{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:35:06Z","timestamp":1774308906635,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462806","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:54Z","timestamp":1626057714000},"page":"1577-1587","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":38,"title":["Towards Multi-Modal Conversational Information Seeking"],"prefix":"10.1145","author":[{"given":"Yashar","family":"Deldjoo","sequence":"first","affiliation":[{"name":"Polytechnic University of Bari, Bari, Italy"}]},{"given":"Johanne R.","family":"Trippas","sequence":"additional","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]},{"given":"Hamed","family":"Zamani","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Mohammad Aliannejadi Hamed Zamani Fabio Crestani and W. Bruce Croft. 2019. Asking Clarifying Questions in Open-Domain Information-Seeking Conversations. In SIGIR. ACM 475--484.","DOI":"10.1145\/3331184.3331265"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451964.3451967"},{"key":"e_1_3_2_2_3_1","unstructured":"Lorin W. Anderson David R. Krathwohl and B. S. Bloom. 2001. A Taxonomy for Learning Teaching and Assessing: A Revision of Bloom's Taxonomy of Educational Objectives. Longman."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767728"},{"key":"e_1_3_2_2_5_1","first-page":"133","article-title":"Anomalous states of knowledge as a basis for information retrieval","volume":"5","author":"Belkin Nicholas J.","year":"1980","unstructured":"Nicholas J. Belkin. 1980. Anomalous states of knowledge as a basis for information retrieval. Canadian Journal of Information Science, Vol. 5, 1 (1980), 133--143.","journal-title":"Canadian Journal of Information Science"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412043"},{"key":"e_1_3_2_2_7_1","series-title":"Dagstuhl Seminar 19461","volume-title":"Scenarios that Invite Conversational Search. Conversational Search","author":"Cavedon Lawrence","unstructured":"Lawrence Cavedon, Bernd Fr\u00f6hlich, Hideo Joho, Ruihua Song, Jaime Teevan, Johanne Trippas, and Emine Yilmaz. 2020. Scenarios that Invite Conversational Search. Conversational Search (Dagstuhl Seminar 19461), Avishek Anand, Lawrence Cavedon, Hideo Joho, Mark Sanderson, and Benno Stein (Eds.). Dagstuhl, 66--69."},{"key":"e_1_3_2_2_8_1","volume-title":"Deep Understanding of Cooking Procedure for Cross-modal Recipe Retrieval. In 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018","author":"Chen Jingjing","year":"2018","unstructured":"Jingjing Chen, Chong-Wah Ngo, Fuli Feng, and Tat-Seng Chua. 2018. Deep Understanding of Cooking Procedure for Cross-modal Recipe Retrieval. In 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018, Seoul, Republic of Korea, October 22--26, 2018. ACM, 1020--1028."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19)","author":"Clark Leigh","unstructured":"Leigh Clark, Nadia Pantidi, Orla Cooney, Philip Doyle, Diego Garaialde, Justin Edwards, Brendan Spillane, Emer Gilmartin, Christine Murad, Cosmin Munteanu, Vincent Wade, and Benjamin R. Cowan. 2019. What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19). 1--12."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331185"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/35053.35054"},{"key":"e_1_3_2_2_12_1","volume-title":"SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platform. CoRR","author":"Crook Paul A.","year":"2019","unstructured":"Paul A. Crook, Shivani Poddar, Ankita De, Semir Shafi, David Whitney, Alborz Geramifard, and Rajen Subba. 2019. SIMMC: Situated Interactive Multi-Modal Conversational Data Collection And Evaluation Platform. CoRR, Vol. abs\/1911.02690 (2019)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331226"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654946"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the Twenty-Eighth Text REtrieval Conference, TREC","author":"Dalton Jeffrey","year":"2019","unstructured":"Jeffrey Dalton, Chenyan Xiong, and Jamie Callan. 2019. CAsT 2019: The Conversational Assistance Track Overview. In Proceedings of the Twenty-Eighth Text REtrieval Conference, TREC 2019, Gaithersburg, Maryland, USA ."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240407"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-019-09221-y"},{"key":"e_1_3_2_2_18_1","volume-title":"CVPR Proceedings.","author":"Deldjoo Yashar","year":"2021","unstructured":"Yashar Deldjoo, Tommaso Di Noia, Daniele Malitesta, and Felice Antonio Merra. 