{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:40:28Z","timestamp":1742913628232,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030770907"},{"type":"electronic","value":"9783030770914"}],"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\/978-3-030-77091-4_17","type":"book-chapter","created":{"date-parts":[[2021,5,21]],"date-time":"2021-05-21T16:03:21Z","timestamp":1621613001000},"page":"263-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Grounding Dialogue History: Strengths and Weaknesses of Pre-trained Transformers"],"prefix":"10.1007","author":[{"given":"Claudio","family":"Greco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Testoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raffaella","family":"Bernardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,22]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1177\/002383099103400404","volume":"34","author":"AH Anderson","year":"1991","unstructured":"Anderson, A.H., et al.: The HCRC map task corpus. Lang. Speech 34, 351\u2013366 (1991)","journal-title":"Lang. Speech"},{"key":"17_CR2","unstructured":"Chen, Y.C., et al.: UNITER: learning universal image-text representations (2019). arXiv:1909.11740"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., Manning, C.D.: What does BERT look at? An analysis of BERT\u2019s attention. In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 276\u2013286 (2019)","DOI":"10.18653\/v1\/W19-4828"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Das, A., Kottur, S., Moura, J.M., Lee, S., Batra, D.: Learning cooperative visual dialog agents with deep reinforcement learning. In: 2017 IEEE International Conference on Computer Vision, pp. 2951\u20132960 (2017)","DOI":"10.1109\/ICCV.2017.321"},{"key":"17_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Long and Short Papers), vol. 1, pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Gan, Z., Cheng, Y., Kholy, A.E., Li, L., Liu, J., Gao, J.: Multi-step reasoning via recurrent dual attention for visual dialog. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6463\u20136474 (2019)","DOI":"10.18653\/v1\/P19-1648"},{"key":"17_CR7","doi-asserted-by":"publisher","unstructured":"Haber, J., Baumg\u00e4rtner, T., Takmaz, E., Gelderloos, L., Bruni, E., Fern\u00e1ndez, R.: The PhotoBook dataset: building common ground through visually-grounded dialogue. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1895\u20131910, July 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1184. https:\/\/www.aclweb.org\/anthology\/P19-1184","DOI":"10.18653\/v1\/P19-1184"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"He, H., Balakrishnan, A., Eric, M., Liang, P.: Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 1766\u20131776 (2017)","DOI":"10.18653\/v1\/P17-1162"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Ilinykh, N., Zarrie\u00df, S., Schlangen, D.: Tell me more: a dataset of visual scene description sequences. In: Proceedings of the 12th International Conference on Natural Language Generation, pp. 152\u2013157 (2019). https:\/\/www.aclweb.org\/anthology\/W19-8621","DOI":"10.18653\/v1\/W19-8621"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.B.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. abs\/1612.06890 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1965\u20131973 (2017)","DOI":"10.1109\/ICCV.2017.217"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Kaushik, D., Lipton, Z.C.: How much reading does reading comprehension require? A critical investigation of popular benchmarks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 5010\u20135015 (2018)","DOI":"10.18653\/v1\/D18-1546"},{"key":"17_CR14","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language (2019). arXiv:1908.03557"},{"key":"17_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"17_CR16","unstructured":"Liu, Y., et al.: RoERTa: a robustly optimized bert pretraining approach (2019). arXiv:1907.11692"},{"key":"17_CR17","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Murahari, V., Batra, D., Parikh, D., Das, A.: Large-scale pretraining for visual dialog: a simple state-of-the-art baseline. arXiv preprint arXiv:1912.02379 (2019)","DOI":"10.1007\/978-3-030-58523-5_20"},{"key":"17_CR20","unstructured":"amd Nan Duan, G.L., Fang, Y., Gong, M., Jiang, D., Zhou, M.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. In: Proceedings of AAAI (2020)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Pang, W., Wang, X.: Visual dialogue state tracking for question generation. In: Proceedings of 34th AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6856"},{"key":"17_CR22","unstructured":"Sang-Woo, L., Tong, G., Sohee, Y., Jaejun, Y., Jung-Woo, H.: Large-scale answerer in questioner\u2019s mind for visual dialog question generation. In: Proceedings of International Conference on Learning Representations, ICLR (2019)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Sankar, C., Subramanian, S., Pal, C., Chandar, S., Bengio, Y.: Do neural dialog systems use the conversation history effectively? An empirical study. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 32\u201337 (2019). https:\/\/www.aclweb.org\/anthology\/P19-1004","DOI":"10.18653\/v1\/P19-1004"},{"issue":"8","key":"17_CR24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"J Schmidhuber","year":"1997","unstructured":"Schmidhuber, J., Hochreiter, S.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Shekhar, R., et al.: FOIL it! Find one mismatch between image and language caption. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Long Papers), vol. 1, pp. 255\u2013265 (2017)","DOI":"10.18653\/v1\/P17-1024"},{"key":"17_CR26","doi-asserted-by":"publisher","unstructured":"Shekhar, R., et al.: Beyond task success: a closer look at jointly learning to see, ask, and GuessWhat. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Long and Short Papers), vol. 1, pp. 2578\u20132587 (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1265. https:\/\/www.aclweb.org\/anthology\/N19-1265","DOI":"10.18653\/v1\/N19-1265"},{"key":"17_CR27","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. In: ICLR (2020)"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Suhr, A., Lewis, M., Yeh, J., Artzi, Y.: A corpus of natural language for visual reasoning. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, pp. 217\u2013223. Association for Computational Linguistics, July 2017. http:\/\/aclweb.org\/anthology\/P17-2034","DOI":"10.18653\/v1\/P17-2034"},{"key":"17_CR29","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems. pp. 3104\u20133112 (2014)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5103\u20135114 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Udagawa, T., Aizawa, A.: A natural language corpus of common grounding under continuous and partially-observable context. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7120\u20137127 (2019)","DOI":"10.1609\/aaai.v33i01.33017120"},{"key":"17_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.C.: GuessWhat?! Visual object discovery through multi-modal dialogue. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 5503\u20135512 (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Yang, T., Zha, Z.J., Zhang, H.: Making history matter: history-advantage sequence training for visual dialog. In: Proceedings of the International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00265"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhao, T., Yu, Z.: Multimodal hierarchical reinforcement learning policy for task-oriented visual dialog. In: Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pp. 140\u2013150 (2018). https:\/\/www.aclweb.org\/anthology\/W18-5015","DOI":"10.18653\/v1\/W18-5015"},{"key":"17_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-030-01228-1_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Zhang","year":"2018","unstructured":"Zhang, J., Wu, Q., Shen, C., Zhang, J., Lu, J., van den Hengel, A.: Goal-oriented visual question generation via intermediate rewards. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 189\u2013204. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_12"},{"key":"17_CR37","unstructured":"Zhao, R., Tresp, V.: Improving goal-oriented visual dialog agents via advanced recurrent nets with tempered policy gradient. In: Proceedings of IJCAI (2018)"}],"container-title":["Lecture Notes in Computer Science","AIxIA 2020 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-77091-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T06:39:48Z","timestamp":1672209588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-77091-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030770907","9783030770914"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-77091-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aixia2020.disco.unimib.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"89","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":"27","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":"3","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":"30% - 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","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}