{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T19:38:04Z","timestamp":1792006684928,"version":"4.4.0"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s00778-023-00779-z","type":"journal-article","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T13:02:43Z","timestamp":1673960563000},"page":"1215-1235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Effective entity matching with transformers"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0602-149X","authenticated-orcid":false,"given":"Yuliang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinfeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshi","family":"Suhara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"AnHai","family":"Doan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang-Chiew","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,17]]},"reference":[{"key":"779_CR1","doi-asserted-by":"crossref","unstructured":"Abuzaid, F., Sethi, G., Bailis, P., Zaharia, M.: To index or not to index: optimizing exact maximum inner product search. In: Proceedings of ICDE \u201919, pp. 1250\u20131261. IEEE (2019)","DOI":"10.1109\/ICDE.2019.00114"},{"key":"779_CR2","doi-asserted-by":"crossref","unstructured":"Baraldi, A., Buono, F.D., Paganelli, M., Guerra, F.: Using landmarks for explaining entity matching models. In: EDBT, pp. 451\u2013456 (2021)","DOI":"10.1145\/3459637.3481981"},{"key":"779_CR3","doi-asserted-by":"crossref","unstructured":"Barlaug, N.: LEMON: explainable entity matching (2021). CoRR arXiv:2110.00516","DOI":"10.1109\/TKDE.2022.3200644"},{"key":"779_CR4","unstructured":"Baxter, L.R., Baxter, R., Christen, P., et al.: A comparison of fast blocking methods for record (2003)"},{"key":"779_CR5","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A.: Scibert: a pretrained language model for scientific text (2019). arXiv preprint arXiv:1903.10676","DOI":"10.18653\/v1\/D19-1371"},{"key":"779_CR6","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: Proceedings KDD \u201903, pp. 39\u201348 (2003)","DOI":"10.1145\/956750.956759"},{"key":"779_CR7","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. TACL 5, 135\u2013146 (2017)","journal-title":"TACL"},{"key":"779_CR8","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures\u2014a step forward in data integration. In: EDBT (2020)"},{"key":"779_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zhu, X., Ling, Z.H., Inkpen, D., Wei, S.: Neural natural language inference models enhanced with external knowledge. In: Proceedings of ACL \u201918, pp. 2406\u20132417 (2018)","DOI":"10.18653\/v1\/P18-1224"},{"issue":"9","key":"779_CR10","first-page":"1537","volume":"24","author":"P Christen","year":"2011","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. TKDE 24(9), 1537\u20131555 (2011)","journal-title":"TKDE"},{"key":"779_CR11","unstructured":"Cicco, V.D., Firmani, D., Koudas, N., Merialdo, P., Srivastava, D.: Interpreting deep learning models for entity resolution: an experience report using LIME. In: aiDM@SIGMOD, pp. 8:1\u20138:4 (2019)"},{"key":"779_CR12","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 BlackBoxNLP \u201919, pp. 276\u2013286 (2019)","DOI":"10.18653\/v1\/W19-4828"},{"key":"779_CR13","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Richman, J.: Learning to match and cluster large high-dimensional data sets for data integration. In: Proceedings of KDD \u201902, pp. 475\u2013480 (2002)","DOI":"10.1145\/775047.775116"},{"key":"779_CR14","doi-asserted-by":"crossref","unstructured":"Dalvi, N., Rastogi, V., Dasgupta, A., Das Sarma, A., Sarlos, T.: Optimal hashing schemes for entity matching. In: Proceeding of WWW \u201913, pp. 295\u2013306 (2013)","DOI":"10.1145\/2488388.2488415"},{"key":"779_CR15","unstructured":"Das, S., Doan, A., Psgc, G.C., Gokhale, C., Konda, P., Govind, Y., Paulsen, D.: The magellan data repository. https:\/\/sites.google.com\/site\/anhaidgroup\/projects\/data"},{"key":"779_CR16","unstructured":"De\u00a0Bruin, J.: Python Record Linkage Toolkit: a toolkit for record linkage and duplicate detection in Python (2019)"},{"key":"779_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT \u201919, pp. 4171\u20134186 (2019)"},{"key":"779_CR18","doi-asserted-by":"crossref","unstructured":"Ebaid, A., Thirumuruganathan, S., Aref, W.G., Elmagarmid, A.K., Ouzzani, M.: EXPLAINER: entity resolution explanations. In: ICDE, pp. 2000\u20132003 (2019)","DOI":"10.1109\/ICDE.2019.00224"},{"issue":"11","key":"779_CR19","first-page":"1454","volume":"11","author":"M Ebraheem","year":"2018","unstructured":"Ebraheem, M., Thirumuruganathan, S., Joty, S., Ouzzani, M., Tang, N.: Distributed representations of tuples for entity resolution. PVLDB 11(11), 1454\u20131467 (2018)","journal-title":"PVLDB"},{"key":"779_CR20","doi-asserted-by":"crossref","unstructured":"Elmagarmid, A., Ilyas, I.F., Ouzzani, M., Quian\u00e9-Ruiz, J.A., Tang, N., Yin, S.: NADEEF\/ER: generic and interactive entity resolution. In: Proceedings of SIGMOD \u201914, pp. 1071\u20131074 (2014)","DOI":"10.1145\/2588555.2594511"},{"key":"779_CR21","doi-asserted-by":"crossref","unstructured":"Fisher, J., Christen, P., Wang, Q., Rahm, E.: A clustering-based framework to control block sizes for entity resolution. In: Proceedings of KDD \u201915, pp. 279\u2013288 (2015)","DOI":"10.1145\/2783258.2783396"},{"key":"779_CR22","doi-asserted-by":"crossref","unstructured":"Fu, C., Han, X., Sun, L., Chen, B., Zhang, W., Wu, S., Kong, H.: End-to-end multi-perspective matching for entity resolution. In: Proceedings of IJCAI \u201919, pp. 4961\u20134967. AAAI Press (2019)","DOI":"10.24963\/ijcai.2019\/689"},{"key":"779_CR23","doi-asserted-by":"crossref","unstructured":"Ge, C., Wang, P., Chen, L., Liu, X., Zheng, B., Gao, Y.: Collaborer: a self-supervised entity resolution framework using multi-features collaboration (2021). CoRR arXiv:2108.08090","DOI":"10.1109\/TKDE.2021.3134806"},{"key":"779_CR24","doi-asserted-by":"crossref","unstructured":"Gokhale, C., Das, S., Doan, A., Naughton, J.F., Rampalli, N., Shavlik, J., Zhu, X.: Corleone: hands-off crowdsourcing for entity matching. In: Proceedings of SIGMOD \u201914, pp. 601\u2013612 (2014)","DOI":"10.1145\/2588555.2588576"},{"key":"779_CR25","doi-asserted-by":"crossref","unstructured":"Gurajada, S., Popa, L., Qian, K., Sen, P.: Learning-based methods with human-in-the-loop for entity resolution. In: CIKM, pp. 2969\u20132970 (2019)","DOI":"10.1145\/3357384.3360316"},{"key":"779_CR26","doi-asserted-by":"crossref","unstructured":"He, Y., Ganjam, K., Lee, K., Wang, Y., Narasayya, V., Chaudhuri, S., Chu, X., Zheng, Y.: Transform-data-by-example (tde) extensible data transformation in excel. In: SIGMOD, pp. 1785\u20131788 (2018)","DOI":"10.1145\/3183713.3193539"},{"key":"779_CR27","unstructured":"Heer, J., Hellerstein, J.M., Kandel, S.: Predictive interaction for data transformation. In: CIDR (2015)"},{"issue":"8","key":"779_CR28","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"1","key":"779_CR29","first-page":"31","volume":"15","author":"A Jain","year":"2021","unstructured":"Jain, A., Sarawagi, S., Sen, P.: Deep indexed active learning for matching heterogeneous entity representations. PVLDB 15(1), 31\u201345 (2021)","journal-title":"PVLDB"},{"issue":"3","key":"779_CR30","first-page":"465","volume":"15","author":"D Jin","year":"2021","unstructured":"Jin, D., Sisman, B., Wei, H., Dong, X.L., Koutra, D.: Deep transfer learning for multi-source entity linkage via domain adaptation. PVLDB 15(3), 465\u2013477 (2021)","journal-title":"PVLDB"},{"key":"779_CR31","doi-asserted-by":"crossref","unstructured":"Kasai, J., Qian, K., Gurajada, S., Li, Y., Popa, L.: Low-resource deep entity resolution with transfer and active learning. In: Proceedings of ACL \u201919, pp. 5851\u20135861 (2019)","DOI":"10.18653\/v1\/P19-1586"},{"key":"779_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"issue":"12","key":"779_CR33","first-page":"1197","volume":"9","author":"P Konda","year":"2016","unstructured":"Konda, P., Das, S., GC, P.S., Doan, A., Ardalan, A., Ballard, J.R., Li, H., Panahi, F., Zhang, H., Naughton, J.F., Prasad, S., Krishnan, G., Deep, R., Raghavendra, V.: Magellan: toward building entity matching management systems. PVLDB 9(12), 1197\u20131208 (2016)","journal-title":"PVLDB"},{"issue":"1\u20132","key":"779_CR34","first-page":"484","volume":"3","author":"H K\u00f6pcke","year":"2010","unstructured":"K\u00f6pcke, H., Thor, A., Rahm, E.: Evaluation of entity resolution approaches on real-world match problems. PVLDB 3(1\u20132), 484\u2013493 (2010)","journal-title":"PVLDB"},{"key":"779_CR35","unstructured":"Lample, G., Conneau, A.: Cross-lingual language model pretraining (2019). arXiv preprint arXiv:1901.07291"},{"issue":"4","key":"779_CR36","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C.H., Kang, J.: Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"779_CR37","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., Zettlemoyer, L.: BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"779_CR38","doi-asserted-by":"crossref","unstructured":"Li, B., Miao, Y., Wang, Y., Sun, Y., Wang, W.: Improving the efficiency and effectiveness for bert-based entity resolution. In: AAAI, vol. 35, pp. 13226\u201313233 (2021)","DOI":"10.1609\/aaai.v35i15.17562"},{"key":"779_CR39","first-page":"1064","volume-title":"Auto-FuzzyJoin: Auto-program Fuzzy Similarity Joins Without Labeled Examples","author":"P Li","year":"2021","unstructured":"Li, P., Cheng, X., Chu, X., He, Y., Chaudhuri, S.: Auto-FuzzyJoin: Auto-program Fuzzy Similarity Joins Without Labeled Examples, pp. 1064\u20131076. Association for Computing Machinery, New York (2021)"},{"key":"779_CR40","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, J., Suhara, Y., Doan, A., Tan, W.C.: Deep entity matching with pre-trained language models (2020). arXiv preprint arXiv:2004.00584","DOI":"10.14778\/3421424.3421431"},{"issue":"1","key":"779_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3431816","volume":"13","author":"Y Li","year":"2021","unstructured":"Li, Y., Li, J., Suhara, Y., Wang, J., Hirota, W., Tan, W.C.: Deep entity matching: challenges and opportunities. J. Data Inf. Qual. (JDIQ) 13(1), 1\u201317 (2021)","journal-title":"J. Data Inf. Qual. (JDIQ)"},{"key":"779_CR42","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: RoBERTa: a robustly optimized bert pretraining approach (2019). arXiv preprint arXiv:1907.11692"},{"key":"779_CR43","doi-asserted-by":"crossref","unstructured":"Marcus, A., Wu, E., Karger, D.R., Madden, S., Miller R.C.: Human-powered sorts and joins. PVLDB 5(1), 13\u201324 (2011)","DOI":"10.14778\/2047485.2047487"},{"key":"779_CR44","doi-asserted-by":"crossref","unstructured":"Meduri, V.V., Popa, L., Sen, P., Sarwat, M.: A comprehensive benchmark framework for active learning methods in entity matching. In: SIGMOD, pp. 1133\u20131147 (2020)","DOI":"10.1145\/3318464.3380597"},{"key":"779_CR45","doi-asserted-by":"crossref","unstructured":"Miao, Z., Li, Y., Wang, X.: Rotom: a meta-learned data augmentation framework for entity matching, data cleaning, text classification, and beyond. In: SIGMOD, pp. 1303\u20131316 (2021)","DOI":"10.1145\/3448016.3457258"},{"key":"779_CR46","doi-asserted-by":"crossref","unstructured":"Miao, Z., Li, Y., Wang, X., Tan, W.C.: Snippext: semi-supervised opinion mining with augmented data. In: Proceedings of WWW \u201920 (2020)","DOI":"10.1145\/3366423.3380144"},{"key":"779_CR47","unstructured":"Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: Proceedings of EMNLP \u201904, pp. 404\u2013411 (2004)"},{"key":"779_CR48","unstructured":"Mitchell, T.M., et al.: Machine Learning, vol. 45, no. 37, pp. 870\u2013877. McGraw Hill, Burr Ridge (1997)"},{"key":"779_CR49","doi-asserted-by":"crossref","unstructured":"Mudgal, S., Li, H., Rekatsinas, T., Doan, A., Park, Y., Krishnan, G., Deep, R., Arcaute, E., Raghavendra, V.: Deep learning for entity matching: a design space exploration. In: Proceedings of SIGMOD \u201918, pp. 19\u201334 (2018)","DOI":"10.1145\/3183713.3196926"},{"key":"779_CR50","doi-asserted-by":"crossref","unstructured":"Papadakis, G., Skoutas, D., Thanos, E., Palpanas, T.: Blocking and filtering techniques for entity resolution: a survey (2019). arXiv preprint arXiv:1905.06167","DOI":"10.1145\/3377455"},{"key":"779_CR51","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Proceedings of NeurIPS \u201919, pp. 8024\u20138035 (2019)"},{"key":"779_CR52","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"779_CR53","doi-asserted-by":"crossref","unstructured":"Peeters, R., Bizer, C.: Cross-language learning for entity matching (2021). arXiv preprint arXiv:2110.03338","DOI":"10.1145\/3487553.3524234"},{"issue":"10","key":"779_CR54","first-page":"1913","volume":"14","author":"R Peeters","year":"2021","unstructured":"Peeters, R., Bizer, C.: Dual-objective fine-tuning of bert for entity matching. PVLDB 14(10), 1913\u20131921 (2021)","journal-title":"PVLDB"},{"key":"779_CR55","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of EMNLP \u201914, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"779_CR56","doi-asserted-by":"crossref","unstructured":"Primpeli, A., Peeters, R., Bizer, C.: The WDC training dataset and gold standard for large-scale product matching. In: Companion Proceedings of WWW \u201919, pp. 381\u2013386 (2019)","DOI":"10.1145\/3308560.3316609"},{"key":"779_CR57","doi-asserted-by":"crossref","unstructured":"Qian, K., Popa, L., Sen, P.: Active learning for large-scale entity resolution. In: CIKM, pp. 1379\u20131388 (2017)","DOI":"10.1145\/3132847.3132949"},{"issue":"8","key":"779_CR58","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"issue":"140","key":"779_CR59","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"779_CR60","first-page":"269","volume":"11","author":"A Ratner","year":"2017","unstructured":"Ratner, A., Bach, S.H., Ehrenberg, H., Fries, J., Wu, S., R\u00e9, C.: Snorkel: rapid training data creation with weak supervision. PVLDB 11, 269 (2017)","journal-title":"PVLDB"},{"key":"779_CR61","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of EMNLP-IJCNLP \u201919, pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"779_CR62","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cWhy should I trust you?\u201d: explaining the predictions of any classifier. In: ACM SIGKDD, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"779_CR63","doi-asserted-by":"crossref","unstructured":"Rush, A.M., Chopra, S., Weston, J.: A neural attention model for abstractive sentence summarization. In: Proceedings of EMNLP \u201915 (2015)","DOI":"10.18653\/v1\/D15-1044"},{"key":"779_CR64","doi-asserted-by":"crossref","unstructured":"Saeedi, A., Peukert, E., Rahm, E.: Using link features for entity clustering in knowledge graphs. In: ESWC, Lecture Notes in Computer Science, vol. 10843, pp. 576\u2013592. Springer (2018)","DOI":"10.1007\/978-3-319-93417-4_37"},{"key":"779_CR65","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In: Proceedings of $$\\text{EMC}^2$$ \u201919 (2019)"},{"key":"779_CR66","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Bhamidipaty, A.: Interactive deduplication using active learning. In: Proceedings of KDD \u201902, pp. 269\u2013278 (2002)","DOI":"10.1145\/775047.775087"},{"issue":"2","key":"779_CR67","first-page":"189","volume":"11","author":"R