{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:20:15Z","timestamp":1742973615727,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030884826"},{"type":"electronic","value":"9783030884833"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-88483-3_34","type":"book-chapter","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T13:55:25Z","timestamp":1633874125000},"page":"422-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["When Few-Shot Learning Meets Large-Scale Knowledge-Enhanced Pre-training: Alibaba at FewCLUE"],"prefix":"10.1007","author":[{"given":"Ziyun","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyu","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengguang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"34_CR1","unstructured":"Bao, H., et al.: UniLMv2: pseudo-masked language models for unified language model pre-training. In: ICML, vol. 119, pp. 642\u2013652 (2020)"},{"key":"34_CR2","unstructured":"Bordes, A., Usunier, N., Garc\u00eda-Dur\u00e1n, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS, pp. 2787\u20132795 (2013)"},{"key":"34_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"34_CR4","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. CoRR abs\/1604.06174 (2016)"},{"key":"34_CR5","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Yang, Z., Wang, S., Hu, G.: Pre-training with whole word masking for Chinese BERT. CoRR abs\/1906.08101 (2019)"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J.G., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: ACL, pp. 2978\u20132988 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"34_CR7","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"34_CR8","unstructured":"Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. CoRR abs\/2012.15723 (2020)"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: CVPR, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"34_CR10","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: ICLR (2020)"},{"key":"34_CR11","unstructured":"Liu, X., et al.: GPT understands, too. CoRR abs\/2103.10385 (2021)"},{"key":"34_CR12","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019)"},{"key":"34_CR13","unstructured":"Micikevicius, P., et al.: Mixed precision training. CoRR abs\/1710.03740 (2017)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Knowledge enhanced contextual word representations. In: EMNLP, pp. 43\u201354 (2019)","DOI":"10.18653\/v1\/D19-1005"},{"key":"34_CR15","unstructured":"Phang, J., F\u00e9vry, T., Bowman, S.R.: Sentence encoders on stilts: supplementary training on intermediate labeled-data tasks. CoRR abs\/1811.01088 (2018)"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Qiu, M., et al.: EasyTransfer - a simple and scalable deep transfer learning platform for NLP applications. CIKM 2021 (2020). https:\/\/arxiv.org\/abs\/2011.09463","DOI":"10.1145\/3459637.3481911"},{"key":"34_CR17","unstructured":"Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., Huang, X.: Pre-trained models for natural language processing: a survey. CoRR abs\/2003.08271 (2020)"},{"key":"34_CR18","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: SIGKDD, pp. 3505\u20133506. ACM (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: Exploiting cloze-questions for few-shot text classification and natural language inference. In: EACL, pp. 255\u2013269 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Shin, T., Razeghi, Y., IV, R.L.L., Wallace, E., Singh, S.: AutoPrompt: eliciting knowledge from language models with automatically generated prompts. In: EMNLP, pp. 4222\u20134235 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"34_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"34_CR23","unstructured":"Wang, A., et al.: SuperGLUE: a stickier benchmark for general-purpose language understanding systems. In: NeurIPS, pp. 3261\u20133275 (2019)"},{"key":"34_CR24","unstructured":"Wang, S., Fang, H., Khabsa, M., Mao, H., Ma, H.: Entailment as few-shot learner. CoRR abs\/2104.14690 (2021)"},{"key":"34_CR25","unstructured":"Wang, W., et al.: StructBERT: incorporating language structures into pre-training for deep language understanding. In: ICLR (2020)"},{"key":"34_CR26","unstructured":"Wang, X., Gao, T., Zhu, Z., Liu, Z., Li, J., Tang, J.: KEPLER: a unified model for knowledge embedding and pre-trained language representation. CoRR abs\/1911.06136 (2019)"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Xu, L., et al.: CLUE: a Chinese language understanding evaluation benchmark. In: COLING, pp. 4762\u20134772 (2020)","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"34_CR28","unstructured":"Xu, L., Zhang, X., Dong, Q.: CLUECorpus 2020: a large-scale Chinese corpus for pre-training language model. CoRR abs\/2003.01355 (2020)"},{"key":"34_CR29","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J.G., Salakhutdinov, R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: NeurIPS, pp. 5754\u20135764 (2019)"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Yin, W., Rajani, N.F., Radev, D.R., Socher, R., Xiong, C.: Universal natural language processing with limited annotations: try few-shot textual entailment as a start. In: EMNLP, pp. 8229\u20138239 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.660"},{"key":"34_CR31","unstructured":"Zhang, D., et al.: E-BERT: a phrase and product knowledge enhanced language model for e-commerce. CoRR abs\/2009.02835 (2020)"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: ERNIE: enhanced language representation with informative entities. In: ACL, pp. 1441\u20131451 (2019)","DOI":"10.18653\/v1\/P19-1139"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88483-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:36:02Z","timestamp":1710257762000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88483-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030884826","9783030884833"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88483-3_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"446","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"66","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23 poster papers and 27 workshop papers are also included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}