Publication Information

{'id': 'https://openalex.org/W2088008685', 'doi': 'https://doi.org/10.1145/1645953.1645994', 'title': 'Robust record linkage blocking using suffix arrays', 'display_name': 'Robust record linkage blocking using suffix arrays', 'publication_year': 2009, 'publication_date': '2009-11-02', 'ids': {'openalex': 'https://openalex.org/W2088008685', 'doi': 'https://doi.org/10.1145/1645953.1645994', 'mag': '2088008685'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1145/1645953.1645994', 'pdf_url': None, 'source': None, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, 'type': 'article', 'type_crossref': 'proceedings-article', 'indexed_in': ['crossref'], 'open_access': {'is_oa': False, 'oa_status': 'closed', 'oa_url': None, 'any_repository_has_fulltext': False}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5039675586', 'display_name': 'Timothy de Vries', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I129604602', 'display_name': 'University of Sydney', 'ror': 'https://ror.org/0384j8v12', 'country_code': 'AU', 'type': 'education', 'lineage': ['https://openalex.org/I129604602']}], 'countries': ['AU'], 'is_corresponding': False, 'raw_author_name': 'Timothy de Vries', 'raw_affiliation_strings': ['Univ. of Sydney, Sydney, NSW, Australia#TAB#'], 'affiliations': [{'raw_affiliation_string': 'Univ. of Sydney, Sydney, NSW, Australia#TAB#', 'institution_ids': ['https://openalex.org/I129604602']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5110638006', 'display_name': 'Hui Ke', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I129604602', 'display_name': 'University of Sydney', 'ror': 'https://ror.org/0384j8v12', 'country_code': 'AU', 'type': 'education', 'lineage': ['https://openalex.org/I129604602']}], 'countries': ['AU'], 'is_corresponding': False, 'raw_author_name': 'Hui Ke', 'raw_affiliation_strings': ['Univ. of Sydney, Sydney, NSW, Australia#TAB#'], 'affiliations': [{'raw_affiliation_string': 'Univ. of Sydney, Sydney, NSW, Australia#TAB#', 'institution_ids': ['https://openalex.org/I129604602']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5037947876', 'display_name': 'Sanjay Chawla', 'orcid': 'https://orcid.org/0000-0002-8102-2572'}, 'institutions': [{'id': 'https://openalex.org/I129604602', 'display_name': 'University of Sydney', 'ror': 'https://ror.org/0384j8v12', 'country_code': 'AU', 'type': 'education', 'lineage': ['https://openalex.org/I129604602']}], 'countries': ['AU'], 'is_corresponding': False, 'raw_author_name': 'Sanjay Chawla', 'raw_affiliation_strings': ['Univ. of Sydney, Sydney, NSW, Australia#TAB#'], 'affiliations': [{'raw_affiliation_string': 'Univ. of Sydney, Sydney, NSW, Australia#TAB#', 'institution_ids': ['https://openalex.org/I129604602']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5022945960', 'display_name': 'Peter Christen', 'orcid': 'https://orcid.org/0000-0003-3435-2015'}, 'institutions': [{'id': 'https://openalex.org/I118347636', 'display_name': 'Australian National University', 'ror': 'https://ror.org/019wvm592', 'country_code': 'AU', 'type': 'education', 'lineage': ['https://openalex.org/I118347636']}], 'countries': ['AU'], 'is_corresponding': False, 'raw_author_name': 'Peter Christen', 'raw_affiliation_strings': ['Australian National University, Canberra, ACT, Australia'], 'affiliations': [{'raw_affiliation_string': 'Australian National University, Canberra, ACT, Australia', 'institution_ids': ['https://openalex.org/I118347636']}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 2, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 6.482, 'has_fulltext': True, 'fulltext_origin': 'ngrams', 'cited_by_count': 46, 'citation_normalized_percentile': {'value': 0.961589, 'is_in_top_1_percent': False, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 94, 'max': 95}, 'biblio': {'volume': None, 'issue': None, 'first_page': '305', 'last_page': '314'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T11719', 'display_name': 'Data Quality and Management', 'score': 1.0, 'subfield': {'id': 'https://openalex.org/subfields/1803', 'display_name': 'Management Science and