{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:15:54Z","timestamp":1770228954156,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416811","type":"print"},{"value":"9783031416828","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\/978-3-031-41682-8_5","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"66-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["RealCQA: Scientific Chart Question Answering as\u00a0a\u00a0Test-Bed for\u00a0First-Order Logic"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8648-9625","authenticated-orcid":false,"given":"Saleem","family":"Ahmed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhavin","family":"Jawade","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubham","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7118-9280","authenticated-orcid":false,"given":"Srirangaraj","family":"Setlur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5318-7409","authenticated-orcid":false,"given":"Venu","family":"Govindaraju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, S., Davila, K., Setlur, S., Govindaraju, V.: Equation attention relationship network (earn) : a geometric deep metric framework for learning similar math expression embedding. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6282\u20136289 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412619","DOI":"10.1109\/ICPR48806.2021.9412619"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: DocFormer: end-to-end transformer for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"5_CR3","unstructured":"Barcel\u00f3, P., Kostylev, E.V., Monet, M., P\u00e9rez, J., Reutter, J., Silva, J.P.: The logical expressiveness of graph neural networks. In: 8th International Conference on Learning Representations (ICLR 2020) (2020)"},{"key":"5_CR4","unstructured":"Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)"},{"key":"5_CR5","unstructured":"Besold, T.R., et al.: Neural-symbolic learning and reasoning: a survey and interpretation. CoRR abs\/1711.03902 (2017)"},{"key":"5_CR6","unstructured":"Borchmann, \u0141., et al.: Due: End-to-end document understanding benchmark. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"5_CR7","unstructured":"Chang, S., Palzer, D., Li, J., Fosler-Lussier, E., Xiao, N.: MapQA: a dataset for question answering on choropleth maps. arXiv preprint arXiv:2211.08545 (2022)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Chaudhry, R., Shekhar, S., Gupta, U., Maneriker, P., Bansal, P., Joshi, A.: Leaf-QA: locate, encode & attend for figure question answering. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3512\u20133521 (2020)","DOI":"10.1109\/WACV45572.2020.9093269"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Chen, C., et al.: Neural caption generation over figures. In: Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, pp. 482\u2013485 (2019)","DOI":"10.1145\/3341162.3345601"},{"key":"5_CR10","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: International Conference on Machine Learning, pp. 1931\u20131942. PMLR (2021)"},{"key":"5_CR11","doi-asserted-by":"publisher","unstructured":"Davila, K., Xu, F., Ahmed, S., Mendoza, D.A., Setlur, S., Govindaraju, V.: ICPR 2022: challenge on harvesting raw tables from infographics (chart-infographics). In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 4995\u20135001 (2022). https:\/\/doi.org\/10.1109\/ICPR56361.2022.9956289","DOI":"10.1109\/ICPR56361.2022.9956289"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Du, Q., Wang, Q., Li, K., Tian, J., Xiao, L., Jin, Y.: CALM: commen-sense knowledge augmentation for document image understanding. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3282\u20133290 (2022)","DOI":"10.1145\/3503161.3548321"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Eisenschlos, J.M., Gor, M., M\u00fcller, T., Cohen, W.W.: MATE: multi-view attention for table transformer efficiency. CoRR abs\/2109.04312 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.600"},{"key":"5_CR14","first-page":"39","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. Adv. Neural. Inf. Process. Syst. 34, 39\u201350 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Herzig, J., Nowak, P.K., M\u00fcller, T., Piccinno, F., Eisenschlos, J.M.: Tapas: weakly supervised table parsing via pre-training. arXiv preprint arXiv:2004.02349 (2020)","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Jawade, B., Mohan, D.D., Ali, N.M., Setlur, S., Govindaraju, V.: NAPReg: nouns as proxies regularization for semantically aware cross-modal embeddings. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1135\u20131144 (2023)","DOI":"10.1109\/WACV56688.2023.00119"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B., Cohen, S., Kanan, C.: DVQA: understanding data visualizations via question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5648\u20135656 (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"5_CR18","unstructured":"Kaliszyk, C., Chollet, F., Szegedy, C.: HolStep: a machine learning dataset for higher-order logic theorem proving. arXiv preprint arXiv:1703.00426 (2017)"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Kodali, V., Berleant, D.: Recent, rapid advancement in visual question answering: a review. In: 2022 IEEE International Conference on Electro Information Technology (eIT), pp. 139\u2013146 (2022). https:\/\/doi.org\/10.1109\/eIT53891.2022.9813988","DOI":"10.1109\/eIT53891.2022.9813988"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Levy, M., Ben-Ari, R., Lischinski, D.: Classification-regression for chart comprehension. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13696, pp. 469\u2013484. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_27","DOI":"10.1007\/978-3-031-20059-5_27"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: SelfDoc: self-supervised document representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652\u20135660 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: MatCha: enhancing visual language pretraining with math reasoning and chart derendering. arXiv preprint arXiv:2212.09662 (2022)","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"5_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-030-99739-7_51","volume-title":"Advances in Information Retrieval","author":"B Mansouri","year":"2022","unstructured":"Mansouri, B., Agarwal, A., Oard, D.W., Zanibbi, R.: Advancing math-aware search: the ARQMath-3 lab at CLEF 2022. In: Hagen, M., et al. (eds.) ECIR 2022. LNCS, vol. 13186, pp. 408\u2013415. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-99739-7_51"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: A dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1527\u20131536 (2020)","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"5_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-030-86331-9_47","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Powalski","year":"2021","unstructured":"Powalski, R., Borchmann, \u0141, Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa\u0142ka, G.: Going Full-TILT Boogie on document understanding with text-image-layout transformer. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 732\u2013747. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_47"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Qi, L., et al.: Dureadervis: a chinese dataset for open-domain document visual question answering. In: Findings of the Association for Computational Linguistics: ACL 2022. pp. 1338\u20131351 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.105"},{"key":"5_CR29","unstructured":"\u0160\u010davnick\u00e1, \u0160., \u0160tef\u00e1nik, M., Kadl\u010d\u00edk, M., Geletka, M., Sojka, P.: Towards general document understanding through question answering. RASLAN 2022 Recent Advances in Slavonic Natural Language Processing, p. 183 (2022)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Singh, H., Shekhar, S.: Stl-cqa: Structure-based transformers with localization and encoding for chart question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3275\u20133284 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.264"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Yoshida, S.: VisualMRC: machine reading comprehension on document images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 13878\u201313888 (2021)","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"5_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1007\/978-3-030-86337-1_42","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"R Tito","year":"2021","unstructured":"Tito, R., Mathew, M., Jawahar, C.V., Valveny, E., Karatzas, D.: ICDAR 2021 Competition on Document Visual Question Answering. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12824, pp. 635\u2013649. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_42"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: A region-based document VQA. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4909\u20134920 (2022)","DOI":"10.1145\/3503161.3548172"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, F., Lei, W., Feng, F., Wang, C., Zhang, H., Chua, T.S.: Towards complex document understanding by discrete reasoning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4857\u20134866 (2022)","DOI":"10.1145\/3503161.3548422"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41682-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:17:27Z","timestamp":1692343047000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41682-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416811","9783031416828"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41682-8_5","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":"19 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","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":"154","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":"49% - 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":"2.89","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":"1.50","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)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}