{"id":"https://openalex.org/W3213486941","doi":"https://doi.org/10.5281/zenodo.3766985","title":"Webis Gmane Email Corpus 2019","display_name":"Webis Gmane Email Corpus 2019","publication_year":2020,"publication_date":"2020-06-03","ids":{"openalex":"https://openalex.org/W3213486941","doi":"https://doi.org/10.5281/zenodo.3766985","mag":"3213486941"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:3766985","is_oa":true,"landing_page_url":"https://zenodo.org/record/3766985","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3766985","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079524270","display_name":"Janek Bevendorff","orcid":"https://orcid.org/0000-0002-3797-0559"},"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":"Bevendorff, Janek","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024644016","display_name":"Khalid Al\u2010Khatib","orcid":"https://orcid.org/0009-0006-7255-5349"},"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":"Al-Khatib, Khalid","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","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/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Potthast, Martin","raw_affiliation_strings":["Leipzig University"],"affiliations":[{"raw_affiliation_string":"Leipzig University","institution_ids":["https://openalex.org/I926574661"]}]},{"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":"Stein, Benno","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079524270"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9531999826431274,"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":0.9531999826431274,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4876915216445923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4601138234138489},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3608497083187103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4876915216445923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4601138234138489},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3608497083187103}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:3766985","is_oa":true,"landing_page_url":"https://zenodo.org/record/3766985","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3766985","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3766985","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3766985","is_oa":true,"landing_page_url":"https://zenodo.org/record/3766985","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"The":[0,35,46,98,141],"Webis":[1],"Gmane":[2,130],"Email":[3],"Corpus":[4],"2019":[5,23],"is":[6,101],"a":[7,41,50,107,118],"dataset":[8,36,47,196],"of":[9,31,52,67,123,235],"more":[10,27,192],"than":[11,28],"153":[12],"million":[13],"parsed":[14,115],"and":[15,21,120,133,197,221,224,227,259],"segmented":[16],"emails":[17],"crawled":[18],"between":[19],"February":[20],"May":[22],"from":[24,166],"gmane.io":[25],"covering":[26],"20":[29],"years":[30],"public":[32],"mailing":[33],"lists.":[34],"has":[37],"been":[38],"published":[39],"as":[40,49,138],"resource":[42,208],"at":[43,201],"ACL":[44],"2020.":[45],"comes":[48],"set":[51,122],"Gzip-compressed":[53],"files":[54,143],"containing":[55],"line-based":[56],"JSON":[57],"in":[58,209],"the":[59,102,110,113,125,128,134,195,198,236],"Elasticsearch":[60,103],"bulk":[61],"format.":[62],"Each":[63],"data":[64],"record":[65],"consists":[66],"two":[68],"lines:":[69],"<pre><code":[70],"class=\"language-json\">{\"index\":":[71],"{\"_id\":":[72],"\"&lt;urn:uuid:c1d95e4b-0f43-46c7-a99e-c575d1d8e1ce&gt;\"}}":[73],"{\"headers\":":[74],"{\"header":[75],"name\":":[76],"\"header":[77],"value\",":[78],"...},":[79],"\"text_plain\":":[80],"\"plaintext":[81],"body\",":[82],"\"lang\":":[83],"\"en\",":[84],"\"segments\":":[85],"[{\"end\":":[86],"99,":[87],"\"label\":":[88],"\"paragraph\",":[89],"\"begin\":":[90],"0},":[91],"...],":[92],"\"group\":":[93],"\"gmane":[94],"group":[95,131],"name\"}":[96],"</code></pre>":[97,272],"first":[99],"line":[100],"index":[104],"action":[105],"with":[106,117],"document":[108],"UUID,":[109],"second":[111],"one":[112],"actual":[114],"email":[116,158],"(reduced":[119],"anonymized)":[121],"headers,":[124],"detected":[126],"language,":[127],"original":[129],"name":[132],"predicted":[135],"content":[136],"segments":[137],"character":[139],"spans.":[140],"Gzip":[142],"are":[144,205],"splittable":[145],"every":[146],"1,000":[147],"records":[148],"(line":[149],"pairs)":[150],"for":[151,238,249,265],"parallel":[152],"processing":[153],"in,":[154],"e.g.,":[155],"Hadoop.":[156],"Available":[157,172],"headers":[159],"are:":[160,175],"message_id":[161],"date":[162],"(yyyy-MM-dd":[163],"HH:mm:ssZZ)":[164],"subject":[165],"to":[167],"cc":[168],"in_reply_to":[169],"references":[170],"list_id":[171],"segment":[173],"classes":[174],"paragraph":[176],"closing":[177],"inline_headers":[178],"log_data":[179],"mua_signature":[180],"patch":[181],"personal_signature":[182],"quotation":[183],"quotation_marker":[184],"raw_code":[185],"salutation":[186],"section_heading":[187],"tabular":[188],"technical":[189],"visual_separator":[190],"Find":[191],"information":[193],"about":[194],"segmentation":[199],"model":[200],"webis.de.":[202],"If":[203],"you":[204],"using":[206],"this":[207],"your":[210],"work,":[211],"please":[212],"cite":[213],"it":[214],"as:":[215],"<pre><code>@InProceedings{stein:2020o,":[216],"author":[217],"=":[218,231,244,247,253,257,269],"{Janek":[219],"Bevendorff":[220],"Khalid":[222],"Al-Khatib":[223],"Martin":[225],"Potthast":[226],"Benno":[228],"Stein},":[229],"booktitle":[230],"{58th":[232],"Annual":[233],"Meeting":[234],"Association":[237],"Computational":[239,250],"Linguistics":[240],"(ACL":[241],"2020)},":[242],"month":[243],"jul,":[245],"publisher":[246],"{Association":[248],"Linguistics},":[251],"site":[252],"{Seattle,":[254],"USA},":[255],"title":[256],"{{Crawling":[258],"Preprocessing":[260],"Mailing":[261],"Lists":[262],"At":[263],"Scale":[264],"Dialog":[266],"Analysis}},":[267],"year":[268],"2020":[270],"}":[271]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}