{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:05:47Z","timestamp":1784217947981,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":50,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819203680","type":"print"},{"value":"9789819203697","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-92-0369-7_38","type":"book-chapter","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T11:14:54Z","timestamp":1778498094000},"page":"608-625","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic String Data Validation with\u00a0Pattern Discovery"],"prefix":"10.1007","author":[{"given":"Ziyan","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinwei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Makoto","family":"Onizuka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuzhang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"key":"38_CR1","unstructured":"Kaggle. https:\/\/www.kaggle.com\/"},{"key":"38_CR2","unstructured":"Ataccama one (2017). https:\/\/www.ataccama.com\/"},{"key":"38_CR3","unstructured":"Excel (2023). https:\/\/www.microsoft.com\/en-us\/microsoft-365\/excel"},{"key":"38_CR4","unstructured":"OpenRefine (2023). https:\/\/openrefine.org\/docs"},{"key":"38_CR5","unstructured":"Power BI: Data Flow (2023). https:\/\/docs.microsoft.com\/en-us\/power-bi\/transform-model\/service-dataflows-create-use"},{"key":"38_CR6","unstructured":"SSIS (2023). https:\/\/docs.microsoft.com\/en-us\/sql\/integration-services\/control-flow\/data-profiling-task?view=sql-server-ver15"},{"key":"38_CR7","unstructured":"Trifacta (2023). https:\/\/www.trifacta.com\/"},{"issue":"4","key":"38_CR8","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/s00778-015-0389-y","volume":"24","author":"Z Abedjan","year":"2015","unstructured":"Abedjan, Z., Golab, L., Naumann, F.: Profiling relational data: a survey. VLDB J. 24(4), 557\u2013581 (2015)","journal-title":"VLDB J."},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Agichtein, E., Ganti, V.: Mining reference tables for automatic text segmentation. In: KDD, pp. 20\u201329 (2004)","DOI":"10.1145\/1014052.1014058"},{"issue":"2","key":"38_CR10","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/0890-5401(87)90052-6","volume":"75","author":"D Angluin","year":"1987","unstructured":"Angluin, D.: Learning regular sets from queries and counter examples. Inf. Comput. 75(2), 87\u2013106 (1987)","journal-title":"Inf. Comput."},{"issue":"8","key":"38_CR11","first-page":"880","volume":"11","author":"L Berti-\u00c9quille","year":"2018","unstructured":"Berti-\u00c9quille, L., Harmouch, H., Naumann, F., Novelli, N., Saravanan, T.: Discovery of genuine functional dependencies from relational data with missing values. PVLDB 11(8), 880\u2013892 (2018)","journal-title":"PVLDB"},{"key":"38_CR12","unstructured":"Biessmann, F., Golebiowski, J., Rukat, T., Lange, D., Schmidt, P.: Automated data validation in machine learning systems. IEEE Data Eng. Bull. (2021)"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"B\u00f6hme, M., Soremekun, E.O., Chattopadhyay, S., Ugherughe, E., Zeller, A.: Where is the bug and how is it fixed? an experiment with practitioners. In: ESEC\/FSE, pp. 117\u2013128 (2017)","DOI":"10.1145\/3106237.3106255"},{"key":"38_CR14","unstructured":"Breck, E., Polyzotis, N., Roy, S., Whang, S., Zinkevich, M.: Data validation for machine learning. In: MLSys (2019)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Chu, X., He, Y., Chakrabarti, K., Ganjam, K.: Tegra: Table extraction by global record alignment. In: SIGMOD, pp. 1713\u20131728 (2015)","DOI":"10.1145\/2723372.2723725"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Cortez, E., Oliveira, D., da\u00a0Silva, A.S., de\u00a0Moura, E.S., Laender, A.H.: Joint unsupervised structure discovery and information extraction. In: SIGMOD, pp. 541\u2013552 (2011)","DOI":"10.1145\/1989323.1989380"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Du, M., Li, F.: Spell: Streaming parsing of system event logs. In: ICDM, pp. 859\u2013864 (2016)","DOI":"10.1109\/ICDM.2016.0103"},{"issue":"1","key":"38_CR18","first-page":"1078","volume":"2","author":"H Elmeleegy","year":"2009","unstructured":"Elmeleegy, H., Madhavan, J., Halevy, A.: Harvesting relational tables from lists on the web. PVLDB 2(1), 1078\u20131089 (2009)","journal-title":"PVLDB"},{"issue":"4","key":"38_CR19","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1016\/j.ic.2008.12.008","volume":"207","author":"H Fernau","year":"2009","unstructured":"Fernau, H.: Algorithms for learning regular expressions from positive data. Inf. Comput. 