{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T13:10:35Z","timestamp":1767964235447,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030461461","type":"print"},{"value":"9783030461478","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-46147-8_40","type":"book-chapter","created":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T02:03:39Z","timestamp":1588298619000},"page":"665-680","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["NSEEN: Neural Semantic Embedding for Entity Normalization"],"prefix":"10.1007","author":[{"given":"Shobeir","family":"Fakhraei","sequence":"first","affiliation":[]},{"given":"Joel","family":"Mathew","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9 Luis","family":"Ambite","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"40_CR1","unstructured":"University of Southern California - Information Science Institute Entity Grounding System (2018). http:\/\/dna.isi.edu:7100\/"},{"key":"40_CR2","unstructured":"Annoy (approximate nearest neighbors oh yeah) (2019). https:\/\/github.com\/spotify\/annoy"},{"key":"40_CR3","doi-asserted-by":"publisher","first-page":"D115","DOI":"10.1093\/nar\/gkh131","volume":"32","author":"R Apweiler","year":"2004","unstructured":"Apweiler, R., et al.: UniProt: the universal protein knowledgebase. Nucleic Acids Res. 32, D115\u2013D119 (2004)","journal-title":"Nucleic Acids Res."},{"key":"40_CR4","unstructured":"Arighi, C., et al.: Bio-ID track overview. In: Proceedings of the BioCreative VI Workshop (2017)"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Bachrach, Y., et al.: Speeding up the Xbox recommender system using a euclidean transformation for inner-product spaces. In: Proceedings of the 8th ACM Conference on Recommender systems (2014)","DOI":"10.1145\/2645710.2645741"},{"key":"40_CR6","unstructured":"Bia\u0142ecki, A., Muir, R., Ingersoll, G.: Apache Lucene 4. In: SIGIR 2012 Workshop on Open Source Information Retrieval (2012)"},{"key":"40_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/978-3-642-41338-4_19","volume-title":"The Semantic Web \u2013 ISWC 2013","author":"M Cheatham","year":"2013","unstructured":"Cheatham, M., Hitzler, P.: String similarity metrics for ontology alignment. In: Alani, H., et al. (eds.) ISWC 2013, Part II. LNCS, vol. 8219, pp. 294\u2013309. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-41338-4_19"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Chen, H., Perozzi, B., Hu, Y., Skiena, S.: HARP: hierarchical representation learning for networks (2018)","DOI":"10.1609\/aaai.v32i1.11849"},{"key":"40_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"issue":"9","key":"40_CR10","first-page":"1537","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. IEEE TKDE 24(9), 1537\u20131555 (2012)","journal-title":"IEEE TKDE"},{"key":"40_CR11","unstructured":"Cohen, W., Ravikumar, P., Fienberg, S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning and Object Consolidation (2003)"},{"key":"40_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"1","key":"40_CR13","first-page":"1","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE TKDE 19(1), 1\u201316 (2007)","journal-title":"IEEE TKDE"},{"issue":"12","key":"40_CR14","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.14778\/2367502.2367564","volume":"5","author":"L Getoor","year":"2012","unstructured":"Getoor, L., Machanavajjhala, A.: Entity resolution: theory, practice & open challenges. Proc. VLDB Endow. 5(12), 2018\u20132019 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"40_CR15","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2006)"},{"key":"40_CR16","doi-asserted-by":"publisher","first-page":"D1214","DOI":"10.1093\/nar\/gkv1031","volume":"44","author":"J Hastings","year":"2015","unstructured":"Hastings, J., et al.: ChEBI in 2016: improved services and an expanding collection of metabolites. Nucleic Acids Res. 44, D1214\u2013D1219 (2015)","journal-title":"Nucleic Acids Res."