Operations Research'}, 'field': {'id': 'https://openalex.org/fields/18', 'display_name': 'Decision Sciences'}, 'domain': {'id': 'https://openalex.org/domains/2', 'display_name': 'Social Sciences'}}, 'topics': [{'id': 'https://openalex.org/T11719', 'display_name': 'Data Quality and Management', 'score': 1.0, 'subfield': {'id': 'https://openalex.org/subfields/1803', 'display_name': 'Management Science and Operations Research'}, 'field': {'id': 'https://openalex.org/fields/18', 'display_name': 'Decision Sciences'}, 'domain': {'id': 'https://openalex.org/domains/2', 'display_name': 'Social Sciences'}}, {'id': 'https://openalex.org/T10764', 'display_name': 'Privacy-Preserving Technologies in Data', 'score': 0.9538, 'subfield': {'id': 'https://openalex.org/subfields/1702', 'display_name': 'Artificial Intelligence'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, {'id': 'https://openalex.org/T12016', 'display_name': 'Web Data Mining and Analysis', 'score': 0.9117, 'subfield': {'id': 'https://openalex.org/subfields/1710', 'display_name': 'Information Systems'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}], 'keywords': [{'id': 'https://openalex.org/keywords/blocking', 'display_name': 'Blocking (statistics)', 'score': 0.61652553}, {'id': 'https://openalex.org/keywords/merge', 'display_name': 'Merge (version control)', 'score': 0.47763982}, {'id': 'https://openalex.org/keywords/suffix-array', 'display_name': 'Suffix array', 'score': 0.47749728}], 'concepts': [{'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.82585156}, {'id': 'https://openalex.org/C75165309', 'wikidata': 'https://www.wikidata.org/wiki/Q2258979', 'display_name': 'Search engine indexing', 'level': 2, 'score': 0.7566541}, {'id': 'https://openalex.org/C48044578', 'wikidata': 'https://www.wikidata.org/wiki/Q727490', 'display_name': 'Scalability', 'level': 2, 'score': 0.70086163}, {'id': 'https://openalex.org/C2779804580', 'wikidata': 'https://www.wikidata.org/wiki/Q102047', 'display_name': 'Suffix', 'level': 2, 'score': 0.63782823}, {'id': 'https://openalex.org/C144745244', 'wikidata': 'https://www.wikidata.org/wiki/Q4927286', 'display_name': 'Blocking (statistics)', 'level': 2, 'score': 0.61652553}, {'id': 'https://openalex.org/C2781166958', 'wikidata': 'https://www.wikidata.org/wiki/Q1426863', 'display_name': 'Suffix tree', 'level': 3, 'score': 0.5764877}, {'id': 'https://openalex.org/C197129107', 'wikidata': 'https://www.wikidata.org/wiki/Q1921621', 'display_name': 'Merge (version control)', 'level': 2, 'score': 0.47763982}, {'id': 'https://openalex.org/C2779259728', 'wikidata': 'https://www.wikidata.org/wiki/Q281472', 'display_name': 'Suffix array', 'level': 3, 'score': 0.47749728}, {'id': 'https://openalex.org/C165696696', 'wikidata': 'https://www.wikidata.org/wiki/Q11287', 'display_name': 'Exploit', 'level': 2, 'score': 0.4704572}, {'id': 'https://openalex.org/C124101348', 'wikidata': 'https://www.wikidata.org/wiki/Q172491', 'display_name': 'Data mining', 'level': 1, 'score': 0.39690453}, {'id': 'https://openalex.org/C162319229', 'wikidata': 'https://www.wikidata.org/wiki/Q175263', 'display_name': 'Data structure', 'level': 2, 'score': 0.38065666}, {'id': 'https://openalex.org/C173608175', 'wikidata': 'https://www.wikidata.org/wiki/Q232661', 'display_name': 'Parallel computing', 'level': 1, 'score': 0.23570472}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.19170406}, {'id': 'https://openalex.org/C77088390', 'wikidata': 'https://www.wikidata.org/wiki/Q8513', 'display_name': 'Database', 'level': 1, 'score': 0.169806}, {'id': 'https://openalex.org/C199360897', 'wikidata': 'https://www.wikidata.org/wiki/Q9143', 'display_name': 'Programming language', 'level': 1, 'score': 0.086373836}, {'id': 'https://openalex.org/C31258907', 'wikidata': 'https://www.wikidata.org/wiki/Q1301371', 'display_name': 'Computer network', 'level': 1, 'score': 0.077031076}, {'id': 'https://openalex.org/C41895202', 'wikidata': 'https://www.wikidata.org/wiki/Q8162', 'display_name': 'Linguistics', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C138885662', 'wikidata': 'https://www.wikidata.org/wiki/Q5891', 