{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:03:21Z","timestamp":1772910201280,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Progetti di Rilevante Interesse Nazionale","award":["2020TA3K9N"],"award-info":[{"award-number":["2020TA3K9N"]}]},{"name":"MUR National Recovery and Resilience Plan","award":["PE0000013-PE00000014-IR0000013"],"award-info":[{"award-number":["PE0000013-PE00000014-IR0000013"]}]},{"name":"EC H2020RIA","award":["871042"],"award-info":[{"award-number":["871042"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591930","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"2619-2628","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Multimodal Neural Databases"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5515-634X","authenticated-orcid":false,"given":"Giovanni","family":"Trappolini","sequence":"first","affiliation":[{"name":"Sapienza University, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8483-2725","authenticated-orcid":false,"given":"Andrea","family":"Santilli","sequence":"additional","affiliation":[{"name":"Sapienza University, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0091-7241","authenticated-orcid":false,"given":"Emanuele","family":"Rodol\u00e0","sequence":"additional","affiliation":[{"name":"Sapienza University, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8717-7356","authenticated-orcid":false,"given":"Alon","family":"Halevy","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7669-9055","authenticated-orcid":false,"given":"Fabrizio","family":"Silvestri","sequence":"additional","affiliation":[{"name":"Sapienza University & ISTI-CNR, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Natural language interfaces to databases--an introduction. Natural language engineering","author":"Androutsopoulos Ion","year":"1995","unstructured":"Ion Androutsopoulos, Graeme D Ritchie, and Peter Thanisch. 1995. Natural language interfaces to databases--an introduction. Natural language engineering, Vol. 1, 1 (1995), 29--81."},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 1298--1312","author":"Baevski Alexei","year":"2022","unstructured":"Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, and Michael Auli. 2022. Data2vec: A general framework for self-supervised learning in speech, vision and language. In International Conference on Machine Learning. PMLR, 1298--1312."},{"key":"e_1_3_2_2_3_1","volume-title":"Kriti Aggarwal, Subhojit Som, and Furu Wei.","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, and Furu Wei. 2021. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. arXiv preprint arXiv:2111.02358 (2021)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1160"},{"key":"e_1_3_2_2_5_1","volume-title":"Search Computing","author":"Bozzon Alessandro","unstructured":"Alessandro Bozzon and Piero Fraternali. 2010. Multimedia and multimodal information retrieval. In Search Computing. Springer, 135--155."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532682"},{"key":"e_1_3_2_2_7_1","volume-title":"WebQA: Multihop and Multimodal QA. CoRR","author":"Chang Yingshan","year":"2021","unstructured":"Yingshan Chang, Mridu Narang, Hisami Suzuki, Guihong Cao, Jianfeng Gao, and Yonatan Bisk. 2021. WebQA: Multihop and Multimodal QA. CoRR, Vol. abs\/2109.00590 (2021). showeprint[arXiv]2109.00590 https:\/\/arxiv.org\/abs\/2109.00590"},{"key":"e_1_3_2_2_8_1","volume-title":"Pali: A jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794","author":"Chen Xi","year":"2022","unstructured":"Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, et al. 2022. Pali: A jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_11_1","unstructured":"Alon Y Halevy Oren Etzioni AnHai Doan Zachary G Ives Jayant Madhavan Luke K McDowell and Igor Tatarinov. 2003. Crossing the Structure Chasm.. In CIDR."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/253262.253291"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331213"},{"key":"e_1_3_2_2_14_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735461.2735468"},{"key":"e_1_3_2_2_17_1","volume-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","unstructured":"Gr\u00e9goire Mialon Roberto Dess\u00ec Maria Lomeli Christoforos Nalmpantis Ram Pasunuru Roberta Raileanu Baptiste Rozi\u00e8re Timo Schick Jane Dwivedi-Yu Asli Celikyilmaz Edouard Grave Yann LeCun and Thomas Scialom. 2023. Augmented Language Models: a Survey. https:\/\/doi.org\/10.48550\/ARXIV.2302.07842","DOI":"10.48550\/ARXIV.2302.07842"},{"key":"e_1_3_2_2_20_1","volume-title":"Compositional semantic parsing on semi-structured tables. arXiv preprint arXiv:1508.00305","author":"Pasupat Panupong","year":"2015","unstructured":"Panupong Pasupat and Percy Liang. 2015. Compositional semantic parsing on semi-structured tables. arXiv preprint arXiv:1508.00305 (2015)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_2_22_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_23_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. OpenAI Blog. https:\/\/openai.com\/blog\/better-language-models\/"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2727--2737","author":"Rao Jun","year":"2022","unstructured":"Jun Rao, Fei Wang, Liang Ding, Shuhan Qi, Yibing Zhan, Weifeng Liu, and Dacheng Tao. 2022. Where Does the Performance Improvement Come From? -A Reproducibility Concern about Image-Text Retrieval. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2727--2737."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1006\/jvci.1999.0413"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532034"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.241"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3447689.3447706"},{"key":"e_1_3_2_2_30_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_2_31_1","volume-title":"A comprehensive survey on cross-modal retrieval. arXiv preprint arXiv:1607.06215","author":"Wang Kaiye","year":"2016","unstructured":"Kaiye Wang, Qiyue Yin, Wei Wang, Shu Wu, and Liang Wang. 2016. A comprehensive survey on cross-modal retrieval. arXiv preprint arXiv:1607.06215 (2016)."},{"key":"e_1_3_2_2_32_1","volume-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. arXiv preprint arXiv:2202.03052","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022b. Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. arXiv preprint arXiv:2202.03052 (2022)."},{"key":"e_1_3_2_2_33_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2022","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al. 2022a. Image as a foreign language: Beit pretraining for all vision and vision-language tasks. arXiv preprint arXiv:2208.10442 (2022)."},{"key":"e_1_3_2_2_34_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022c. Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531826"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539813.3545148"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"e_1_3_2_2_38_1","volume-title":"Caiming Xiong, Richard Socher, Michael R Lyu, Irwin King, and Steven CH Hoi.","author":"Zeng Jichuan","year":"2020","unstructured":"Jichuan Zeng, Xi Victoria Lin, Caiming Xiong, Richard Socher, Michael R Lyu, Irwin King, and Steven CH Hoi. 2020. Photon: a robust cross-domain text-to-SQL system. arXiv preprint arXiv:2007.15280 (2020)."},{"key":"e_1_3_2_2_39_1","volume-title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering. CoRR","author":"Zhu Fengbin","year":"2021","unstructured":"Fengbin Zhu, Wenqiang Lei, Chao Wang, Jianming Zheng, Soujanya Poria, and Tat-Seng Chua. 2021. Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering. CoRR, Vol. abs\/2101.00774 (2021). showeprint[arXiv]2101.00774 https:\/\/arxiv.org\/abs\/2101.00774"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591930","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:38:07Z","timestamp":1750178287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":39,"alternative-id":["10.1145\/3539618.3591930","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591930","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}