},{"issue":"11","key":"40_CR17","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":"40_CR18","unstructured":"Jurczyk, P., Lu, J.J., Xiong, L., Cragan, J.D., Correa, A.: FRIL: a tool for comparative record linkage. In: American Medical Informatics Association (AMIA) Annual Symposium Proceedings (2008)"},{"issue":"5","key":"40_CR19","first-page":"876","volume":"20","author":"N Kang","year":"2012","unstructured":"Kang, N., Singh, B., Afzal, Z., van Mulligen, E.M., Kors, J.A.: Using rule-based natural language processing to improve disease normalization in biomedical text. JAMIA 20(5), 876\u2013881 (2012)","journal-title":"JAMIA"},{"key":"40_CR20","unstructured":"Kotnis, B., Nastase, V.: Analysis of the impact of negative sampling on link prediction in knowledge graphs. In: WSDM 1st Workshop on Knowledge Base Construction, Reasoning and Mining (KBCOM) (2017)"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Koudas, N., Sarawagi, S., Srivastava, D.: Record linkage: similarity measures and algorithms. In: Proceedings of the 2006 ACM SIGMOD International Conference on Management of Data (2006)","DOI":"10.1145\/1142473.1142599"},{"issue":"22","key":"40_CR22","doi-asserted-by":"publisher","first-page":"2909","DOI":"10.1093\/bioinformatics\/btt474","volume":"29","author":"R Leaman","year":"2013","unstructured":"Leaman, R., Islamaj Do\u011fan, R., Lu, Z.: DNorm: disease name normalization with pairwise learning to rank. Bioinformatics 29(22), 2909\u20132917 (2013)","journal-title":"Bioinformatics"},{"issue":"18","key":"40_CR23","doi-asserted-by":"publisher","first-page":"2839","DOI":"10.1093\/bioinformatics\/btw343","volume":"32","author":"R Leaman","year":"2016","unstructured":"Leaman, R., Lu, Z.: TaggerOne: joint named entity recognition and normalization with semi-Markov models. Bioinformatics 32(18), 2839\u20132846 (2016)","journal-title":"Bioinformatics"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: BioBERT: pre-trained biomedical language representation model for biomedical text mining. arXiv preprint arXiv:1901.08746 (2019)","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"40_CR25","unstructured":"Mathew, J., Fakhraei, S., Ambite, J.L.: Biomedical named entity recognition via reference-set augmented bootstrapping. In: ICML Workshop on Computational Biology (2019)"},{"key":"40_CR26","unstructured":"Michelson, M., Knoblock, C.A.: Learning blocking schemes for record linkage. In: AAAI (2006)"},{"key":"40_CR27","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems (2013)"},{"key":"40_CR28","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 (2018)","DOI":"10.1145\/3183713.3196926"},{"key":"40_CR29","unstructured":"Naidan, B., Boytsov, L.: Non-metric space library manual. arXiv preprint arXiv:1508.05470 (2015)"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Neculoiu, P., Versteegh, M., Rotaru, M.: Learning text similarity with siamese recurrent networks. In: Proceedings the 1st Workshop on Representation Learning for NLP (2016)","DOI":"10.18653\/v1\/W16-1617"},{"issue":"9","key":"40_CR31","doi-asserted-by":"publisher","first-page":"684","DOI":"10.14778\/2947618.2947624","volume":"9","author":"G Papadakis","year":"2016","unstructured":"Papadakis, G., Svirsky, J., Gal, A., Palpanas, T.: Comparative analysis of approximate blocking techniques for entity resolution. Proc. VLDB Endow. 9(9), 684\u2013695 (2016)","journal-title":"Proc. VLDB Endow."},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"40_CR33","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of NAACL (2018)","DOI":"10.18653\/v1\/N18-1202"},{"key":"40_CR34","unstructured":"Ponomarenko, A., Avrelin, N., Naidan, B., Boytsov, L.: Comparative analysis of data structures for approximate nearest neighbor search. In: Data Analytics (2014)"},{"key":"40_CR35","unstructured":"Rastegari, M., Choi, J., Fakhraei, S., Hal, D., Davis, L.: Predictable dual-view hashing. In: International Conference on Machine Learning (ICML) (2013)"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"40_CR37","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.220"},{"key":"40_CR38","unstructured":"Yadav, V., Bethard, S.: A survey on recent advances in named entity recognition from deep learning models. In: Proceedings of the 27th International Conference on Computational Linguistics (2018)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-46147-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T09:23:03Z","timestamp":1746523383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-46147-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461461","9783030461478"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46147-8_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"130","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.04","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}