{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T04:53:18Z","timestamp":1767156798312,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533075"},{"type":"electronic","value":"9783031533082"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53308-2_8","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"98-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MRHF: Multi-stage Retrieval and\u00a0Hierarchical Fusion for\u00a0Textbook Question Answering"],"prefix":"10.1007","author":[{"given":"Peide","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Manabu","family":"Okumura","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"8_CR1","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR2","unstructured":"Fedus, W., Dean, J., Zoph, B.: A review of sparse expert models in deep learning. arXiv preprint arXiv:2209.01667 (2022)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-P\u00e9rez, J.M., Ortega, R.: ISAAQ-mastering textbook questions with pre-trained transformers and bottom-up and top-down attention. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5469\u20135479 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.441"},{"key":"8_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-86380-7_8","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"J He","year":"2021","unstructured":"He, J., Fu, X., Long, Z., Wang, S., Liang, C., Lin, H.: Textbook question answering with multi-type question learning and contextualized diagram representation. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12894, pp. 86\u201398. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86380-7_8"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"8_CR6","unstructured":"Honnibal, M., Montani, I.: spaCy 2: natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing (2017). to appear"},{"issue":"1","key":"8_CR7","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)","journal-title":"Neural Comput."},{"key":"8_CR8","unstructured":"Jiang, Y., et al.: Improving machine reading comprehension with single-choice decision and transfer learning. arXiv preprint arXiv:2011.03292 (2020)"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Jocher, G., et al.: ultralytics\/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration. Zenodo, January 2021. https:\/\/doi.org\/10.5281\/zenodo.4418161","DOI":"10.5281\/zenodo.4418161"},{"issue":"2","key":"8_CR10","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","volume":"6","author":"MI Jordan","year":"1994","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6(2), 181\u2013214 (1994)","journal-title":"Neural Comput."},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"8_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? Textbook question answering for multimodal machine comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4999\u20135007 (2017)","DOI":"10.1109\/CVPR.2017.571"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Kim, D., Kim, S., Kwak, N.: Textbook question answering with multi-modal context graph understanding and self-supervised open-set comprehension. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3568\u20133584 (2019)","DOI":"10.18653\/v1\/P19-1347"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: RACE: large-scale reading comprehension dataset from examinations. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 785\u2013794 (2017)","DOI":"10.18653\/v1\/D17-1082"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Su, H., Zhu, J., Wang, S., Zhang, B.: Textbook question answering under instructor guidance with memory networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3655\u20133663 (2018)","DOI":"10.1109\/CVPR.2018.00385"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Su, H., Zhu, J., Zhang, B.: Essay-anchor attentive multi-modal bilinear pooling for textbook question answering. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICME.2018.8486468"},{"key":"8_CR18","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Ma, J., Chai, Q., Liu, J., Yin, Q., Wang, P., Zheng, Q.: XTQA: span-level explanations for textbook question answering (2023)","DOI":"10.1109\/TNNLS.2023.3294991"},{"key":"8_CR20","unstructured":"Ma, J., Liu, J., Wang, Y., Li, J., Liu, T.: Relation-aware fine-grained reasoning network for textbook question answering. IEEE Transactions on Neural Networks and Learning Systems (2021)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-Networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, November 2019","DOI":"10.18653\/v1\/D19-1410"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-Networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"8_CR24","first-page":"8583","volume":"34","author":"C Riquelme","year":"2021","unstructured":"Riquelme, C., et al.: Scaling vision with sparse mixture of experts. Adv. Neural Inf. Process. Syst. 34, 8583\u20138595 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8_CR25","doi-asserted-by":"publisher","unstructured":"Robertson, S.E., Walker, S.: Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval. In: Croft, B.W., van Rijsbergen, C.J. (eds.) SIGIR \u201994, pp. 232\u2013241. Springer, London (1994). https:\/\/doi.org\/10.1007\/978-1-4471-2099-5_24","DOI":"10.1007\/978-1-4471-2099-5_24"},{"issue":"1\u201320","key":"8_CR26","first-page":"10","volume":"1","author":"S Rose","year":"2010","unstructured":"Rose, S., Engel, D., Cramer, N., Cowley, W.: Automatic keyword extraction from individual documents. Text Min. Appl. Theory 1(1\u201320), 10\u20131002 (2010)","journal-title":"Text Min. Appl. Theory"},{"key":"8_CR27","first-page":"16857","volume":"33","author":"K Song","year":"2020","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: MPNet: masked and permuted pre-training for language understanding. Adv. Neural Inf. Process. Syst. 33, 16857\u201316867 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8_CR28","first-page":"5776","volume":"33","author":"W Wang","year":"2020","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: MINILM: deep self-attention distillation for task-agnostic compression of pre-trained transformers. Adv. Neural Inf. Process. Syst. 33, 5776\u20135788 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109588","volume":"140","author":"F Xu","year":"2023","unstructured":"Xu, F., et al.: MoCA: incorporating domain pretraining and cross attention for textbook question answering. Pattern Recognit. 140, 109588 (2023)","journal-title":"Pattern Recognit."},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Ni, X., Ding, Y., Ke, Q.: Paragraph-level neural question generation with maxout pointer and gated self-attention networks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3901\u20133910 (2018)","DOI":"10.18653\/v1\/D18-1424"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53308-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:06:34Z","timestamp":1710241594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53308-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533075","9783031533082"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53308-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","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":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","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":"112","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":"38% - 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":"3.2","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":"3.2","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}