{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:14:07Z","timestamp":1776096847509,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645483","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"1474-1485","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7275-5398","authenticated-orcid":false,"given":"Yifei","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5301-4244","authenticated-orcid":false,"given":"Clemencia","family":"Siro","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9447-4172","authenticated-orcid":false,"given":"Mohammad","family":"Aliannejadi","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten de","family":"Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5479-377X","authenticated-orcid":false,"given":"Wai","family":"Lam","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482231"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Mohammad Aliannejadi Julia Kiseleva Aleksandr Chuklin Jeff Dalton and Mikhail Burtsev. 2021b. Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.367"},{"key":"e_1_3_2_2_3_1","volume-title":"Burtsev","author":"Aliannejadi Mohammad","year":"2020","unstructured":"Mohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin, Jeffrey Dalton, and Mikhail S. Burtsev. 2020. ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ). ArXiv , Vol. abs\/2009.11352 (2020)."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 2019 International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Aliannejadi Mohammad","unstructured":"Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, and W. Bruce Croft. 2019. Asking Clarifying Questions in Open-Domain Information-Seeking Conversations. In Proceedings of the 2019 International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_2_2_5_1","volume-title":"IEEE Intelligent Systems & Their Applications","volume":"14","author":"Allen James","year":"1999","unstructured":"James Allen, Curry I. Guinn, and E. Horvtz. 1999. Mixed-initiative interaction. IEEE Intelligent Systems & Their Applications , Vol. 14 (1999)."},{"key":"e_1_3_2_2_6_1","volume-title":"Sebastian Riedel, and Fabio Petroni.","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Wen tau Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive Search Engines: Generating Substrings as Document Identifiers. ArXiv , Vol. abs\/2204.10628 (2022)."},{"key":"e_1_3_2_2_7_1","volume-title":"International Journal of Computer Applications","volume":"74","author":"Bokhari Mohammad Ubaidullah","year":"2013","unstructured":"Mohammad Ubaidullah Bokhari and Faraz Hasan. 2013. Multimodal Information Retrieval: Challenges and Future Trends. International Journal of Computer Applications , Vol. 74 (2013)."},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of the 2003 Conference of North American Chapter of the Association for Computational Linguistics.","author":"Boni Marco De","year":"2003","unstructured":"Marco De Boni and Suresh Manandhar. 2003. An Analysis of Clarification Dialogue for Question Answering. In Proceedings of the 2003 Conference of North American Chapter of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020165.3022149"},{"key":"e_1_3_2_2_10_1","volume-title":"Language Models are Few-Shot Learners. ArXiv","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, T. J. Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeff Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. ArXiv , Vol. abs\/2005.14165 (2020)."},{"key":"e_1_3_2_2_11_1","volume-title":"Autoregressive Entity Retrieval. ArXiv","author":"Cao Nicola De","year":"2020","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2020. Autoregressive Entity Retrieval. ArXiv , Vol. abs\/2010.00904 (2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Chang Yingshan","year":"2021","unstructured":"Yingshan Chang, Mridu Baldevraj Narang, Hisami Suzuki, Guihong Cao, Jianfeng Gao, and Yonatan Bisk. 2021. WebQA: Multihop and Multimodal QA. In Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_13_1","volume-title":"2023 b. A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning. ArXiv","author":"Chen Jiangui","year":"2023","unstructured":"Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yiqun Liu, Yixing Fan, and Xueqi Cheng. 2023 b. A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning. ArXiv , Vol. abs\/2304.14856 (2023)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531827"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557271"},{"key":"e_1_3_2_2_16_1","volume-title":"2023 a. Understanding Differential Search Index for Text Retrieval. ArXiv","author":"Chen Xiaoyang","year":"2073","unstructured":"Xiaoyang Chen, Yanjiang Liu, Ben He, Le Sun, and Yingfei Sun. 2023 a. Understanding Differential Search Index for Text Retrieval. ArXiv , Vol. abs\/2305.02073 (2023)."