{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:46:52Z","timestamp":1771958812654,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030858957","type":"print"},{"value":"9783030858964","type":"electronic"}],"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\/978-3-030-85896-4_26","type":"book-chapter","created":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T10:06:38Z","timestamp":1629281198000},"page":"332-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Difficulty-Controllable Visual Question Generation"],"prefix":"10.1007","author":[{"given":"Feng","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jiayuan","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Denkowski, M.J., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: WMT@ACL, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"26_CR3","unstructured":"Desai, T., Moldovan, D.I.: Towards predicting difficulty of reading comprehension questions. In: FLAIRS Conference, pp. 8\u201313 (2019)"},{"key":"26_CR4","unstructured":"dos Santos, C.N., Melnyk, I., Padhi, I.: Fighting offensive language on social media with unsupervised text style transfer. In: ACL, pp. 189\u2013194 (2018)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Du, X., Shao, J., Cardie, C.: Learning to ask: neural question generation for reading comprehension. In: ACL, pp. 1342\u20131352 (2017)","DOI":"10.18653\/v1\/P17-1123"},{"issue":"2","key":"26_CR6","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1037\/0096-3445.123.2.161","volume":"123","author":"R Egly","year":"1994","unstructured":"Egly, R., Driver, J., Rafal, R.D.: Shifting visual attention between objects and locations: evidence from normal and parietal lesion subjects. J. Exper. Psychol. Gen. 123(2), 161\u201377 (1994)","journal-title":"J. Exper. Psychol. Gen."},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wei, Z., Li, P., Lan, Y., Huang, X.: A question type driven framework to diversify visual question generation. In: Lang, J. (ed.) IJCAI, pp. 4048\u20134054 (2018)","DOI":"10.24963\/ijcai.2018\/563"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Gao, Y., Bing, L., Chen, W., Lyu, M.R., King, I.: Difficulty controllable generation of reading comprehension questions. In: IJCAI, pp. 4968\u20134974 (2019)","DOI":"10.24963\/ijcai.2019\/690"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR, pp. 6325\u20136334 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Ha, L.A., Yaneva, V., Baldwin, P., Mee, J.: Predicting the difficulty of multiple choice questions in a high-stakes medical exam. In: BEA@ACL, pp. 11\u201320 (2019)","DOI":"10.18653\/v1\/W19-4402"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR12","unstructured":"Heilman, M., Smith, N.A.: Good question! statistical ranking for question generation. In: HLT-NAACL, pp. 609\u2013617 (2010)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Jain, U., Lazebnik, S., Schwing, A.G.: Two can play this game: visual dialog with discriminative question generation and answering. In: CVPR, pp. 5754\u20135763 (2018)","DOI":"10.1109\/CVPR.2018.00603"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Jain, U., Zhang, Z., Schwing, A.G.: Creativity: generating diverse questions using variational autoencoders. In: CVPR, pp. 5415\u20135424 (2017)","DOI":"10.1109\/CVPR.2017.575"},{"key":"26_CR15","unstructured":"Kim, J., Jun, J., Zhang, B.: Bilinear attention networks. In: NIPS, pp. 1571\u20131581 (2018)"},{"key":"26_CR16","doi-asserted-by":"publisher","first-page":"6602","DOI":"10.1609\/aaai.v33i01.33016602","volume":"33","author":"Y Kim","year":"2019","unstructured":"Kim, Y., Lee, H., Shin, J., Jung, K.: Improving neural question generation using answer separation. AAAI 33, 6602\u20136609 (2019)","journal-title":"AAAI"},{"key":"26_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Krishna, R., Bernstein, M., Fei-Fei, L.: Information maximizing visual question generation. In: CVPR, pp. 2008\u20132018 (2019)","DOI":"10.1109\/CVPR.2019.00211"},{"key":"26_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"26_CR20","first-page":"382","volume":"11778","author":"V Kumar","year":"2019","unstructured":"Kumar, V., Hua, Y., Ramakrishnan, G., Qi, G., Gao, L., Li, Y.: Difficulty-controllable multi-hop question generation from knowledge graphs. ISWC 11778, 382\u2013398 (2019)","journal-title":"ISWC"},{"key":"26_CR21","unstructured":"Kunichika, H., Katayama, T., Hirashima, T., Takeuchi, A.: Automated question generation methods for intelligent English learning systems and its evaluation. In: Proceedings of ICCE (2004)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Labutov, I., Basu, S., Vanderwende, L.: Deep questions without deep understanding. In: ACL, pp. 889\u2013898 (2015)","DOI":"10.3115\/v1\/P15-1086"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Li, J., Gao, Y., Bing, L., King, I., Lyu, M.R.: Improving question generation with to the point context. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) EMNLP-IJCNLP, pp. 3214\u20133224 (2019)","DOI":"10.18653\/v1\/D19-1317"},{"issue":"2","key":"26_CR24","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1007\/s11280-018-0531-z","volume":"22","author":"X Li","year":"2019","unstructured":"Li, X., Zhou, Z., Chen, L., Gao, L.: Residual attention-based LSTM for video captioning. World Wide Web 22(2), 621\u2013636 (2019)","journal-title":"World Wide Web"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Visual question generation as dual task of visual question answering. In: CVPR, pp. 6116\u20136124 (2018)","DOI":"10.1109\/CVPR.2018.00640"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Liao, Y., Bing, L., Li, P., Shi, S., Lam, W., Zhang, T.: Quase: sequence editing under quantifiable guidance. In: EMNLP, pp. 3855\u20133864 (2018)","DOI":"10.18653\/v1\/D18-1420"},{"key":"26_CR27","unstructured":"Lin, C.: ROUGE: a package for automatic evaluation of summaries, pp. 74\u201381 (2004)"},{"key":"26_CR28","unstructured":"Lindberg, D., Popowich, F., Nesbit, J.C., Winne, P.H.: Generating natural language questions to support learning on-line. In: ENLG, pp. 105\u2013114 (2013)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhu, Q., Zhou, Y., Li, X.: Improving question generation with sentence-level semantic matching and answer position inferring. In: AAAI, pp. 8464\u20138471 (2020)","DOI":"10.1609\/aaai.v34i05.6366"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., Vanderwende, L.: Generating natural questions about an image. In: ACL (2016)","DOI":"10.18653\/v1\/P16-1170"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Nema, P., Mohankumar, A.K., Khapra, M.M., Srinivasan, B.V., Ravindran, B.: Let\u2019s ask again: refine network for automatic question generation. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) EMNLP-IJCNLP, pp. 3312\u20133321 (2019)","DOI":"10.18653\/v1\/D19-1326"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"26_CR33","unstructured":"Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: NIPS, pp. 2953\u20132961 (2015)"},{"key":"26_CR34","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"issue":"1\u20132","key":"26_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0010-0277(00)00152-9","volume":"80","author":"BJ Scholl","year":"2001","unstructured":"Scholl, B.J.: Objects and attention: the state of the art. Cognition 80(1\u20132), 1\u201346 (2001)","journal-title":"Cognition"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Scialom, T., Piwowarski, B., Staiano, J.: Self-attention architectures for answer-agnostic neural question generation. In: Korhonen, A., Traum, D.R., M\u00e0rquez, L. (eds.) ACL, pp. 6027\u20136032 (2019)","DOI":"10.18653\/v1\/P19-1604"},{"key":"26_CR37","unstructured":"Sharma, S., El Asri, L., Schulz, H., Zumer, J.: Relevance of unsupervised metrics in task-oriented dialogue for evaluating natural language generation. arXiv:1706.09799 (2017)"},{"key":"26_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Teney, D., Anderson, P., He, X., van den Hengel, A.: Tips and tricks for visual question answering: learnings from the 2017 challenge. In: CVPR 2018, pp. 4223\u20134232 (2017)","DOI":"10.1109\/CVPR.2018.00444"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van den Hengel, A.: Graph-structured representations for visual question answering. In: CVPR, pp. 3233\u20133241 (2017)","DOI":"10.1109\/CVPR.2017.344"},{"issue":"3","key":"26_CR41","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1007\/s11280-018-0548-3","volume":"22","author":"H Tian","year":"2019","unstructured":"Tian, H., Tao, Y., Pouyanfar, S., Chen, S.-C., Shyu, M.-L.: Multimodal deep representation learning for video classification. World Wide Web 22(3), 1325\u20131341 (2019)","journal-title":"World Wide Web"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Tuan, L.A., Shah, D.J., Barzilay, R.: Capturing greater context for question generation. In: AAAI, pp. 9065\u20139072 (2020)","DOI":"10.1609\/aaai.v34i05.6440"},{"key":"26_CR43","unstructured":"Wajeeha, D., et al.: Difficulty index, discrimination index and distractor efficiency in multiple choice questions. Ann. PIMS 4 (2018). ISSN:1815\u20132287"},{"issue":"2","key":"26_CR44","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1007\/s11280-018-0541-x","volume":"22","author":"X Xu","year":"2019","unstructured":"Xu, X., He, L., Lu, H., Gao, L., Ji, Y.: Deep adversarial metric learning for cross-modal retrieval. World Wide Web 22(2), 657\u2013672 (2019)","journal-title":"World Wide Web"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, S., Qu, L., You, S., Yang, Z., Zhang, J.: Automatic generation of grounded visual questions. In: Sierra, C. (ed.) IJCAI, pp. 4235\u20134243 (2017)","DOI":"10.24963\/ijcai.2017\/592"},{"key":"26_CR46","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: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) EMNLP, pp. 3901\u20133910 (2018)","DOI":"10.18653\/v1\/D18-1424"},{"key":"26_CR47","first-page":"662","volume":"10619","author":"Q Zhou","year":"2017","unstructured":"Zhou, Q., Yang, N., Wei, F., Tan, C., Bao, H., Zhou, M.: Neural question generation from text: a preliminary study. NLPCC 10619, 662\u2013671 (2017)","journal-title":"NLPCC"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, W., Zhang, M., Wu, Y.: Question-type driven question generation. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) EMNLP-IJCNLP, pp. 6031\u20136036 (2019)","DOI":"10.18653\/v1\/D19-1622"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85896-4_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T08:37:42Z","timestamp":1632904662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85896-4_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030858957","9783030858964"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85896-4_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"19 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"23 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2021","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"184","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":"44","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":"24","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":"24% - 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":"3.6","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":"6.38","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)"}}]}}