'display_name': 'Philosophy', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C38652104', 'wikidata': 'https://www.wikidata.org/wiki/Q3510521', 'display_name': 'Computer security', 'level': 1, 'score': 0.0}], 'mesh': [], 'locations_count': 1, 'locations': [{'is_oa': False, 'landing_page_url': 'https://doi.org/10.1145/1645953.1645994', 'pdf_url': None, 'source': None, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}], 'best_oa_location': None, 'sustainable_development_goals': [], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 18, 'referenced_works': ['https://openalex.org/W118209581', 'https://openalex.org/W1612155886', 'https://openalex.org/W1979821252', 'https://openalex.org/W1997927541', 'https://openalex.org/W2034190452', 'https://openalex.org/W2036216970', 'https://openalex.org/W2073471108', 'https://openalex.org/W2112912553', 'https://openalex.org/W2128661986', 'https://openalex.org/W2139585610', 'https://openalex.org/W2141634619', 'https://openalex.org/W2161600801', 'https://openalex.org/W2164625277', 'https://openalex.org/W2166988329', 'https://openalex.org/W2171574281', 'https://openalex.org/W2334251884', 'https://openalex.org/W36024057', 'https://openalex.org/W4234053595'], 'related_works': ['https://openalex.org/W2583658747', 'https://openalex.org/W2405892617', 'https://openalex.org/W2159613260', 'https://openalex.org/W2158874082', 'https://openalex.org/W2123393931', 'https://openalex.org/W2055795184', 'https://openalex.org/W2003608043', 'https://openalex.org/W1746392762', 'https://openalex.org/W1575722140', 'https://openalex.org/W153119118'], 'abstract_inverted_index': {'Record': [0], 'linkage': [1], 'is': [2, 97], 'an': [3, 46, 111], 'important': [4], 'data': [5, 142], 'integration': [6], 'task': [7], 'that': [8], 'has': [9], 'many': [10], 'practical': [11], 'uses': [12], 'for': [13, 28], 'matching,': [14], 'merging': [15], 'and': [16, 21, 44, 48, 117, 124, 135], 'duplicate': [17], 'removal': [18], 'in': [19, 77, 137], 'large': [20], 'diverse': [22], 'databases.': [23], 'However,': [24], 'a': [25, 78, 104], 'quadratic': [26], 'scalability': [27, 86], 'the': [29, 34, 62, 66, 84, 88, 101, 129], 'brute': [30], 'force': [31], 'approach': [32, 52], 'necessitates': [33], 'design': [35, 43], 'of': [36, 87, 103, 114, 131, 146], 'appropriate': [37], 'indexing': [38, 134], 'or': [39], 'blocking': [40, 51, 136], 'techniques.': [41], 'We': [42, 108], 'evaluate': [45], 'efficient': [47, 133], 'highly': [49], 'scalable': [50], 'based': [53], 'on': [54], 'suffix': [55, 58, 90], 'arrays.': [56], 'Our': [57], 'grouping': [59, 94], 'technique': [60], 'exploits': [61], 'ordering': [63], 'used': [64], 'by': [65], 'index': [67], 'to': [68], 'merge': [69], 'similar': [70, 95], 'blocks': [71], 'at': [72], 'marginal': [73], 'extra': [74], 'cost,': [75], 'resulting': [76], 'much': [79], 'higher': [80], 'accuracy': [81], 'while': [82], 'retaining': [83], 'high': [85], 'base': [89], 'array': [91], 'method.': [92], 'Efficiently': [93], 'suffixes': [96], 'carried': [98], 'out': [99, 110], 'with': [100], 'use': [102], 'sliding': [105], 'window': [106], 'technique.': [107], 'carry': [109], 'in-depth': [112], 'analysis': [113], 'our': [115], 'method': [116], 'show': [118], 'results': [119], 'from': [120], 'experiments': [121], 'using': [122, 132], 'real': [123, 138], 'synthetic': [125], 'data,': [126], 'which': [127], 'highlights': [128], 'importance': [130], 'world': [139], 'applications': [140], 'where': [141], 'sets': [143], 'contain': [144], 'millions': [145], 'records.': [147]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2088008685', 'counts_by_year': [{'year': 2022, 'cited_by_count': 1}, {'year': 2021, 'cited_by_count': 2}, {'year': 2020, 'cited_by_count': 4}, {'year': 2019, 'cited_by_count': 6}, {'year': 2018, 'cited_by_count': 1}, {'year': 2017, 'cited_by_count': 1}, {'year': 2016, 'cited_by_count': 5}, {'year': 2015, 'cited_by_count': 3}, {'year': 2014, 'cited_by_count': 3}, {'year': 2013, 'cited_by_count': 4}, {'year': 2012, 'cited_by_count': 4}], 'updated_date': '2024-12-15T20:04:31.133987', 'created_date': '2016-06-24'}