},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Cho Jaemin","year":"2021","unstructured":"Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying Vision-and-Language Tasks via Text Generation. In Proceedings of the 38th International Conference on Machine Learning, Vol. 139."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939746"},{"key":"e_1_3_2_2_19_1","volume-title":"Overview of the TREC 2009 Web Track. In Text REtrieval Conference.","author":"Clarke Charles L. A.","year":"2009","unstructured":"Charles L. A. Clarke, Nick Craswell, and Ian Soboroff. 2009. Overview of the TREC 2009 Web Track. In Text REtrieval Conference."},{"key":"e_1_3_2_2_20_1","volume-title":"Overview of the TREC 2010 Web Track. In Text REtrieval Conference.","author":"Clarke Charles L. A.","unstructured":"Charles L. A. Clarke, Nick Craswell, Ian Soboroff, and Gordon V. Cormack. 2010. Overview of the TREC 2010 Web Track. In Text REtrieval Conference."},{"key":"e_1_3_2_2_21_1","volume-title":"Mendes","author":"Coden Anni","year":"2015","unstructured":"Anni Coden, Daniel F. Gruhl, Neal Lewis, and Pablo N. Mendes. 2015. Did you mean A or B? Supporting Clarification Dialog for Entity Disambiguation. In SumPre-HSWI@ESWC."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.09.039"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462806"},{"key":"e_1_3_2_2_24_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv , Vol. abs\/1810.04805 (2019)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1358"},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Hashemi Helia","unstructured":"Helia Hashemi, Hamed Zamani, and W. Bruce Croft. 2020. Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_2_2_28_1","volume-title":"Trends & Controversies: Mixed-initiative Interaction","author":"Hearst Marti A.","year":"1999","unstructured":"Marti A. Hearst. 1999. Trends & Controversies: Mixed-initiative Interaction. IEEE Intell. Syst. , Vol. 14 (1999)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210160"},{"key":"e_1_3_2_2_30_1","volume-title":"International Journal of Computer Vision","volume":"123","author":"Krishna Ranjay","year":"2016","unstructured":"Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A. Shamma, Michael S. Bernstein, and Li Fei-Fei. 2016. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. International Journal of Computer Vision , Vol. 123 (2016)."},{"key":"e_1_3_2_2_31_1","volume-title":"Contextualized Generative Retrieval. ArXiv","author":"Lee Hyunji","year":"2068","unstructured":"Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vladimir Karpukhin, Yi Lu, and Minjoon Seo. 2022. Contextualized Generative Retrieval. ArXiv , Vol. abs\/2210.02068 (2022)."},{"key":"e_1_3_2_2_32_1","volume-title":"The Power of Scale for Parameter-Efficient Prompt Tuning. ArXiv","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The Power of Scale for Parameter-Efficient Prompt Tuning. ArXiv , Vol. abs\/2104.08691 (2021)."},{"key":"e_1_3_2_2_33_1","volume-title":"Hoi","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. ArXiv , Vol. abs\/2301.12597 (2023)."},{"key":"e_1_3_2_2_34_1","volume-title":"VisualBERT: A Simple and Performant Baseline for Vision and Language. ArXiv","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. VisualBERT: A Simple and Performant Baseline for Vision and Language. ArXiv , Vol. abs\/1908.03557 (2019)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462970"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240605"},{"key":"e_1_3_2_2_38_1","volume-title":"Mixed-Modality Interaction in Conversational Recommender Systems. In IntRS workshop at RecSys.","author":"Ma Yuan","year":"2021","unstructured":"Yuan Ma, Timm Kleemann, and J\u00fcrgen Ziegler. 2021. Mixed-Modality Interaction in Conversational Recommender Systems. In IntRS workshop at RecSys."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462824"},{"key":"e_1_3_2_2_41_1","volume-title":"Computerized Medical Imaging and Graphics: The Official Journal of the Computerized Medical Imaging Society","volume":"39","author":"Andr\u00e9 Mour","year":"2015","unstructured":"Andr\u00e9 Mour ao, Fl\u00e1vio Martins, and Jo ao Magalh aes. 2015. Multimodal Medical Information Retrieval with Unsupervised Rank Fusion. Computerized Medical Imaging and Graphics: The Official Journal of the Computerized Medical Imaging Society , Vol. 39 (2015)."