{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T15:50:11Z","timestamp":1763308211370,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446955"},{"type":"electronic","value":"9783031446962"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44696-2_60","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:03:59Z","timestamp":1696669439000},"page":"772-783","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Neural Knowledge Bank for\u00a0Pretrained Transformers"],"prefix":"10.1007","author":[{"given":"Damai","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingxiu","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajuan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifang","family":"Sui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"60_CR1","unstructured":"Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. In: EMNLP 2013, pp. 1533\u20131544 (2013)"},{"key":"60_CR2","unstructured":"Cao, B., et al.: Knowledgeable or educated guess? Revisiting language models as knowledge bases. In: ACL\/IJCNLP 2021, pp. 1860\u20131874 (2021)"},{"key":"60_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. In: ACL 2017, pp. 1870\u20131879 (2017)","DOI":"10.18653\/v1\/P17-1171"},{"key":"60_CR4","unstructured":"Clark, K., Luong, M., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generators. In: ICLR 2020. OpenReview.net (2020)"},{"key":"60_CR5","doi-asserted-by":"crossref","unstructured":"Dai, D., Dong, L., Hao, Y., Sui, Z., Chang, B., Wei, F.: Knowledge neurons in pretrained transformers. In: ACL 2022, pp. 8493\u20138502 (2022)","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"60_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019, pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"60_CR7","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: NeurIPS 2019, pp. 13042\u201313054 (2019)"},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Elazar, Y., et al.: Measuring and improving consistency in pretrained language models. CoRR abs\/2102.01017 (2021)","DOI":"10.1162\/tacl_a_00410"},{"key":"60_CR9","doi-asserted-by":"crossref","unstructured":"Geva, M., Caciularu, A., Wang, K.R., Goldberg, Y.: Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. CoRR abs\/2203.14680 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.3"},{"key":"60_CR10","doi-asserted-by":"crossref","unstructured":"Geva, M., Schuster, R., Berant, J., Levy, O.: Transformer feed-forward layers are key-value memories. CoRR abs\/2012.14913 (2020)","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"60_CR11","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: REALM: retrieval-augmented language model pre-training. CoRR abs\/2002.08909 (2020)"},{"key":"60_CR12","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1162\/tacl_a_00324","volume":"8","author":"Z Jiang","year":"2020","unstructured":"Jiang, Z., Xu, F.F., Araki, J., Neubig, G.: How can we know what language models know? Trans. Assoc. Comput. Linguist. 8, 423\u2013438 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"60_CR13","first-page":"452","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 452\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"60_CR14","doi-asserted-by":"crossref","unstructured":"Lee, K., Chang, M., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. In: ACL 2019, pp. 6086\u20136096 (2019)","DOI":"10.18653\/v1\/P19-1612"},{"key":"60_CR15","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches out, pp. 74\u201381 (2004)"},{"key":"60_CR16","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: K-BERT: enabling language representation with knowledge graph. In: AAAI 2020, pp. 2901\u20132908. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"60_CR17","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019)"},{"key":"60_CR18","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in Adam. CoRR abs\/1711.05101 (2017)"},{"key":"60_CR19","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., Lapata, M.: Don\u2019t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. In: EMNLP 2018, pp. 1797\u20131807. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1206"},{"key":"60_CR20","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Knowledge enhanced contextual word representations. In: EMNLP-IJCNLP 2019, pp. 43\u201354. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1005"},{"key":"60_CR21","doi-asserted-by":"crossref","unstructured":"Petroni, F., et al.: Language models as knowledge bases? In: EMNLP-IJCNLP 2019, pp. 2463\u20132473. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1250"},{"key":"60_CR22","unstructured":"P\u00f6rner, N., Waltinger, U., Sch\u00fctze, H.: BERT is not a knowledge base (yet): factual knowledge vs. name-based reasoning in unsupervised QA. CoRR abs\/1911.03681 (2019)"},{"key":"60_CR23","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. In: Bojar, O., et al. (eds.) WMT 2018, pp. 186\u2013191. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/W18-6319"},{"issue":"140","key":"60_CR24","first-page":"1","volume":"21","author":"C Raffel","year":"2020","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\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"60_CR25","doi-asserted-by":"crossref","unstructured":"Roberts, A., Raffel, C., Shazeer, N.: How much knowledge can you pack into the parameters of a language model? In: EMNLP 2020, pp. 5418\u20135426. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"60_CR26","unstructured":"Shazeer, N., Stern, M.: Adafactor: adaptive learning rates with sublinear memory cost. In: ICML 2018, pp. 4603\u20134611 (2018)"},{"key":"60_CR27","unstructured":"Vaswani, A., et al.: In: NeurIPS 2017, pp. 5998\u20136008 (2017)"},{"key":"60_CR28","doi-asserted-by":"crossref","unstructured":"Vilares, D., G\u00f3mez-Rodr\u00edguez, C.: HEAD-QA: a healthcare dataset for complex reasoning. In: ACL 2019, pp. 960\u2013966 (2019)","DOI":"10.18653\/v1\/P19-1092"},{"key":"60_CR29","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: K-adapter: infusing knowledge into pre-trained models with adapters. In: ACL-IJCNLP 2021. Findings of ACL, vol. ACL\/IJCNLP 2021, pp. 1405\u20131418. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.findings-acl.121"},{"key":"60_CR30","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1162\/tacl_a_00360","volume":"9","author":"X Wang","year":"2021","unstructured":"Wang, X., et al.: KEPLER: a unified model for knowledge embedding and pre-trained language representation. Trans. Assoc. Comput. Linguist. 9, 176\u2013194 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"60_CR31","doi-asserted-by":"crossref","unstructured":"Yao, Y., Huang, S., Zhang, N., Dong, L., Wei, F., Chen, H.: Kformer: knowledge injection in transformer feed-forward layers. CoRR abs\/2201.05742 (2022)","DOI":"10.1007\/978-3-031-17120-8_11"},{"key":"60_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 2019, pp. 1441\u20131451. Association for Computational Linguistics (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\/978-3-031-44696-2_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:12:56Z","timestamp":1696669976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44696-2_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446955","9783031446962"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44696-2_60","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","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":"Foshan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","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":"478","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":"143","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":"30% - 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":"4","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)"}}]}}