Singh","year":"2017","unstructured":"Singh, R., Meduri, V.V., Elmagarmid, A., Madden, S., Papotti, P., Quian\u00e9-Ruiz, J.A., Solar-Lezama, A., Tang, N.: Synthesizing entity matching rules by examples. PVLDB 11(2), 189\u2013202 (2017)","journal-title":"PVLDB"},{"key":"779_CR68","unstructured":"Spacy: https:\/\/spacy.io\/api\/entityrecognizer"},{"key":"779_CR69","doi-asserted-by":"crossref","unstructured":"Stoyanovich, J., Howe, B., Jagadish, H.V.: Responsible data management. PVLDB 13(12), 3474\u20133488 (2020)","DOI":"10.14778\/3415478.3415570"},{"key":"779_CR70","unstructured":"Sun, Y., Wang, S., Li, Y., Feng, S., Chen, X., Zhang, H., Tian, X., Zhu, D., Tian, H., Wu, H.: ERNIE: enhanced representation through knowledge integration (2019). arXiv preprint arXiv:1904.09223"},{"issue":"3","key":"779_CR71","first-page":"699","volume":"15","author":"S Suri","year":"2021","unstructured":"Suri, S., Ilyas, I.F., R\u00e9, C., Rekatsinas, T.: Ember: no-code context enrichment via similarity-based keyless joins. PVLDB 15(3), 699\u2013712 (2021)","journal-title":"PVLDB"},{"issue":"8","key":"779_CR72","first-page":"1254","volume":"14","author":"N Tang","year":"2021","unstructured":"Tang, N., Fan, J., Li, F., Tu, J., Du, X., Li, G., Madden, S., Ouzzani, M.: RPT: relational pre-trained transformer is almost all you need towards democratizing data preparation. PVLDB 14(8), 1254\u20131261 (2021)","journal-title":"PVLDB"},{"key":"779_CR73","doi-asserted-by":"crossref","unstructured":"Tenney, I., Das, D., Pavlick, E.: BERT rediscovers the classical NLP pipeline. In: Proceedings of ACL \u201919, pp. 4593\u20134601 (2019)","DOI":"10.18653\/v1\/P19-1452"},{"key":"779_CR74","doi-asserted-by":"crossref","unstructured":"Teofili, T., Firmani, D., Koudas, N., Martello, V., Merialdo, P., Srivastava, D.: Effective explanations for entity resolution models. In: ICDE, pp. 2709\u20132721. IEEE (2022)","DOI":"10.1109\/ICDE53745.2022.00248"},{"issue":"11","key":"779_CR75","first-page":"2459","volume":"14","author":"S Thirumuruganathan","year":"2021","unstructured":"Thirumuruganathan, S., Li, H., Tang, N., Ouzzani, M., Govind, Y., Paulsen, D., Fung, G., Doan, A.: Deep learning for blocking in entity matching: a design space exploration. PVLDB 14(11), 2459\u20132472 (2021)","journal-title":"PVLDB"},{"issue":"12","key":"779_CR76","first-page":"3666","volume":"15","author":"J Tu","year":"2022","unstructured":"Tu, J., Han, X., Fan, J., Tang, N., Chai, C., Li, G., Du, X.: Dader: hands-off entity resolution with domain adaptation. PVLDB 15(12), 3666\u20133669 (2022)","journal-title":"PVLDB"},{"key":"779_CR77","first-page":"223","volume":"12","author":"P Varma","year":"2018","unstructured":"Varma, P., R\u00e9, C.: Snuba: automating weak supervision to label training data. PVLDB 12, 223 (2018)","journal-title":"PVLDB"},{"key":"779_CR78","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Proceedings of NIPS \u201917, pp. 5998\u20136008 (2017)"},{"issue":"11","key":"779_CR79","first-page":"1483","volume":"5","author":"J Wang","year":"2012","unstructured":"Wang, J., Kraska, T., Franklin, M.J., Feng, J.: CrowdER: crowdsourcing entity resolution. PVLDB 5(11), 1483\u20131494 (2012)","journal-title":"PVLDB"},{"issue":"10","key":"779_CR80","first-page":"622","volume":"4","author":"J Wang","year":"2011","unstructured":"Wang, J., Li, G., Yu, J.X., Feng, J.: Entity matching: how similar is similar. PVLDB 4(10), 622\u2013633 (2011)","journal-title":"PVLDB"},{"key":"779_CR81","doi-asserted-by":"crossref","unstructured":"Wang, P., Zheng, W., Wang, J., Pei, J.: Automating entity matching model development. In: ICDE, pp. 1296\u20131307. IEEE (2021)","DOI":"10.1109\/ICDE51399.2021.00116"},{"issue":"1","key":"779_CR82","first-page":"166","volume":"28","author":"Q Wang","year":"2015","unstructured":"Wang, Q., Cui, M., Liang, H.: