{"id":"https://openalex.org/W2150749667","doi":"https://doi.org/10.3115/1220175.1220245","title":"Exploiting comparable corpora and bilingual dictionaries for cross-language text categorization","display_name":"Exploiting comparable corpora and bilingual dictionaries for cross-language text categorization","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2150749667","doi":"https://doi.org/10.3115/1220175.1220245","mag":"2150749667"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220245","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220245","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220245","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220245","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087419620","display_name":"Alfio Gliozzo","orcid":"https://orcid.org/0000-0002-8044-2911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfio Gliozzo","raw_affiliation_strings":["ITC-Irst, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-Irst, Trento, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006685038","display_name":"Carlo Strapparava","orcid":"https://orcid.org/0000-0002-9365-0242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlo Strapparava","raw_affiliation_strings":["ITC-Irst, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-Irst, Trento, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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":0.9987999796867371,"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/categorization","display_name":"Categorization","score":0.8759450912475586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8555132746696472},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7897570133209229},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7173254489898682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6803375482559204},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5815154314041138},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5221472382545471}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8759450912475586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555132746696472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7897570133209229},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7173254489898682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6803375482559204},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5815154314041138},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5221472382545471},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1220175.1220245","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220245","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220245","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.7788","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.7788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P06/P06-1070.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220245","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220245","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1220175.1220245","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326086","display_name":"Provincia Autonoma di Trento","ror":"https://ror.org/017e99q89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150749667.pdf","grobid_xml":"https://content.openalex.org/works/W2150749667.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W98435347","https://openalex.org/W1489959797","https://openalex.org/W1540550673","https://openalex.org/W1604792744","https://openalex.org/W1974406477","https://openalex.org/W2068761270","https://openalex.org/W2099031744","https://openalex.org/W2111329418","https://openalex.org/W2121415745","https://openalex.org/W2129765547","https://openalex.org/W2133837072","https://openalex.org/W2140500610","https://openalex.org/W2147152072","https://openalex.org/W2166843810","https://openalex.org/W2301772290","https://openalex.org/W3160981298","https://openalex.org/W3161401723"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2390698788","https://openalex.org/W2133651098","https://openalex.org/W2078570174","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"Cross-language":[0],"Text":[1,95],"Categorization":[2,96],"is":[3,22,51],"the":[4,20,41,56,70,81,92,105,108],"task":[5],"of":[6,43,73,83,107,114],"assigning":[7],"semantic":[8],"classes":[9],"to":[10,40,53,112],"documents":[11,26],"written":[12],"in":[13,27],"a":[14,28,87],"target":[15],"language":[16,30],"(e.g.":[17,31],"English)":[18],"while":[19],"system":[21],"trained":[23],"using":[24],"labeled":[25],"source":[29],"Italian).In":[32],"this":[33],"work":[34],"we":[35,47],"present":[36],"many":[37],"solutions":[38],"according":[39],"availability":[42],"bilingual":[44,101],"resources,":[45],"and":[46],"show":[48,80],"that":[49,113],"it":[50],"possible":[52],"deal":[54],"with":[55],"problem":[57],"even":[58],"when":[59,100],"no":[60],"such":[61],"resources":[62],"are":[63,103],"accessible.":[64],"The":[65],"core":[66],"technique":[67],"relies":[68],"on":[69],"automatic":[71],"acquisition":[72],"Multilingual":[74],"Domain":[75],"Models":[76],"from":[77],"comparable":[78],"corpora.Experiments":[79],"effectiveness":[82],"our":[84],"approach,":[85],"providing":[86],"low":[88],"cost":[89],"solution":[90],"for":[91],"Cross":[93],"Language":[94],"task.":[97],"In":[98],"particular,":[99],"dictionaries":[102],"available":[104],"performance":[106],"categorization":[109],"gets":[110],"close":[111],"monolingual":[115],"text":[116],"categorization.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
