{"id":"https://openalex.org/W2911367192","doi":"https://doi.org/10.1007/978-3-319-99004-0_3","title":"Collecting Comparable Corpora","display_name":"Collecting Comparable Corpora","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2911367192","doi":"https://doi.org/10.1007/978-3-319-99004-0_3","mag":"2911367192"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-99004-0_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-99004-0_3","pdf_url":null,"source":{"id":"https://openalex.org/S4210206418","display_name":"Theory and applications of natural language processing","issn_l":"2192-032X","issn":["2192-032X","2192-0338"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Theory and Applications of Natural Language Processing","raw_type":"book-chapter"},"type":"book-chapter","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/A5003699544","display_name":"Monica Lestari Paramita","orcid":"https://orcid.org/0000-0002-9414-1853"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Monica Lestari Paramita","raw_affiliation_strings":["University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065296262","display_name":"Ahmet Aker","orcid":"https://orcid.org/0000-0003-3381-0790"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmet Aker","raw_affiliation_strings":["University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011889540","display_name":"Paul Clough","orcid":"https://orcid.org/0000-0003-1739-175X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Clough","raw_affiliation_strings":["University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040587162","display_name":"Robert Gaizauskas","orcid":"https://orcid.org/0000-0002-3356-5126"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert Gaizauskas","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK","University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041232293","display_name":"Nikos Glaros","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikos Glaros","raw_affiliation_strings":["Institute for Language and Speech Processing (ILSP), Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing (ILSP), Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045614251","display_name":"Nikos Mastropavlos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikos Mastropavlos","raw_affiliation_strings":["Institute for Language and Speech Processing (ILSP), Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing (ILSP), Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084668427","display_name":"Olga Yannoutsou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Olga Yannoutsou","raw_affiliation_strings":["Institute for Language and Speech Processing (ILSP), Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing (ILSP), Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058386804","display_name":"Radu Ion","orcid":"https://orcid.org/0000-0002-3421-3173"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Radu Ion","raw_affiliation_strings":["Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036691231","display_name":"Dan \u015etef\u0103nescu","orcid":null},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan \u0218tef\u0103nescu","raw_affiliation_strings":["Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090205535","display_name":"Alexandru Ceau\u015fu","orcid":null},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Alexandru Ceau\u015fu","raw_affiliation_strings":["Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062940611","display_name":"Dan Tufi\u015f","orcid":"https://orcid.org/0000-0002-8280-9852"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Tufi\u0219","raw_affiliation_strings":["Institute for Artificial Intelligence, Romanian Academy, Bucharest, Romania","Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]},{"raw_affiliation_string":"Research Institute for Artificial Intelligence, Romanian Academy Center for Artificial Intelligence (RACAI), Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038724800","display_name":"Judita Preiss","orcid":"https://orcid.org/0000-0002-2158-5832"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Judita Preiss","raw_affiliation_strings":["University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2804,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51064431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"87"},"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":0.9988999962806702,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.8176367282867432},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.572697103023529},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5497629046440125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176367282867432},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.572697103023529},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5497629046440125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-99004-0_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-99004-0_3","pdf_url":null,"source":{"id":"https://openalex.org/S4210206418","display_name":"Theory and applications of natural language processing","issn_l":"2192-032X","issn":["2192-032X","2192-0338"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Theory and Applications of Natural Language Processing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W14574270","https://openalex.org/W84079877","https://openalex.org/W85946539","https://openalex.org/W97009826","https://openalex.org/W110443600","https://openalex.org/W150793826","https://openalex.org/W185074583","https://openalex.org/W191422183","https://openalex.org/W207422111","https://openalex.org/W753536477","https://openalex.org/W756467256","https://openalex.org/W1481125541","https://openalex.org/W1504406162","https://openalex.org/W1533946607","https://openalex.org/W1543107604","https://openalex.org/W1562514231","https://openalex.org/W1636405317","https://openalex.org/W1880262756","https://openalex.org/W1916559533","https://openalex.org/W1982474572","https://openalex.org/W2001832505","https://openalex.org/W2017726337","https://openalex.org/W2029341294","https://openalex.org/W2037796960","https://openalex.org/W2044743392","https://openalex.org/W2061118075","https://openalex.org/W2066636486","https://openalex.org/W2083901795","https://openalex.org/W2086039194","https://openalex.org/W2090146924","https://openalex.org/W2101096097","https://openalex.org/W2102749417","https://openalex.org/W2105673178","https://openalex.org/W2107130271","https://openalex.org/W2107695330","https://openalex.org/W2109803107","https://openalex.org/W2116713744","https://openalex.org/W2120101509","https://openalex.org/W2124718840","https://openalex.org/W2132019450","https://openalex.org/W2136477195","https://openalex.org/W2138575863","https://openalex.org/W2140903445","https://openalex.org/W2141825421","https://openalex.org/W2145080939","https://openalex.org/W2145685230","https://openalex.org/W2153488166","https://openalex.org/W2167170026","https://openalex.org/W2171836785","https://openalex.org/W2250924616","https://openalex.org/W2405617275","https://openalex.org/W2551380700","https://openalex.org/W2588710172","https://openalex.org/W2989939775","https://openalex.org/W3208719332","https://openalex.org/W3211848854","https://openalex.org/W6603373351","https://openalex.org/W6607528661","https://openalex.org/W6622431068","https://openalex.org/W6632118081","https://openalex.org/W6639619044","https://openalex.org/W6676298475","https://openalex.org/W6691611999"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}