{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:19Z","timestamp":1740172459712,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1836222","61733011"],"award-info":[{"award-number":["U1836222","61733011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chinese National Key Laboratory of Science and Technology on Information System Security"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2021.3130972","type":"journal-article","created":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T20:14:44Z","timestamp":1637957684000},"page":"49-59","source":"Crossref","is-referenced-by-count":1,"title":["Which Apple Keeps Which Doctor Away? Colorful Word Representations With Visual Oracles"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4183-3645","authenticated-orcid":false,"given":"Zhuosheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haojie","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-0487","authenticated-orcid":false,"given":"Hai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1111-9245","authenticated-orcid":false,"given":"Masao","family":"Utiyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"The fifth PASCAL recognizing textual entailment challenge","volume-title":"Proc. Assoc. Comput. Linguistics-PASCAL","author":"Bentivogli","year":"2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1075"},{"issue":"4","key":"ref3","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Comput. Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1024218913435"},{"article-title":"Better Deep Learning: Train Faster, Reduce Overfitting, and Make Better Predictions","year":"2018","author":"Brownlee","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s17-2001"},{"article-title":"Quora question pairs","year":"2018","author":"Chen","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219906"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref10","first-page":"9","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Proc. 3rd Int. Workshop Paraphrasing","author":"Dolan","year":"2005"},{"article-title":"Using BERT for word sense disambiguation","year":"2019","author":"Du","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1355"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref23","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32, Annu. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1170"},{"key":"ref25","first-page":"2746","article-title":"Glyce: Glyph-vectors for chinese character representations","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Meng","year":"2019"},{"key":"ref26","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 26, 27th Annu. Conf. Neural Inf. Process. Syst., Proc. Meeting Held","author":"Mikolov","year":"2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5301"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1459352.1459355"},{"key":"ref29","first-page":"5115","article-title":"Regularizing deep neural networks by noise: Its interpretation and optimization","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Noh","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.13053\/cys-23-4-3294"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1120"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1068"},{"key":"ref39","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Socher","year":"2013"},{"key":"ref40","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6304"},{"key":"ref45","article-title":"VidLanKD: Improving language understanding via video-distilled knowledge transfer","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Tang","year":"2021"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30, Annu. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11939"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00090"},{"key":"ref52","first-page":"1","article-title":"Neural machine translation with universal visual representation","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09627795.pdf?arnumber=9627795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T04:16:16Z","timestamp":1710389776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9627795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3130972","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2022]]}}}