{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T10:10:19Z","timestamp":1773310219449,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031171192","type":"print"},{"value":"9783031171208","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-17120-8_11","type":"book-chapter","created":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T13:02:58Z","timestamp":1663938178000},"page":"131-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Kformer: Knowledge Injection in\u00a0Transformer Feed-Forward Layers"],"prefix":"10.1007","author":[{"given":"Yunzhi","family":"Yao","sequence":"first","affiliation":[]},{"given":"Shaohan","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Huajun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ningyu","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,24]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Chang, T.Y., Liu, Y., Gopalakrishnan, K., Hedayatnia, B., Zhou, P., Hakkani-Tur, D.: Incorporating commonsense knowledge graph in pretrained models for social commonsense tasks. In: Proceedings of DeeLIO: The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures (2020)","DOI":"10.18653\/v1\/2020.deelio-1.9"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Dai, D., Dong, L., Hao, Y., Sui, Z., Wei, F.: Knowledge neurons in pretrained transformers. In: Proceedings of ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"11_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL (2019)"},{"key":"11_CR4","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: Proceedings of NeurIPS (2019)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Geva, M., Schuster, R., Berant, J., Levy, O.: Transformer feed-forward layers are key-value memories. In: Proceedings of EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"11_CR6","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","volume":"2","author":"X Han","year":"2021","unstructured":"Han, X., et al.: Pre-trained models: past, present and future. AI Open 2, 225\u2013250 (2021)","journal-title":"AI Open"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Hao, Y., Dong, L., Wei, F., Xu, K.: Self-attention attribution: interpreting information interactions inside transformer. In: Proceedings of AAAI (2021)","DOI":"10.1609\/aaai.v35i14.17533"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Jin, D., Pan, E., Oufattole, N., Weng, W.H., Fang, H., Szolovits, P.: What disease does this patient have? A large-scale open domain question answering dataset from medical exams. arXiv preprint arXiv:2009.13081 (2020)","DOI":"10.20944\/preprints202105.0498.v1"},{"key":"11_CR9","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: K-BERT: enabling language representation with knowledge graph. In: Proceedings of AAAI (2020)","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Lv, S., et al.: Graph-based reasoning over heterogeneous external knowledge for commonsense question answering. In: Proceedings of AAAI (2020)","DOI":"10.1609\/aaai.v34i05.6364"},{"key":"11_CR12","unstructured":"Mitra, A., Banerjee, P., Pal, K.K., Mishra, S., Baral, C.: How additional knowledge can improve natural language commonsense question answering. arXiv Computation and Language (2020)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Ott, M., et al.: fairseq: A fast, extensible toolkit for sequence modeling. In: Proceedings of NAACL: Demonstrations (2019)","DOI":"10.18653\/v1\/N19-4009"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Robertson, S., Zaragoza, H.: The Probabilistic Relevance Framework: BM25 and Beyond. Now Publishers Inc., Norwell (2009)","DOI":"10.1561\/1500000019"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Sap, M., et al.: Atomic: an atlas of machine commonsense for if-then reasoning. In: Proceedings of AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Sap, M., Rashkin, H., Chen, D., Le Bras, R., Choi, Y.: Social IQa: commonsense reasoning about social interactions. In: Proceedings of EMNLP (2019)","DOI":"10.18653\/v1\/D19-1454"},{"key":"11_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of NeurIPS (2017)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Wang, P., Peng, N., Ilievski, F., Szekely, P., Ren, X.: Connecting the dots: a knowledgeable path generator for commonsense question answering. In: Findings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.369"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Wang, W., Tu, Z.: Rethinking the value of transformer components. In: Proceedings of COLING (2020)","DOI":"10.18653\/v1\/2020.coling-main.529"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Improving natural language inference using external knowledge in the science questions domain. In: Proceedings of AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33017208"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, C., Xu, R., Liu, Y., Zeng, M., Huang, X.: Fusing context into knowledge graph for commonsense reasoning. arXiv preprint arXiv:2012.04808 (2020)","DOI":"10.18653\/v1\/2021.findings-acl.102"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, N., et al.: Drop redundant, shrink irrelevant: selective knowledge injection for language pretraining. In: In Proceedings of IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/552"}],"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\/978-3-031-17120-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T13:05:24Z","timestamp":1663938324000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-17120-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031171192","9783031171208"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-17120-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"24 September 2022","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":"Guilin","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2022\/","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":"327","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":"73","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":"22% - 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)"}}]}}