2021 a. A Study on the Relative Importance of Convolutional Neural Networks in Visually-Aware Recommender Systems. In CVPRW-CVFAD 2021 :The 4th CVPR Workshop on Computer Vision for Fashion, Art, and Design. CVPR Proceedings."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439729"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3407190"},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. of NAACL .","author":"Devlin J.","unstructured":"J. Devlin, M. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. of NAACL ."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080774"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/brv.12535"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-4501-9"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.1996.556455"},{"key":"e_1_3_2_2_26_1","volume-title":"Interactive Search and Exploration in Online Discussion Forums Using Multimodal Embeddings. CoRR","author":"Gornishka Iva","year":"2019","unstructured":"Iva Gornishka, Stevan Rudinac, and Marcel Worring. 2019. Interactive Search and Exploration in Online Discussion Forums Using Multimodal Embeddings. CoRR, Vol. abs\/1905.02430 (2019)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3421900"},{"key":"e_1_3_2_2_29_1","volume-title":"Multimodal human-computer interaction: A survey. Computer vision and image understanding","author":"Jaimes Alejandro","year":"2007","unstructured":"Alejandro Jaimes and Nicu Sebe. 2007. Multimodal human-computer interaction: A survey. Computer vision and image understanding, Vol. 108, 1--2 (2007), 116--134."},{"key":"e_1_3_2_2_30_1","volume-title":"Rosie Jones, Umut Ozertem, Imed Zitouni, Ranjitha Gurunath Kulkarni, and Omar Zia Khan.","author":"Jiang Jiepu","year":"2015","unstructured":"Jiepu Jiang, Ahmed Hassan Awadallah, Rosie Jones, Umut Ozertem, Imed Zitouni, Ranjitha Gurunath Kulkarni, and Omar Zia Khan. 2015. Automatic Online Evaluation of Intelligent Assistants .International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, 506--516."},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the 1st Nordic Symposium on Multimodal Interfaces. 239--251","author":"Jokinen Kristiina","year":"2003","unstructured":"Kristiina Jokinen and Antti Raike. 2003. Multimodality--technology, visions and demands for the future. In Proceedings of the 1st Nordic Symposium on Multimodal Interfaces. 239--251."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507180"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210160"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2854946.2854961"},{"key":"e_1_3_2_2_35_1","unstructured":"Multimodal Interaction Lab. 2015. Multimodal Interaction - Human Car Interaction. http:\/\/humancarinteraction.com\/multimodal-interaction.html. (2015). (Last accessed February 4 2021)."},{"key":"e_1_3_2_2_36_1","first-page":"9","article-title":"Conversational","volume":"43","author":"Lai Jennifer","year":"2000","unstructured":"Jennifer Lai. 2000. Conversational Interfaces. Commun. ACM, Vol. 43, 9 (Sept. 2000), 24--27.","journal-title":"Interfaces. Commun. ACM"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_38_1","volume-title":"Knowledge-aware Multimodal Dialogue Systems. In 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018","author":"Liao Lizi","year":"2018","unstructured":"Lizi Liao, Yunshan Ma, Xiangnan He, Richang Hong, and Tat-Seng Chua. 2018. Knowledge-aware Multimodal Dialogue Systems. In 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018, Seoul, Republic of Korea, October 22--26, 2018. ACM, 801--809."},{"key":"e_1_3_2_2_39_1","volume-title":"The Cambridge handbook of multimedia learning","author":"Mayer Richard E.","unstructured":"Richard E. Mayer. 2005. The Cambridge handbook of multimedia learning, 1st Edition .Cambridge Univ. Press. http:\/\/www.worldcat.org\/oclc\/57526976","edition":"1"},{"key":"e_1_3_2_2_40_1","volume-title":"Nine ways to reduce cognitive load in multimedia learning. Educational psychologist","author":"Mayer Richard E","year":"2003","unstructured":"Richard E Mayer and Roxana Moreno. 2003. Nine ways to reduce cognitive load in multimedia learning. Educational psychologist, Vol. 38, 1 (2003), 43--52."},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"McAuley Julian J.","year":"2015","unstructured":"Julian J. McAuley, Christopher Targett, Qinfeng Shi, and Anton van den Hengel. 2015. Image-Based Recommendations on Styles and Substitutes. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, Santiago, Chile, August 9--13, 2015. ACM, 43--52."