NAACL"},{"key":"3190_CR5","unstructured":"Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2019) ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In: International conference on learning representations"},{"key":"3190_CR6","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Effificient estimation of word representations in vector space. arXiv:1301.3781"},{"key":"3190_CR7","doi-asserted-by":"crossref","unstructured":"Howard J, Ruder S (2018) Universal language model fine-tuning for text classification. Inproceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1:, Long Papers), pp 328\u2013339","DOI":"10.18653\/v1\/P18-1031"},{"key":"3190_CR8","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: Global vectors for word representation. Inproceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"3190_CR9","unstructured":"McCann B, Bradbury J, Xiong C, Socher R (2017) Learned in translation: Contextualized word vectors. In: Advances in neural In formation processing systems, pp 6294\u20136305"},{"key":"3190_CR10","doi-asserted-by":"crossref","unstructured":"Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. In: Proceedings of NAACL-HLT, pp 2227\u20132237","DOI":"10.18653\/v1\/N18-1202"},{"key":"3190_CR11","unstructured":"Brown BT, Mann B, Ryder N (2019) Language Models are Few-Shot Learners. arXiv:2005.14165"},{"key":"3190_CR12","doi-asserted-by":"crossref","unstructured":"Yang X, Tang K, Zhang H, Cai J (2019) Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer vision and pattern recognition, pp 10685\u201310694","DOI":"10.1109\/CVPR.2019.01094"},{"key":"3190_CR13","doi-asserted-by":"crossref","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","DOI":"10.18653\/v1\/D19-1387"},{"key":"3190_CR14","doi-asserted-by":"crossref","unstructured":"Gu J, Shen Y, Zhou B (2020) Image processing using multi-code gan prior. In: Inproceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3012\u20133021","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"3190_CR15","doi-asserted-by":"crossref","unstructured":"Qiu X, Sun T, Xu Y, Shao Y, Dai N, Huang X (2020) Pre-trained models for natural language processing: a survey. Sci China Technol Sci, 1\u201326","DOI":"10.1007\/s11431-020-1647-3"},{"key":"3190_CR16","unstructured":"Joseph T, Ratinov L, Bengio Y (2010) Word representations: a simple and general method for semi-supervised learning. Published as a conference paper at ACL"},{"key":"3190_CR17","doi-asserted-by":"crossref","unstructured":"Kaliyev A, Rybin SV, Matveev Y (2017) The pausing method based on brown clustering and word embedding. In: International conference on speech and computer","DOI":"10.1007\/978-3-319-66429-3_74"},{"key":"3190_CR18","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio Y, Ducharme R, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3:1137\u20131155","journal-title":"J Mach Learn Res"},{"key":"3190_CR19","unstructured":"Collobert R, Weston J (2007) Fast Semantic Extraction Using a Novel Neural Network Architecture. Published as a conference paper at ACL"},{"key":"3190_CR20","unstructured":"Guo J, Che W, Wang H, Liu T (2014) Learning sense-specific word embeddings by exploiting bilingual resources. In: proceedings of COLING, vol 2014, pp 497\u2013507"},{"key":"3190_CR21","first-page":"93","volume":"6","author":"S Chopra","year":"2016","unstructured":"Chopra S (2016) Abstractive sentence summarization with attentive recurrent neural networks. The Association for Computational Linguistics 6:93\u201398","journal-title":"The Association for Computational Linguistics"},{"key":"3190_CR22","doi-asserted-by":"crossref","unstructured":"Chen Y-C (2018) Fast Abstractive Summarization with Reinforce Selected Sentence Rewriting. The Association for Computational Linguistics","DOI":"10.18653\/v1\/P18-1063"},{"key":"3190_CR23","unstructured":"Vaswani A, Shazeer N, Polosukhin I (2017) Attention is all you need. InNeurIPS"},{"key":"3190_CR24","doi-asserted-by":"crossref","unstructured":"Zhang Z, Han X, Liu Z, Jiang X, Sun M, Liu Q (2019) ERNIE: enhanced language representation with informative entities. In: ACL","DOI":"10.18653\/v1\/P19-1139"},{"key":"3190_CR25","doi-asserted-by":"crossref","unstructured":"Joshi M, Chen D, Liu Y, Weld DS, Zettlemoyer L, Levy O (2019) SpanBERT:, Improving Pre-training by Representing and Predicting Spans. arXiv:1907.10529","DOI":"10.1162\/tacl_a_00300"},{"key":"3190_CR26","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Stoyanov V (2019) Roberta:, A robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"3190_CR27","unstructured":"Yang Z, Dai Z, Le QV (2019) XLNEt: Generalized autoregressive pretraining for language understanding. In: NeurIPS, pp 5754\u20135764"},{"key":"3190_CR28","unstructured":"Lauscher A, Vulic I, Glavas G (2019) Informing unsupervised pre-training with external linguistic knowledge. arXiv:1909.02339"},{"key":"3190_CR29","doi-asserted-by":"crossref","unstructured":"Peters ME, Smith NA (2019) Knowledge enhanced contextual word representations. In: EMNLP-IJCNLP","DOI":"10.18653\/v1\/D19-1005"},{"key":"3190_CR30","doi-asserted-by":"crossref","unstructured":"Liu W, Zhou P, Wang P (2019) K-BERT: Enabling language representation with knowledge graph. In: AAAI","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"3190_CR31","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu Y, Gu J, Goyal N, Li X, Edunov S, Ghazvininejad M, Zettlemoyer L (2020) Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics 8:726\u2013742","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"3190_CR32","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019) DistilBERT, a