{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:07Z","timestamp":1740172447502,"version":"3.37.3"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3304468","type":"journal-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T17:28:59Z","timestamp":1691774939000},"page":"704-713","source":"Crossref","is-referenced-by-count":0,"title":["Entity Resolution in Situated Dialog With Unimodal and Multimodal Transformers"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-9501","authenticated-orcid":false,"given":"Alejandro Santorum","family":"Varela","sequence":"first","affiliation":[{"name":"Department of Engineering, Cambridge University, Cambridge, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetlana","family":"Stoyanchev","sequence":"additional","affiliation":[{"name":"Speech Technology Group, Toshiba Europe Limited Cambridge Research Laboratory, Cambridge, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0173-8966","authenticated-orcid":false,"given":"Simon","family":"Keizer","sequence":"additional","affiliation":[{"name":"Speech Technology Group, Toshiba Europe Limited Cambridge Research Laboratory, Cambridge, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1061-9512","authenticated-orcid":false,"given":"Rama","family":"Doddipatla","sequence":"additional","affiliation":[{"name":"Speech Technology Group, Toshiba Europe Limited Cambridge Research Laboratory, Cambridge, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1292-2769","authenticated-orcid":false,"given":"Kate","family":"Knill","sequence":"additional","affiliation":[{"name":"Department of Engineering, Cambridge University, Cambridge, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414888"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4610"},{"key":"ref3","article-title":"UNITER-based situated coreference resolution with rich multimodal input","author":"Huang","year":"2021","journal-title":"CoRR"},{"key":"ref4","article-title":"Exploring multi-modal representations for ambiguity detection & coreference resolution in the SIMMC 2.0 challenge","author":"Chiyah-Garcia","year":"2023","journal-title":"CoRR"},{"key":"ref5","article-title":"Tackling situated multi-modal task-oriented dialogs with a single transformer model","volume-title":"Proc. AAAI Conf. Artif. Intell. Workshop","author":"Lee","year":"2022"},{"volume-title":"Anaphora Resolution - Algorithms, Resources, and Applications, Theory and Applications of Natural Language Processing","year":"2016","author":"Poesio","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/002383099103400404"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00064"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700875"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5526"},{"issue":"4","key":"ref11","first-page":"629","article-title":"On coreferring: Coreference in MUC and related annotation schemes","volume-title":"Comput. Linguistics","volume":"26","author":"Deemter","year":"2000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/089120101753342653"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220180"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_7"},{"key":"ref16","first-page":"3722","article-title":"Visual reference resolution using attention memory for visual dialog","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Seo","year":"2017"},{"key":"ref17","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref18","article-title":"Multi-modal space structure: A new kind of latent correlation for multi-modal entity resolution","author":"Zheng","year":"2018","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SemDial.2017-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2012.05.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.96"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.401"},{"article-title":"A history of the Unity game engine","year":"2014","author":"Haas","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref27","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter, Assoc. Comput. Linguistics","author":"Devlin","year":"2019"},{"issue":"8","key":"ref28","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Documentation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5709"},{"article-title":"Multimodal interactions using pretrained unimodal models for SIMMC 2.0","year":"2021","author":"Lee","key":"ref30"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref35","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","volume-title":"Proc. 24th Int. Conf. Neural Image Process. Syst.","author":"Ordonez","year":"2011"},{"issue":"1","key":"ref36","first-page":"2853","article-title":"The benefit of multitask representation learning","volume":"17","author":"Maurer","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10214620.pdf?arnumber=10214620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:00:14Z","timestamp":1703030414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10214620\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3304468","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}