{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:11:09Z","timestamp":1781737869754,"version":"3.54.5"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031446924","type":"print"},{"value":"9783031446931","type":"electronic"}],"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\/978-3-031-44693-1_47","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"604-615","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Mixture-of-Experts for\u00a0Biomedical Question Answering"],"prefix":"10.1007","author":[{"given":"Damai","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajuan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifang","family":"Sui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baobao","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"47_CR1","unstructured":"Alsentzer, E., et al.: Publicly available clinical BERT embeddings. CoRR abs\/1904.03323 (2019). http:\/\/arxiv.org\/abs\/1904.03323"},{"issue":"1","key":"47_CR2","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/BF00247653","volume":"1","author":"DP Bertsekas","year":"1992","unstructured":"Bertsekas, D.P.: Auction algorithms for network flow problems: a tutorial introduction. Comput. Optim. Appl. 1(1), 7\u201366 (1992). https:\/\/doi.org\/10.1007\/BF00247653","journal-title":"Comput. Optim. Appl."},{"key":"47_CR3","doi-asserted-by":"publisher","unstructured":"Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. In: ACL 2017, pp. 1870\u20131879 (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1171","DOI":"10.18653\/v1\/P17-1171"},{"key":"47_CR4","doi-asserted-by":"crossref","unstructured":"Dai, D., Dong, L., Ma, S., Zheng, B., Sui, Z., Chang, B., Wei, F.: StableMoE: stable routing strategy for mixture of experts. In: ACL 2022 (2022)","DOI":"10.18653\/v1\/2022.acl-long.489"},{"key":"47_CR5","doi-asserted-by":"publisher","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 (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"47_CR6","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. CoRR abs\/2101.03961 (2021). https:\/\/arxiv.org\/abs\/2101.03961"},{"key":"47_CR7","unstructured":"Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing. CoRR abs\/2007.15779 (2020). https:\/\/arxiv.org\/abs\/2007.15779"},{"key":"47_CR8","doi-asserted-by":"publisher","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: adapt language models to domains and tasks. In: ACL 2020, pp. 8342\u20138360 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.740","DOI":"10.18653\/v1\/2020.acl-main.740"},{"issue":"1","key":"47_CR9","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991). https:\/\/doi.org\/10.1162\/neco.1991.3.1.79","journal-title":"Neural Comput."},{"key":"47_CR10","doi-asserted-by":"crossref","unstructured":"Jin, D., Pan, E., Oufattole, N., Weng, W., Fang, H., Szolovits, P.: What disease does this patient have? A large-scale open domain question answering dataset from medical exams. CoRR abs\/2009.13081 (2020). https:\/\/arxiv.org\/abs\/2009.13081","DOI":"10.20944\/preprints202105.0498.v1"},{"issue":"4","key":"47_CR11","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinform. 36(4), 1234\u20131240 (2020). https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinform."},{"key":"47_CR12","unstructured":"Lepikhin, D., et al.: GShard: scaling giant models with conditional computation and automatic sharding. In: ICLR 2021 (2021). https:\/\/openreview.net\/forum?id=qrwe7XHTmYb"},{"key":"47_CR13","unstructured":"Lewis, M., Bhosale, S., Dettmers, T., Goyal, N., Zettlemoyer, L.: BASE layers: simplifying training of large, sparse models. In: ICML 2021. Proceedings of Machine Learning Research, vol. 139, pp. 6265\u20136274 (2021). http:\/\/proceedings.mlr.press\/v139\/lewis21a.html"},{"key":"47_CR14","doi-asserted-by":"publisher","unstructured":"Li, D., Hu, B., Chen, Q., Peng, W., Wang, A.: Towards medical machine reading comprehension with structural knowledge and plain text. In: EMNLP 2020, pp. 1427\u20131438 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.111","DOI":"10.18653\/v1\/2020.emnlp-main.111"},{"key":"47_CR15","unstructured":"Liu, Y., Chowdhury, S., Zhang, C., Caragea, C., Yu, P.S.: Interpretable multi-step reasoning with knowledge extraction on complex healthcare question answering. CoRR abs\/2008.02434 (2020). https:\/\/arxiv.org\/abs\/2008.02434"},{"key":"47_CR16","unstructured":"Liu, Yet al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019). http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"47_CR17","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in Adam. CoRR abs\/1711.05101 (2017). http:\/\/arxiv.org\/abs\/1711.05101"},{"key":"47_CR18","doi-asserted-by":"crossref","unstructured":"Meng, Z., Liu, F., Clark, T.H., Shareghi, E., Collier, N.: Mixture-of-partitions: infusing large biomedical knowledge graphs into BERT. In: EMNLP 2021, pp. 4672\u20134681 (2021). https:\/\/aclanthology.org\/2021.emnlp-main.383","DOI":"10.18653\/v1\/2021.emnlp-main.383"},{"key":"47_CR19","doi-asserted-by":"publisher","unstructured":"Pampari, A., Raghavan, P., Liang, J.J., Peng, J.: emrQA: a large corpus for question answering on electronic medical records. In: EMNLP 2018, pp. 2357\u20132368 (2018). https:\/\/doi.org\/10.18653\/v1\/d18-1258","DOI":"10.18653\/v1\/d18-1258"},{"key":"47_CR20","unstructured":"Roller, S., Sukhbaatar, S., Szlam, A., Weston, J.: Hash layers for large sparse models. CoRR abs\/2106.04426 (2021). https:\/\/arxiv.org\/abs\/2106.04426"},{"key":"47_CR21","unstructured":"Seo, M.J., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. In: ICLR 2017 (2017). https:\/\/openreview.net\/forum?id=HJ0UKP9ge"},{"key":"47_CR22","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In: ICLR 2017 (2017). https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"47_CR23","unstructured":"Sun, Y., et al.: ERNIE: enhanced representation through knowledge integration. CoRR abs\/1904.09223 (2019). http:\/\/arxiv.org\/abs\/1904.09223"},{"key":"47_CR24","unstructured":"Tsatsaronis, G., et al.: BioASQ: a challenge on large-scale biomedical semantic indexing and question answering. In: AAAI 2012 (2012). http:\/\/www.aaai.org\/ocs\/index.php\/FSS\/FSS12\/paper\/view\/5600"},{"key":"47_CR25","doi-asserted-by":"publisher","unstructured":"Vilares, D., G\u00f3mez-Rodr\u00edguez, C.: HEAD-QA: a healthcare dataset for complex reasoning. In: ACL 2019, pp. 960\u2013966 (2019). https:\/\/doi.org\/10.18653\/v1\/p19-1092","DOI":"10.18653\/v1\/p19-1092"}],"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\/978-3-031-44693-1_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T08:26:38Z","timestamp":1696839998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44693-1_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446924","9783031446931"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44693-1_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}