distilled version of BERT:, smaller, faster,cheaper and lighter. arXiv:1910.01108"},{"key":"3190_CR33","doi-asserted-by":"crossref","unstructured":"Shen S, Dong Z, Keutzer K (2020) Q-BERT: Hessian based ultra low precision quantization of BERT. In: AAAI","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"3190_CR34","doi-asserted-by":"crossref","unstructured":"Jiao X, Yin Y, Shang L, Jiang X, Chen X, Li L, Liu Q (2020) TinyBERT: distilling BERT for natural language understanding. In: Proceedings of the 2020 conference on empirical methods in natural language processing:, Findings, pp 4163\u20134174","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"3190_CR35","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.neunet.2020.01.018","volume":"124","author":"D-X Zhou","year":"2020","unstructured":"Zhou D-X (2020) Theory of deep convolutional neural networks: downsampling. Neural Netw 124:319\u2013327","journal-title":"Neural Netw"},{"key":"3190_CR36","doi-asserted-by":"crossref","unstructured":"Huang Z (2019) Mask Scoring R-CNN. Published as a conference paper at CVPR","DOI":"10.1109\/CVPR.2019.00657"},{"key":"3190_CR37","doi-asserted-by":"crossref","unstructured":"Xie H, Shi F, Wang D, et al. (2018) A novel attention based CNN model for emotion intensity prediction international conference on natural language processing and chinese computing. Springer, Cham","DOI":"10.1007\/978-3-319-99495-6_31"},{"key":"3190_CR38","doi-asserted-by":"crossref","unstructured":"Yin R, Wang Q, Li P, Li R, Wang B (2016) Multi-granularity chinese word embedding. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 981\u2013 986","DOI":"10.18653\/v1\/D16-1100"},{"key":"3190_CR39","doi-asserted-by":"crossref","unstructured":"Su T-R, Lee H-Y (2017) Learning chinese word representations from glyphs of characters. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp 264\u2013 273","DOI":"10.18653\/v1\/D17-1025"},{"key":"3190_CR40","doi-asserted-by":"publisher","first-page":"106548","DOI":"10.1016\/j.knosys.2020.106548","volume":"212","author":"JC-W Lin","year":"2021","unstructured":"Lin JC-W, Shao Y, Djenouri Y, Yun U (2021) As RNN: a recurrent neural network with an attention model for sequence labeling. Knowl-Based Syst 212:106548","journal-title":"Knowl-Based Syst"},{"key":"3190_CR41","unstructured":"Li J, Sun M (2007) Scalable term selection for text categorization. EMNLP-CoNLL, pp 774\u2013782"},{"key":"3190_CR42","unstructured":"Levow G-A (2006) The third international chinese language processing bakeoff: word segmentation and named entity recognition. Association for Computational Linguistics, pp 108\u2013117"},{"key":"3190_CR43","unstructured":"Shao C C, Liu T, Lai Y, Tseng Y, Tsai S (2019) DRCD:, a Chinese Machine Reading Comprehension Dataset. arXiv:1806.00920"},{"key":"3190_CR44","unstructured":"Yudong, L, Chinese scientific literature dataset. https:\/\/github.com\/P01son6415\/CSL"},{"key":"3190_CR45","doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional Neural Networks for Sentence Classification","DOI":"10.3115\/v1\/D14-1181"},{"key":"3190_CR46","doi-asserted-by":"crossref","unstructured":"Lai S, Xu L (2015) Recurrent Convolutional Neural Networks for Text Classification. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v29i1.9513"},{"key":"3190_CR47","unstructured":"Joulin A, Grave E, Bojanowski Mikolov T (2016) Fasttext. zip:, Compressing text classification models. arXiv:1612.03651"},{"key":"3190_CR48","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"3190_CR49","doi-asserted-by":"crossref","unstructured":"Wang Y, Sun Y, Ma Z, Gao L, Xu Y, Sun T (2020) Application of pre-training models in named entity recognition. In: 2020 12th international conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) (Vol. 1, pp. 23\u201326). IEEE","DOI":"10.1109\/IHMSC49165.2020.00013"},{"key":"3190_CR50","unstructured":"Wang Y, Ru LI, Zhang H, et al. (2018) Causal options in Chinese reading comprehension[J] Journal of Tsinghua University(Science and Technology)"},{"key":"3190_CR51","doi-asserted-by":"crossref","unstructured":"Wang W, Yang N (2017) Gated Self-Matching networks for reading comprehension and question answering. I Association for Computational Linguistics, pp 189\u2013198","DOI":"10.18653\/v1\/P17-1018"},{"key":"3190_CR52","doi-asserted-by":"crossref","unstructured":"He W, Liu K, Liu J, Lyu Y, Zhao S, Wang H (2018) Dureader: a Chinese machine reading comprehension dataset from real-world applications. In: Proceedings of the workshop on machine reading for question answering, pp 37\u201346","DOI":"10.18653\/v1\/W18-2605"},{"key":"3190_CR53","unstructured":"Yu AW, Dohan D, Luong MT, Zhao R, Chen K, Norouzi M, Le QV (2018) QANet: combining local convolution with global self-attention for reading comprehension. In: International conference on learning representations"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03190-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03190-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03190-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T19:22:33Z","timestamp":1668021753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03190-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,19]]},"references-count":53,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["3190"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03190-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,19]]},"assertion":[{"value":"4 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}