},{"key":"e_1_3_2_2_42_1","volume-title":"Image Retrieval with Mixed Initiative and Multimodal Feedback. In British Machine Vision Conference.","author":"Murrugarra-Llerena Nils","year":"2018","unstructured":"Nils Murrugarra-Llerena and Adriana Kovashka. 2018. Image Retrieval with Mixed Initiative and Multimodal Feedback. In British Machine Vision Conference."},{"key":"e_1_3_2_2_43_1","volume-title":"Staging transformations for multimodal web interaction management. ArXiv","author":"Narayan Michael","year":"2003","unstructured":"Michael Narayan, Christopher Williams, Saverio Perugini, and Naren Ramakrishnan. 2003. Staging transformations for multimodal web interaction management. ArXiv , Vol. cs.IR\/0311029 (2003)."},{"key":"e_1_3_2_2_44_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. ArXiv Vol. abs\/2303.08774 (2023)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591683"},{"key":"e_1_3_2_2_46_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Neural Information Processing Systems."},{"key":"e_1_3_2_2_47_1","volume-title":"ACM SIGIR Forum","volume":"51","author":"Ponte Jay M.","year":"1998","unstructured":"Jay M. Ponte and W. Bruce Croft. 1998. A Language Modeling Approach to Information Retrieval. ACM SIGIR Forum , Vol. 51 (1998)."},{"key":"e_1_3_2_2_48_1","volume-title":"abs\/1306.2597","author":"Qin Tao","year":"2013","unstructured":"Tao Qin and Tie-Yan Liu. 2013. Introducing LETOR 4.0 Datasets. ArXiv , Vol. abs\/1306.2597 (2013)."},{"key":"e_1_3_2_2_49_1","volume-title":"Question\/Answering Clarification Dialogues. In MICAI 2008: Advances in Artificial Intelligence.","author":"Quintano Luis","year":"2008","unstructured":"Luis Quintano and Irene Pimenta Rodrigues. 2008. Question\/Answering Clarification Dialogues. In MICAI 2008: Advances in Artificial Intelligence."},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning."},{"key":"e_1_3_2_2_51_1","volume-title":"Liu","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam M. Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. ArXiv , Vol. abs\/1910.10683 (2019)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1255"},{"key":"e_1_3_2_2_53_1","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol. 39 (2015).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_54_1","volume-title":"Robertson and Hugo Zaragoza","author":"Stephen","year":"2009","unstructured":"Stephen E. Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends in Information Retrieval , Vol. 3 (2009)."},{"key":"e_1_3_2_2_55_1","volume-title":"Edleno Silva de Moura, Marcos Andr\u00e9 Gon\u00e7alves, and Ricardo da Silva Torres.","author":"Saraiva Patricia Correia","year":"2016","unstructured":"Patricia Correia Saraiva, Jo ao M. B. Cavalcanti, Edleno Silva de Moura, Marcos Andr\u00e9 Gon\u00e7alves, and Ricardo da Silva Torres. 2016. A Multimodal Query Expansion Based on Genetic Programming for Visually-oriented E-commerce Applications. Inf. Process. Manag. , Vol. 52 (2016)."},{"key":"e_1_3_2_2_56_1","volume-title":"Proceedings of the 43rd European Conference on Information Retrieval.","author":"Sekulic Ivan","unstructured":"Ivan Sekulic, Mohammad Aliannejadi, and Fabio A. Crestani. 2021. User Engagement Prediction for Clarification in Search. In Proceedings of the 43rd European Conference on Information Retrieval."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871458"},{"key":"e_1_3_2_2_58_1","volume-title":"MultiModalQA: Complex Question Answering over Text, Tables and Images. ArXiv","author":"Talmor Alon","year":"2021","unstructured":"Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, and Jonathan Berant. 2021. MultiModalQA: Complex Question Answering over Text, Tables and Images. ArXiv , Vol. abs\/2104.06039 (2021)."},{"key":"e_1_3_2_2_59_1","volume-title":"I Want This Product but Different : Multimodal Retrieval with Synthetic Query Expansion. ArXiv","author":"Tautkute Ivona","year":"2021","unstructured":"Ivona Tautkute and Tomasz Trzci'ski. 2021. I Want This Product but Different : Multimodal Retrieval with Synthetic Query Expansion. ArXiv , Vol. abs\/2102.08871 (2021)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531750"},{"key":"e_1_3_2_2_61_1","volume-title":"Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Gupta","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Vinh Quang Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Gupta, Tal Schuster, William W. Cohen, and Donald Metzler. 2022. Transformer Memory as a Differentiable Search Index. ArXiv , Vol. abs\/2202.06991 (2022)."