Semantic-aware blocking for entity resolution. TKDE 28(1), 166\u2013180 (2015)","journal-title":"TKDE"},{"key":"779_CR83","doi-asserted-by":"crossref","unstructured":"Wang, X., He, X., Cao, Y., Liu, M., Chua, T.S.: KGAT: knowledge graph attention network for recommendation. In: Proceedings of KDD \u201919, pp. 950\u2013958 (2019)","DOI":"10.1145\/3292500.3330989"},{"key":"779_CR84","unstructured":"WDC Product Data Corpus: http:\/\/webdatacommons.org\/largescaleproductcorpus\/v2"},{"key":"779_CR85","doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. In: Proceedings of EMNLP-IJCNLP \u201919, pp. 6382\u20136388 (2019)","DOI":"10.18653\/v1\/D19-1670"},{"key":"779_CR86","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et\u00a0al.: Huggingface\u2019s transformers: state-of-the-art natural language processing (2019). arXiv preprint arXiv:1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"779_CR87","doi-asserted-by":"crossref","unstructured":"Wu, R., Bendeck, A., Chu, X., He, Y.: Ground truth inference for weakly supervised entity matching (2022). arXiv preprint arXiv:2211.06975","DOI":"10.1145\/3588712"},{"key":"779_CR88","doi-asserted-by":"crossref","unstructured":"Wu, R., Chaba, S., Sawlani, S., Chu, X., Thirumuruganathan, S.: Zeroer: entity resolution using zero labeled examples. In: SIGMOD, pp. 1149\u20131164. Association for Computing Machinery, New York (2020)","DOI":"10.1145\/3318464.3389743"},{"issue":"12","key":"779_CR89","first-page":"2735","volume":"14","author":"R Wu","year":"2021","unstructured":"Wu, R., Sakala, P., Li, P., Chu, X., He, Y.: Demonstration of panda: a weakly supervised entity matching system. PVLDB 14(12), 2735\u20132738 (2021)","journal-title":"PVLDB"},{"key":"779_CR90","doi-asserted-by":"crossref","unstructured":"Xiao, C., Wang, W., Lin, X., Yu, J.X., Wang, G.: Efficient similarity joins for near-duplicate detection. TODS 36(3), 15:1\u201315:41 (2011)","DOI":"10.1145\/2000824.2000825"},{"key":"779_CR91","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation (2019). arXiv preprint arXiv:1904.12848"},{"key":"779_CR92","doi-asserted-by":"crossref","unstructured":"Yang, B., Mitchell, T.: Leveraging knowledge bases in LSTMs for improving machine reading. In: Proceedings of ACL \u201917, pp. 1436\u20131446 (2017)","DOI":"10.18653\/v1\/P17-1132"},{"key":"779_CR93","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: Proceedings of NeurIPS \u201919, pp. 5754\u20135764 (2019)"},{"issue":"3","key":"779_CR94","first-page":"1501","volume":"34","author":"D Zhang","year":"2022","unstructured":"Zhang, D., Li, D., Guo, L., Tan, K.: Unsupervised entity resolution with blocking and graph algorithms. TKDE 34(3), 1501\u20131515 (2022)","journal-title":"TKDE"},{"key":"779_CR95","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: Proceedings of ICLR \u201918 (2018)"},{"key":"779_CR96","doi-asserted-by":"crossref","unstructured":"Zhao, C., He, Y.: Auto-EM: end-to-end fuzzy entity-matching using pre-trained deep models and transfer learning. In: Proceedings of WWW \u201919, pp. 2413\u20132424 (2019)","DOI":"10.1145\/3308558.3313578"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-023-00779-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00778-023-00779-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-023-00779-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T06:07:25Z","timestamp":1697782045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00778-023-00779-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,17]]},"references-count":96,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["779"],"URL":"https:\/\/doi.org\/10.1007\/s00778-023-00779-z","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,17]]},"assertion":[{"value":"1 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}