{"id":"https://openalex.org/W2741195357","doi":"https://doi.org/10.1145/3077136.3080749","title":"A Large-Scale Query Spelling Correction Corpus","display_name":"A Large-Scale Query Spelling Correction Corpus","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741195357","doi":"https://doi.org/10.1145/3077136.3080749","mag":"2741195357"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3080749","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014322854","display_name":"Matthias Hagen","orcid":"https://orcid.org/0000-0002-9733-2890"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Hagen","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020942073","display_name":"Marcel Gohsen","orcid":"https://orcid.org/0000-0002-1020-6745"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcel Gohsen","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063831640","display_name":"Anja Rathgeber","orcid":null},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anja Rathgeber","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benno Stein","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014322854"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":1.3652,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85877383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1261","last_page":"1264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9965000152587891,"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/spelling","display_name":"Spelling","score":0.975162923336029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8685327768325806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6454614996910095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5378363132476807},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49550068378448486},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4804270267486572},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4125932455062866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3242531716823578},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12520268559455872}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.975162923336029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8685327768325806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6454614996910095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5378363132476807},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49550068378448486},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4804270267486572},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4125932455062866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3242531716823578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12520268559455872},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3077136.3080749","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W41966708","https://openalex.org/W66690650","https://openalex.org/W71986290","https://openalex.org/W186413630","https://openalex.org/W1982858363","https://openalex.org/W1984316072","https://openalex.org/W2087198174","https://openalex.org/W2104925369","https://openalex.org/W2125022429","https://openalex.org/W2129271949","https://openalex.org/W2144318140","https://openalex.org/W2160039544","https://openalex.org/W2168322422","https://openalex.org/W2250316417","https://openalex.org/W2522306626","https://openalex.org/W2585868976","https://openalex.org/W4205355130"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2021532426","https://openalex.org/W2081317458"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"new":[3,35,55],"large-scale":[4,56],"collection":[5],"of":[6,16,40,63,66,101],"54,772":[7],"queries":[8,18],"with":[9],"manually":[10],"annotated":[11],"spelling":[12,20,48,82,98],"corrections.":[13],"For":[14],"9,170":[15],"the":[17,26,54,64,67,76,97],"(16.74%),":[19],"variants":[21],"that":[22],"are":[23,29],"different":[24,77],"to":[25,52,81],"original":[27],"query":[28,47],"proposed.":[30],"With":[31],"its":[32],"size,":[33],"our":[34],"corpus":[36],"is":[37],"an":[38,61],"order":[39],"magnitude":[41],"larger":[42],"than":[43],"other":[44],"publicly":[45,78],"available":[46,79],"corpora.":[49],"In":[50],"addition":[51],"releasing":[53],"corpus,":[57],"we":[58,91],"also":[59,92],"provide":[60],"implementation":[62],"winner":[65],"Microsoft":[68],"Speller":[69],"Challenge":[70],"from~2011":[71],"and":[72,87],"compare":[73],"it":[74],"on":[75,96],"corpora":[80],"corrections":[83],"mined":[84],"from":[85],"Google":[86],"Bing.":[88],"This":[89],"way,":[90],"shed":[93],"some":[94],"light":[95],"correction":[99],"performance":[100],"state-of-the-art":[102],"commercial":[103],"search":[104],"systems.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}