},{"key":"e_1_3_2_2_62_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. ArXiv","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. ArXiv , Vol. abs\/2302.13971 (2023)."},{"key":"e_1_3_2_2_63_1","volume-title":"Surya Kallumadi, Vanessa Murdock, and Maarten de Rijke.","author":"Tsagkias Manos","year":"2020","unstructured":"Manos Tsagkias, Tracy Holloway King, Surya Kallumadi, Vanessa Murdock, and Maarten de Rijke. 2020. Challenges and Research Opportunities in eCommerce Search and Recommendations. SIGIR Forum , Vol. 54 (2020)."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401297"},{"key":"e_1_3_2_2_65_1","volume-title":"Generative Recommendation: Towards Next-generation Recommender Paradigm. ArXiv","author":"Wang Wenjie","year":"2023","unstructured":"Wenjie Wang, Xinyu Lin, Fuli Feng, Xiangnan He, and Tat-Seng Chua. 2023. Generative Recommendation: Towards Next-generation Recommender Paradigm. ArXiv , Vol. abs\/2304.03516 (2023)."},{"key":"e_1_3_2_2_66_1","volume-title":"A Neural Corpus Indexer for Document Retrieval. ArXiv","author":"Wang Yujing","year":"2022","unstructured":"Yujing Wang, Ying Hou, Hong Wang, Ziming Miao, Shibin Wu, Hao Sun, Qi Chen, Yuqing Xia, Chengmin Chi, Guoshuai Zhao, Zheng Liu, Xing Xie, Hao Sun, Weiwei Deng, Qi Zhang, and Mao Yang. 2022. A Neural Corpus Indexer for Document Retrieval. ArXiv , Vol. abs\/2206.02743 (2022)."},{"key":"e_1_3_2_2_67_1","volume-title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing. ArXiv","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, and Jamie Brew. 2019. HuggingFace's Transformers: State-of-the-art Natural Language Processing. ArXiv , Vol. abs\/1910.03771 (2019)."},{"key":"e_1_3_2_2_68_1","volume-title":"Krysta Marie Svore, and Jianfeng Gao","author":"Wu Qiang","year":"2010","unstructured":"Qiang Wu, Christopher J. C. Burges, Krysta Marie Svore, and Jianfeng Gao. 2010. Adapting boosting for information retrieval measures. Information Retrieval , Vol. 13 (2010)."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209990"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1172"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313739"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462881"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.320"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380126"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412772"},{"key":"e_1_3_2_2_76_1","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.","author":"Zamani Hamed","unstructured":"Hamed Zamani, Bhaskar Mitra, Everest Chen, Gord Lueck, Fernando Diaz, Paul N. Bennett, Nick Craswell, and Susan T. Dumais. 2020c. Analyzing and Learning from User Interactions for Search Clarification. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval."},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_2_78_1","volume-title":"User Respond. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management.","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."},{"key":"e_1_3_2_2_79_1","volume-title":"Unified Vision-Language Pre-Training for Image Captioning and VQA. ArXiv","author":"Zhou Luowei","year":"2019","unstructured":"Luowei Zhou, Hamid Palangi, Lei Zhang, Houdong Hu, Jason J. Corso, and Jianfeng Gao. 2019. Unified Vision-Language Pre-Training for Image Captioning and VQA. ArXiv , Vol. abs\/1909.11059 (2019)."},{"key":"e_1_3_2_2_80_1","volume-title":"Ledell Yu Wu, and Ji rong Wen","author":"Zhou Yujia","year":"2022","unstructured":"Yujia Zhou, Jing Yao, Zhicheng Dou, Ledell Yu Wu, and Ji rong Wen. 2022. DynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense Index. ArXiv , Vol. abs\/2203.00537 (2022)."},{"key":"e_1_3_2_2_81_1","volume-title":"Users Meet Clarifying Questions: Toward a Better Understanding of User Interactions for Search Clarification. ACM Transactions on Information Systems","volume":"41","author":"Zou Jie","year":"2022","unstructured":"Jie Zou, Mohammad Aliannejadi, E. Kanoulas, Maria Soledad Pera, and Yiqun Liu. 2022. Users Meet Clarifying Questions: Toward a Better Understanding of User Interactions for Search Clarification. ACM Transactions on Information Systems , Vol. 41 (2022). io"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645483","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:26:16Z","timestamp":1755822376000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":81,"alternative-id":["10.1145\/3589334.3645483","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645483","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}