{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:28:08Z","timestamp":1772908088290,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0109700"],"award-info":[{"award-number":["2020AAA0109700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206314"],"award-info":[{"award-number":["62206314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976233"],"award-info":[{"award-number":["61976233"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of Guangdong Province","award":["2022A1515011835"],"award-info":[{"award-number":["2022A1515011835"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation Funded Project","doi-asserted-by":"publisher","award":["2021M703687"],"award-info":[{"award-number":["2021M703687"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tnnls.2023.3265173","type":"journal-article","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T18:39:55Z","timestamp":1682966395000},"page":"12823-12835","source":"Crossref","is-referenced-by-count":1,"title":["Template-Based Contrastive Distillation Pretraining for Math Word Problem Solving"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0663-199X","authenticated-orcid":false,"given":"Jinghui","family":"Qin","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"given":"Zhicheng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}]},{"given":"Jiaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1088"},{"key":"ref2","first-page":"213","article-title":"Neural math word problem solver with reinforcement learning","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Huang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11981"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017144"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/736"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1272"},{"key":"ref7","first-page":"4011","article-title":"Teacher-student networks with multiple decoders for solving math word problem","volume-title":"Proc. 29th Int. Joint Conf. Artif. Intell.","author":"Zhang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.362"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.309"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.456"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1207\/s1532690xci0904_2"},{"key":"ref12","first-page":"2227","article-title":"Deep contextualized word representations","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","volume":"1","author":"Peters"},{"key":"ref13","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref14","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref15","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Advances in Neural Information Processing System","volume":"32","author":"Yang","year":"2019"},{"key":"ref16","first-page":"1536","article-title":"CodeBERT: A pre-trained model for programming and natural languages","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Feng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/485"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.455"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16547"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.127"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.68"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.195"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03855-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16629"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17538"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531824"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6479"},{"key":"ref32","article-title":"Incorporating BERT into neural machine translation","author":"Zhu","year":"2020","journal-title":"arXiv:2002.06823"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1623"},{"key":"ref36","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020","journal-title":"arXiv:2003.10555"},{"key":"ref37","first-page":"6894","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Gao"},{"key":"ref38","article-title":"Contrastive representation distillation","author":"Tian","year":"2019","journal-title":"arXiv:1910.10699"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5917"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5842"},{"key":"ref44","first-page":"1317","article-title":"Sequence-level knowledge distillation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Kim"},{"key":"ref45","first-page":"2077","article-title":"Attention-guided answer distillation for machine reading comprehension","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Hu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00816"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref50","first-page":"657","article-title":"Revisiting pre-trained models for Chinese natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Findings","author":"Cui"},{"key":"ref51","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1132"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1619"},{"key":"ref54","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1241"},{"key":"ref56","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref57","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"issue":"11","key":"ref58","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10663876\/10113691.pdf?arnumber=10113691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:14:59Z","timestamp":1725473699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10113691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":59,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3265173","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}