{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:37Z","timestamp":1737176857023,"version":"3.33.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825708","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"6092-6100","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Semantic Joinability in Heterogeneous Data: A Triplet-Based Approach with Pre-trained Deep Learning Models"],"prefix":"10.1109","author":[{"given":"Magnus Guldberg","family":"Pedersen","sequence":"first","affiliation":[{"name":"Technical University of Denmark,DTU Compute,Kongens Lyngby,Denmark"}]},{"given":"Benjamin","family":"Kock Fazal","sequence":"additional","affiliation":[{"name":"Technical University of Denmark,DTU Compute,Kongens Lyngby,Denmark"}]},{"given":"Kyoung-Sook","family":"Kim","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Artificial Intelligence Research Center,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-374765-5.00004-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34770-3_10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSE.2016.7823936"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00775-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-83193-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44550-2_5"},{"issue":"1","key":"ref7","first-page":"674","article-title":"Semantic Issues in Integrating Data from Different Models to Achieve Data Interoperability","volume":"129","author":"Rahil","year":"2007","journal-title":"Studies in health technology and informatics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375731"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3588689"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00046"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300065"},{"article-title":"MATE: Multi-Attribute Table Extraction","year":"2021","author":"Esmailoghli","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00815-1"},{"article-title":"A Closer Look at Deep Learning on Tabular Data","year":"2024","author":"Ye","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127967"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14778\/3603581.3603587"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/3430915.3430921"},{"article-title":"SGPT: GPT Sentence Embeddings for Semantic Search","year":"2022","author":"Muennighoff","key":"ref18"},{"article-title":"On Embeddings for Numerical Features in Tabular Deep Learning","year":"2022","author":"Gorishniy","key":"ref19"},{"article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"article-title":"TabText: A Flexible and Contextual Approach to Tabular Data Representation","year":"2022","author":"Carballo","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0295598"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30460"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111293"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2015.7298682","article-title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","author":"Schroff","year":"2015"},{"article-title":"Deep Learning using Rectified Linear Units (ReLU)","year":"2018","author":"Agarap","key":"ref29"},{"article-title":"TripletGAN: Training Generative Model with Triplet Loss","year":"2017","author":"Cao","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref32","article-title":"Enriching Word Vectors with Subword Information","author":"Bojanowski","year":"2016","journal-title":"Transactions of the association for computational linguistics"},{"article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability","author":"MacQueen","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1976.tb01573.x"},{"article-title":"Evaluation of Classifier Models Using Stratified Tenfold Cross Validation Techniques","volume-title":"International Conference on Computing and Communication Systems. ObCom 2011","author":"Purushotham","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3588710"},{"key":"ref38","article-title":"Decoupled Weight Decay Regularization","author":"Loshchilov","year":"2017","journal-title":"ICLR 2019"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825708.pdf?arnumber=10825708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:47Z","timestamp":1737101687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825708","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}