207(4), 521\u2013541 (2009)","journal-title":"Inf. Comput."},{"issue":"6","key":"38_CR20","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1145\/1064978.1065046","volume":"40","author":"K Fisher","year":"2005","unstructured":"Fisher, K., Gruber, R.: Pads: a domain-specific language for processing Ad hoc data. ACM Sigplan Notices 40(6), 295\u2013304 (2005)","journal-title":"ACM Sigplan Notices"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Fisher, K., Walker, D.: The pads project: an overview. In: ICDT, pp. 11\u201317 (2011)","DOI":"10.1145\/1938551.1938556"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Gao, Y., Huang, S., Parameswaran, A.: Navigating the data lake with datamaran: automatically extracting structure from log datasets. In: SIGMOD, pp. 943\u2013958 (2018)","DOI":"10.1145\/3183713.3183746"},{"issue":"1\u20132","key":"38_CR23","first-page":"1641","volume":"3","author":"L Golab","year":"2010","unstructured":"Golab, L., Karloff, H., Korn, F., Srivastava, D.: Data auditor: exploring data quality and semantics using pattern tableaux. PVLDB 3(1\u20132), 1641\u20131644 (2010)","journal-title":"PVLDB"},{"issue":"3","key":"38_CR24","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/S0019-9958(78)90562-4","volume":"37","author":"EM Gold","year":"1978","unstructured":"Gold, E.M.: Complexity of automaton identification from given data. Inf. Control 37(3), 302\u2013320 (1978)","journal-title":"Inf. Control"},{"key":"38_CR25","doi-asserted-by":"crossref","unstructured":"Goues, C.L., Dewey-Vogt, M., Forrest, S., Weimer, W.: A systematic study of automated program repair: Fixing 55 out of 105 bugs for 8 each. In: ICSE, pp. 3\u201313 (2012)","DOI":"10.1109\/ICSE.2012.6227211"},{"issue":"1","key":"38_CR26","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1145\/1925844.1926423","volume":"46","author":"S Gulwani","year":"2011","unstructured":"Gulwani, S.: Automating string processing in spreadsheets using input-output examples. ACM Sigplan Notices 46(1), 317\u2013330 (2011)","journal-title":"ACM Sigplan Notices"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Hulsebos, M., Hu, K., Bakker, M., Zgraggen, E., Satyanarayan, A., Kraska, T., Demiralp, \u00c7., Hidalgo, C.: Sherlock: A deep learning approach to semantic data type detection. In: KDD, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3292500.3330993"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Ilyas, A., da\u00a0Trindade, J.M., Fernandez, R.C., Madden, S.: Extracting syntactical patterns from databases. In: ICDE, pp. 41\u201352 (2018)","DOI":"10.1109\/ICDE.2018.00014"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Kirschner, L., Soremekun, E.O., Zeller, A.: Debugging inputs. In: ICSE, pp. 75\u201386 (2020)","DOI":"10.1145\/3377811.3380329"},{"key":"38_CR30","unstructured":"Klettke, M., St\u00f6rl, U., Scherzinger, S.: Schema extraction and structural outlier detection for json-based nosql data stores. BTW (2015)"},{"key":"38_CR31","doi-asserted-by":"crossref","unstructured":"Kozielski, S., Wrembel, R.: New Trends in Data Warehousing and Data Analysis. Springer, Cham (2009)","DOI":"10.1007\/978-0-387-87431-9"},{"key":"38_CR32","doi-asserted-by":"crossref","unstructured":"Padhi, S., Jain, P., Perelman, D., Polozov, O., Gulwani, S., Millstein, T.: Flashprofile: a framework for synthesizing data profiles. PACMPL 2(OOPSLA), 1\u201328 (2018)","DOI":"10.1145\/3276520"},{"issue":"1","key":"38_CR33","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/138027.138042","volume":"40","author":"L Pitt","year":"1993","unstructured":"Pitt, L., Warmuth, M.K.: The minimum consistent DFA problem cannot be approximated within any polynomial. J. ACM 40(1), 95\u2013142 (1993)","journal-title":"J. ACM"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Polyzotis, N., Roy, S., Whang, S.E., Zinkevich, M.: Data management challenges in production machine learning. In: SIGMOD, pp. 1723\u20131726 (2017)","DOI":"10.1145\/3035918.3054782"},{"issue":"5","key":"38_CR35","first-page":"684","volume":"13","author":"A Qahtan","year":"2020","unstructured":"Qahtan, A., Tang, N., Ouzzani, M., Cao, Y., Stonebraker, M.: Pattern functional dependencies for data cleaning. PVLDB 13(5), 684\u2013697 (2020)","journal-title":"PVLDB"},{"key":"38_CR36","unstructured":"Raman, V., Hellerstein, J.M.: Potter\u2019s wheel: An interactive data cleaning system. In: PVLDB, pp. 381\u2013390 (2001)"},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Schelter, S., et al.: Unit testing data with deequ. In: SIGMOD, pp. 1993\u20131996 (2019)","DOI":"10.1145\/3299869.3320210"},{"key":"38_CR38","doi-asserted-by":"crossref","unstructured":"Schelter, S., Lange, D., Schmidt, P., Celikel, M., Biessmann, F., Grafberger, A.: Automating large-scale data quality verification. PVLDB 11(12), 1781\u20131794 (2018)","DOI":"10.14778\/3229863.3229867"},{"key":"38_CR39","doi-asserted-by":"crossref","unstructured":"Song, J., He, Y.: Auto-Validate: Unsupervised data validation using data-domain patterns inferred from data lakes. In: SIGMOD, pp. 1678\u20131691 (2021)","DOI":"10.1145\/3448016.3457250"},{"key":"38_CR40","doi-asserted-by":"crossref","unstructured":"Teoh, J., Gulzar, M.A., Xu, G.H., Kim, M.: Perfdebug: Performance debugging of computation skew in dataflow systems. In: SoCC, pp. 465\u2013476 (2019)","DOI":"10.1145\/3357223.3362727"},{"issue":"4","key":"38_CR41","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1089\/cmb.1994.1.337","volume":"1","author":"L Wang","year":"1994","unstructured":"Wang, L., Jiang, T.: On the complexity of multiple sequence alignment. J. Comput. Biol. 1(4), 337\u2013348 (1994)","journal-title":"J. Comput. Biol."},{"key":"38_CR42","doi-asserted-by":"crossref","unstructured":"Wang, P., He, Y.: Uni-detect: a unified approach to automated error detection in tables. In: SIGMOD, pp. 811\u2013828 (2019)","DOI":"10.1145\/3299869.3319855"},{"issue":"10","key":"38_CR43","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1145\/3022671.2984030","volume":"51","author":"X Wang","year":"2016","unstructured":"Wang, X., Gulwani, S., Singh, R.: FIDEX: filtering spreadsheet data using examples. ACM SIGPLAN Notices 51(10), 195\u2013213 (2016)","journal-title":"ACM SIGPLAN Notices"},{"key":"38_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111488","volume":"194","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Chen, T.P., Zhang, H., Wang, S.: An empirical study on the challenges that developers encounter when developing apache spark applications. J. Syst. Softw. 194, 111488 (2022)","journal-title":"J. Syst. Softw."},{"key":"38_CR45","doi-asserted-by":"crossref","unstructured":"Wen, M., Chen, J., Wu, R., Hao, D., Cheung, S.: Context-aware patch generation for better automated program repair. In: ICSE, pp. 1\u201311 (2018)","DOI":"10.1145\/3180155.3180233"},{"issue":"8","key":"38_CR46","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1109\/TSE.2016.2521368","volume":"42","author":"WE Wong","year":"2016","unstructured":"Wong, W.E., Gao, R., Li, Y., Abreu, R., Wotawa, F.: A survey on software fault localization. IEEE Trans. Software Eng. 42(8), 707\u2013740 (2016)","journal-title":"IEEE Trans. Software Eng."},{"key":"38_CR47","doi-asserted-by":"crossref","unstructured":"Yan, C., He, Y.: Synthesizing type-detection logic for rich semantic data types using open-source code. In: SIGMOD, pp. 35\u201350 (2018)","DOI":"10.1145\/3183713.3196888"},{"issue":"2","key":"38_CR48","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/32.988498","volume":"28","author":"A Zeller","year":"2002","unstructured":"Zeller, A., Hildebrandt, R.: Simplifying and isolating failure-inducing input. IEEE Trans. Software Eng. 28(2), 183\u2013200 (2002)","journal-title":"IEEE Trans. Software Eng."},{"issue":"11","key":"38_CR49","first-page":"1835","volume":"13","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Suhara, Y., Li, J., Hulsebos, M., Demiralp, \u00c7., Tan, W.C.: Sato: contextual semantic type detection in tables. PVLDB 13(11), 1835\u20131848 (2020)","journal-title":"PVLDB"},{"key":"38_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wang, J., Gulzar, M.A., Padhye, R., Kim, M.: Bigfuzz: efficient fuzz testing for data analytics using framework abstraction. In: ASE, pp. 722\u2013733 (2020)","DOI":"10.1145\/3324884.3416641"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0369-7_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:24:49Z","timestamp":1784215489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0369-7_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819203680","9789819203697"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0369-7_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2026.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}