{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T17:00:39Z","timestamp":1784998839896,"version":"3.55.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032022141","type":"print"},{"value":"9783032022158","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-02215-8_8","type":"book-chapter","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T17:30:08Z","timestamp":1755624608000},"page":"111-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Entity Resolution for\u00a0Streaming Data with\u00a0Embeddings"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4276-1821","authenticated-orcid":false,"given":"Zhongwei","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2227-3283","authenticated-orcid":false,"given":"Philippe","family":"Roose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2066-7051","authenticated-orcid":false,"given":"Jiefu","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"8_CR1","unstructured":"Almeida, F., Xex\u00e9o, G.: Word embeddings: a survey (2023)"},{"issue":"3","key":"8_CR2","doi-asserted-by":"publisher","first-page":"120","DOI":"10.14778\/2850583.2850587","volume":"9","author":"H Altwaijry","year":"2015","unstructured":"Altwaijry, H., Mehrotra, S., Kalashnikov, D.V.: Query: a framework for integrating entity resolution with query processing. Proc. VLDB Endow. 9(3), 120\u2013131 (2015)","journal-title":"Proc. VLDB Endow."},{"issue":"3","key":"8_CR3","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1405","volume":"11","author":"M Bahri","year":"2021","unstructured":"Bahri, M., Bifet, A., Gama, J., Gomes, H.M., Maniu, S.: Data stream analysis: foundations, major tasks and tools. WIREs Data Min. Knowl. Discov. 11(3), e1405 (2021). https:\/\/doi.org\/10.1002\/widm.1405","journal-title":"WIREs Data Min. Knowl. Discov."},{"issue":"1","key":"8_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3483595","volume":"55","author":"CDT Barros","year":"2021","unstructured":"Barros, C.D.T., Mendon\u00e7a, M.R.F., Vieira, A.B., Ziviani, A.: A survey on embedding dynamic graphs. ACM Comput. Surv. 55(1), 1\u201337 (2021)","journal-title":"ACM Comput. Surv."},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Binette, O., Steorts, R.C.: (Almost) all of entity resolution. Sci. Adv. 8(12), eabi8021 (2022)","DOI":"10.1126\/sciadv.abi8021"},{"issue":"1","key":"8_CR6","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/s12559-021-09831-y","volume":"14","author":"F Bravo-Marquez","year":"2021","unstructured":"Bravo-Marquez, F., Khanchandani, A., Pfahringer, B.: Incremental word vectors for time-evolving sentiment lexicon induction. Cogn. Comput. 14(1), 425\u2013441 (2021). https:\/\/doi.org\/10.1007\/s12559-021-09831-y","journal-title":"Cogn. Comput."},{"key":"8_CR7","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures - a step forward in data integration. In: Proceedings of the 23rd International Conference on Extending Database Technology (EDBT) (2020)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Cappuzzo, R., Papotti, P., Thirumuruganathan, S.: Creating embeddings of heterogeneous relational datasets for data integration tasks. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, Portland, OR, USA, pp. 1335\u20131349. ACM (2020)","DOI":"10.1145\/3318464.3389742"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Chen, R., Shen, Y., Zhang, D.: Gnem: a generic one-to-set neural entity matching framework. In: Proceedings of the Web Conference 2021, Ljubljana, Slovenia, pp. 1686\u20131694. ACM (2021). https:\/\/doi.org\/10.1145\/3442381.3450119","DOI":"10.1145\/3442381.3450119"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Christophides, V., Efthymiou, V., Palpanas, T., Papadakis, G., Stefanidis, K.: An overview of end-to-end entity resolution for big data. ACM Comput. Surv. (2020)","DOI":"10.1145\/3418896"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/j.jss.2017.11.074","volume":"137","author":"DC Do Nascimento","year":"2018","unstructured":"Do Nascimento, D.C., Santos Pires, C.E., Gomes Mestre, D.: Heuristic-based approaches for speeding up incremental record linkage. J. Syst. Softw. 137, 335\u2013354 (2018)","journal-title":"J. Syst. Softw."},{"issue":"11","key":"8_CR12","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.14778\/3236187.3236198","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. Proc. VLDB Endow. 11(11), 1454\u20131467 (2018)","journal-title":"Proc. VLDB Endow."},{"key":"8_CR13","unstructured":"Efthymiou, V., Papadakis, G., Stefanidis, K., Christophides, V.: Minoaner: schema-agnostic, non-iterative, massively parallel resolution of web entities. In: Proceedings of the 22nd International Conference on Extending Database Technology (EDBT) (2019)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gazzarri, L., Herschel, M.: End-to-end task based parallelization for entity resolution on dynamic data. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), Chania, Greece, pp. 1248\u20131259. IEEE (2021)","DOI":"10.1109\/ICDE51399.2021.00112"},{"key":"8_CR15","unstructured":"Gazzarri, L., Herschel, M.: Progressive entity resolution over incremental data. In: Proceedings of the 26th International Conference on Extending Database Technology (EDBT). OpenProceedings.org (2023)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Genossar, B., Shraga, R., Gal, A.: Flexer: flexible entity resolution for multiple intents. Proc. ACM Manag. Data 1(1) (2023)","DOI":"10.1145\/3588722"},{"key":"8_CR17","doi-asserted-by":"publisher","first-page":"154300","DOI":"10.1109\/ACCESS.2019.2946884","volume":"7","author":"H Isah","year":"2019","unstructured":"Isah, H., Abughofa, T., Mahfuz, S., Ajerla, D., Zulkernine, F., Khan, S.: A survey of distributed data stream processing frameworks. IEEE Access 7, 154300\u2013154316 (2019)","journal-title":"IEEE Access"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Kaji, N., Kobayashi, H.: Incremental skip-gram model with negative sampling. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, pp. 363\u2013371. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/D17-1037"},{"issue":"1","key":"8_CR19","doi-asserted-by":"publisher","first-page":"50","DOI":"10.14778\/3421424.3421431","volume":"14","author":"Y Li","year":"2020","unstructured":"Li, Y., Li, J., Suhara, Y., Doan, A., Tan, W.C.: Deep entity matching with pre-trained language models. Proc. VLDB Endow. 14(1), 50\u201360 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Maharana, K., Mondal, S., Nemade, B.: A review: data pre-processing and data augmentation techniques. Glob. Transit. Proc. 3(1), 91\u201399 (2022). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2666285X22000565. International Conference on Intelligent Engineering Approach (ICIEA-2022)","DOI":"10.1016\/j.gltp.2022.04.020"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Mahdavi, S., Khoshraftar, S., An, A.: dynnode2vec: scalable dynamic network embedding arXiv:1812.02356 (2019)","DOI":"10.1109\/BigData.2018.8621910"},{"key":"8_CR22","unstructured":"Marz, N., Warren, J.: Big Data: Principles and Best Practices of Scalable Realtime Data Systems, 1st edn. Manning Publications Co., USA (2015)"},{"key":"8_CR23","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS 2013, pp. 3111\u20133119. Curran Associates Inc., Red Hook (2013)"},{"issue":"2","key":"8_CR24","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/0167-6423(82)90012-0","volume":"2","author":"J Misra","year":"1982","unstructured":"Misra, J., Gries, D.: Finding repeated elements. Sci. Comput. Program. 2(2), 143\u2013152 (1982)","journal-title":"Sci. Comput. Program."},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Mudgal, S., et al.: Deep learning for entity matching: a design space exploration. In: Proceedings of the 2018 International Conference on Management of Data, Houston, TX, USA, pp. 19\u201334. ACM (2018)","DOI":"10.1145\/3183713.3196926"},{"issue":"6","key":"8_CR26","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1007\/s00778-023-00791-3","volume":"32","author":"G Papadakis","year":"2023","unstructured":"Papadakis, G., Efthymiou, V., Thanos, E., Hassanzadeh, O., Christen, P.: An analysis of one-to-one matching algorithms for entity resolution. VLDB J. 32(6), 1369\u20131400 (2023)","journal-title":"VLDB J."},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Peng, H., et al.: Incremental term representation learning for social network analysis. Future Gener. Comput. Syst. 86 (2017)","DOI":"10.1016\/j.future.2017.05.020"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"8_CR29","unstructured":"\u0158eh\u016f\u0159ek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, Valletta, Malta, pp. 45\u201350. ELRA (2010)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Ren, W., Lian, X., Ghazinour, K.: Online topic-aware entity resolution over incomplete data streams. In: Proceedings of the 2021 International Conference on Management of Data, SIGMOD 2021, pp. 1478\u20131490. Association for Computing Machinery, New York (2021)","DOI":"10.1145\/3448016.3457238"},{"key":"8_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/978-3-030-49461-2_23","volume-title":"The Semantic Web","author":"A Saeedi","year":"2020","unstructured":"Saeedi, A., Peukert, E., Rahm, E.: Incremental multi-source entity resolution for knowledge graph completion. In: Harth, A., et al. (eds.) ESWC 2020. LNCS, vol. 12123, pp. 393\u2013408. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-49461-2_23"},{"issue":"7","key":"8_CR32","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.14778\/3523210.3523226","volume":"15","author":"G Simonini","year":"2022","unstructured":"Simonini, G., Zecchini, L., Bergamaschi, S., Naumann, F.: Entity resolution on-demand. Proc. VLDB Endow. 15(7), 1506\u20131518 (2022)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"8_CR33","first-page":"1","volume":"1","author":"J Tu","year":"2023","unstructured":"Tu, J., et al.: Unicorn: a unified multi-tasking model for supporting matching tasks in data integration. Proc. ACM Manag. Data 1(1), 1\u201326 (2023)","journal-title":"Proc. ACM Manag. Data"},{"issue":"3","key":"8_CR34","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/s00607-019-00768-7","volume":"102","author":"S Wang","year":"2020","unstructured":"Wang, S., Zhou, W., Jiang, C.: A survey of word embeddings based on deep learning. Computing 102(3), 717\u2013740 (2020)","journal-title":"Computing"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Zeng, X., Wang, P., Mao, Y., Chen, L., Liu, X., Gao, Y.: Multiem: efficient and effective unsupervised multi-table entity matching. In: 2024 IEEE 40th International Conference on Data Engineering (ICDE), pp. 3421\u20133434 (2024)","DOI":"10.1109\/ICDE60146.2024.00264"}],"container-title":["Lecture Notes in Computer Science","Big Data Analytics and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02215-8_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:02:36Z","timestamp":1784995356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02215-8_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"ISBN":["9783032022141","9783032022158"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02215-8_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"19 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DaWaK","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data Analytics and Knowledge Discovery","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dawak2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dexa.org\/2025\/dawak2025.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}