},{"key":"e_1_3_2_2_42_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350923"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb026631"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3125486.3125492"},{"key":"e_1_3_2_2_46_1","series-title":"Dagstuhl Seminar 19461","volume-title":"Conversational Search for Learning Technologies. Conversational Search","author":"Oviatt Sharon","unstructured":"Sharon Oviatt and Laure Soulier. 2020. Conversational Search for Learning Technologies. Conversational Search (Dagstuhl Seminar 19461), Avishek Anand, Lawrence Cavedon, Hideo Joho, Mark Sanderson, and Benno Stein (Eds.). Dagstuhl, 69--74."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781410615862.ch3"},{"key":"e_1_3_2_2_48_1","volume-title":"KDD 2020 Workshop on Conversational Systems Towards Mainstream Adoption (KDD-Converse","volume":"2666","author":"Penha Gustavo","year":"2020","unstructured":"Gustavo Penha and Claudia Hauff. 2020. Challenges in the evaluation of conversational search systems. In KDD 2020 Workshop on Conversational Systems Towards Mainstream Adoption (KDD-Converse 2020), Vol. 2666. CEUR-WS."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174214"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020165.3020183"},{"key":"e_1_3_2_2_52_1","volume-title":"Multimodal Human-Computer Interaction: a constructive and empirical study","author":"Raisamo Roope","unstructured":"Roope Raisamo. 1999. Multimodal Human-Computer Interaction: a constructive and empirical study .Tampere University Press."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11331"},{"key":"e_1_3_2_2_54_1","volume-title":"Towards Natural Clarification Questions in Dialogue Systems. In AISB '14","volume":"20","author":"Stoyanchev Svetlana","year":"2014","unstructured":"Svetlana Stoyanchev, Alex Liu, and Julia Hirschberg. 2014. Towards Natural Clarification Questions in Dialogue Systems. In AISB '14, Vol. 20."},{"key":"e_1_3_2_2_55_1","volume-title":"Toward Explainable Fashion Recommendation. In IEEE Winter Conference on Applications of Computer Vision, WACV 2020","author":"Tangseng Pongsate","year":"2020","unstructured":"Pongsate Tangseng and Takayuki Okatani. 2020. Toward Explainable Fashion Recommendation. In IEEE Winter Conference on Applications of Computer Vision, WACV 2020, Snowmass Village, CO, USA, March 1--5, 2020. IEEE, 2142--2151."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.5090130405"},{"key":"e_1_3_2_2_57_1","volume-title":"SIGIR 1st International Workshop on Conversational Approaches to Information Retrieval (CAIR'17)","author":"Thomas Paul","year":"2017","unstructured":"Paul Thomas, Daniel McDuff, Mary Czerwinski, and Nick Craswell. 2017. MISC: A data set of information-seeking conversations. In SIGIR 1st International Workshop on Conversational Approaches to Information Retrieval (CAIR'17). 6 pages."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3176349.3176387"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767826"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102162"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.07.003"},{"key":"e_1_3_2_2_62_1","unstructured":"Alexandra Vtyurina Charles LA Clarke Edith Law Johanne R. Trippas and Horatiu Bota. A Mixed-Method Analysis of Text and Audio Search Interfaces with Varying Task Complexity. In Proceedings of International Conference on the Theory of Information Retrieval (ICTIR). 61--68."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052638"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401415"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380126"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403202"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"crossref","unstructured":"Shuo Zhang Zhuyun Dai Krisztian Balog and Jamie Callan. 2020. Summarizing and Exploring Tabular Data in Conversational Search. 1537--1540.","DOI":"10.1145\/3397271.3401205"},{"key":"e_1_3_2_2_68_1","volume-title":"User Respond. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM '18)","author":"Zhang Yongfeng","unstructured":"Yongfeng Zhang, Xu Chen, Qingyao Ai, Liu Yang, and W. Bruce Croft. 2018. Towards Conversational Search and Recommendation: System Ask, User Respond. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM '18). Association for Computing Machinery, 177--186."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.880078"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462806","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:32Z","timestamp":1750199912000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":69,"alternative-id":["10.1145\/3404835.3462806","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462806","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}