{"id":"https://openalex.org/W3083478299","doi":"https://doi.org/10.1145/3411170.3411258","title":"Building an Italian-Chinese Parallel Corpus for Machine Translation from the Web","display_name":"Building an Italian-Chinese Parallel Corpus for Machine Translation from the Web","publication_year":2020,"publication_date":"2020-09-04","ids":{"openalex":"https://openalex.org/W3083478299","doi":"https://doi.org/10.1145/3411170.3411258","mag":"3083478299"},"language":"en","primary_location":{"id":"doi:10.1145/3411170.3411258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411170.3411258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th EAI International Conference on Smart Objects and Technologies for Social Good","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/A5092503600","display_name":"Rita Tse","orcid":"https://orcid.org/0009-0004-7901-8680"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Rita Tse","raw_affiliation_strings":["School of Applied Sciences - Macao Polytechnic Institute, Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence, Ministry of Education - Macao (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Applied Sciences - Macao Polytechnic Institute, Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence, Ministry of Education - Macao (China)","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012162579","display_name":"Silvia Mirri","orcid":"https://orcid.org/0000-0002-5385-4734"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvia Mirri","raw_affiliation_strings":["Department of Computer Science and Engineering - University of Bologna - Bologna (Italy)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering - University of Bologna - Bologna (Italy)","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046907628","display_name":"Su-Kit Tang","orcid":"https://orcid.org/0000-0001-8104-7887"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Su-Kit Tang","raw_affiliation_strings":["School of Applied Sciences - Macao Polytechnic Institute, Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence, Ministry of Education - Macao (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Applied Sciences - Macao Polytechnic Institute, Engineering Research Centre of Applied Technology on Machine Translation and Artificial Intelligence, Ministry of Education - Macao (China)","institution_ids":["https://openalex.org/I49835588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048063581","display_name":"Giovanni Pau","orcid":"https://orcid.org/0000-0003-2216-7170"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Pau","raw_affiliation_strings":["Department of Computer Science and Engineering - University of Bologna - Bologna (Italy), Computer Science Department - UCLA - Los Angeles, CA (USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering - University of Bologna - Bologna (Italy), Computer Science Department - UCLA - Los Angeles, CA (USA)","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021701472","display_name":"Paola Salomoni","orcid":"https://orcid.org/0000-0002-1717-1901"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paola Salomoni","raw_affiliation_strings":["Department of Computer Science and Engineering - University of Bologna - Bologna (Italy)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering - University of Bologna - Bologna (Italy)","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092503600"],"corresponding_institution_ids":["https://openalex.org/I49835588"],"apc_list":null,"apc_paid":null,"fwci":1.6319,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87448014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"268"},"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":0.9968000054359436,"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/T13629","display_name":"Text Readability and Simplification","score":0.9951000213623047,"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/machine-translation","display_name":"Machine translation","score":0.8320725560188293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8248288631439209},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7156537771224976},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6836752891540527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6652240753173828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6486623883247375},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.6284354329109192},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4968767464160919},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4380411207675934},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.4110042154788971},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17750948667526245}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8320725560188293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248288631439209},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7156537771224976},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6836752891540527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6652240753173828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6486623883247375},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6284354329109192},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4968767464160919},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4380411207675934},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.4110042154788971},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17750948667526245},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3411170.3411258","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411170.3411258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th EAI International Conference on Smart Objects and Technologies for Social Good","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/773799","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/773799","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W423733794","https://openalex.org/W1489181569","https://openalex.org/W1563858398","https://openalex.org/W1916559533","https://openalex.org/W1968554861","https://openalex.org/W2083160100","https://openalex.org/W2117652747","https://openalex.org/W2126807068","https://openalex.org/W2261662069","https://openalex.org/W2531621976","https://openalex.org/W2566516706","https://openalex.org/W2576968057","https://openalex.org/W2749116339","https://openalex.org/W2759083144","https://openalex.org/W2802168367","https://openalex.org/W2883349992","https://openalex.org/W2915403486","https://openalex.org/W2965598341","https://openalex.org/W2990714382","https://openalex.org/W3008568651","https://openalex.org/W4205918858","https://openalex.org/W4240795705"],"related_works":["https://openalex.org/W193726211","https://openalex.org/W4287212313","https://openalex.org/W2986030184","https://openalex.org/W2904817833","https://openalex.org/W2104907655","https://openalex.org/W3152052241","https://openalex.org/W3155572818","https://openalex.org/W3023559046","https://openalex.org/W2798493043","https://openalex.org/W2250639243"],"abstract_inverted_index":{"In":[0],"an":[1,77,88,100],"increasingly":[2],"globalized":[3],"world,":[4],"being":[5],"able":[6],"to":[7,85,109,133,143],"understand":[8],"texts":[9,112],"in":[10,16,43],"different":[11,17,35,39],"languages":[12],"(even":[13],"more":[14,169],"so":[15],"alphabets":[18],"and":[19,32,70,83,150,175],"charsets)":[20],"has":[21],"become":[22,47],"a":[23,63,68,118,183],"necessity.":[24],"This":[25,74],"can":[26],"be":[27],"strategic":[28],"even":[29],"while":[30],"moving":[31],"travelling":[33],"across":[34],"countries,":[36],"characterized":[37],"by":[38],"languages.":[40],"With":[41],"this":[42],"mind,":[44],"bilingual":[45],"corpora":[46],"critical":[48],"resources":[49],"since":[50],"they":[51],"are":[52,178],"the":[53,93,114,126,129,134,145,157,179],"basis":[54,180],"of":[55,95,128,147,156,168],"every":[56],"state-of-the-art":[57],"automatic":[58],"translation":[59],"system;":[60],"moreover,":[61],"building":[62,182],"parallel":[64,90,111],"corpus":[65,163],"is":[66,108],"usually":[67],"complex":[69],"very":[71],"expensive":[72],"operation.":[73],"paper":[75],"describes":[76],"innovative":[78],"approach":[79,149],"we":[80,116,164],"have":[81,165],"defined":[82,117],"adopted":[84],"automatically":[86],"build":[87],"Italian-Chinese":[89,101],"corpus,":[91],"with":[92],"aim":[94],"using":[96],"it":[97],"for":[98,181],"training":[99],"Neural":[102],"Machine":[103,184],"Translation.":[104],"Our":[105],"main":[106],"idea":[107],"scrape":[110],"from":[113,125],"Web:":[115],"general":[119],"pipeline,":[120],"describing":[121],"each":[122],"specific":[123],"step":[124],"selection":[127],"appropriate":[130],"data":[131],"sources":[132],"sentence":[135,172],"alignment":[136],"method.":[137],"A":[138],"final":[139],"evaluation":[140],"was":[141],"conducted":[142],"evaluate":[144],"goodness":[146],"our":[148],"its":[151],"results":[152],"show":[153],"that":[154],"90%":[155],"sentences":[158],"were":[159],"correctly":[160],"aligned.":[161],"The":[162],"obtained":[166],"consists":[167],"than":[170],"6,000":[171],"pairs":[173],"(Italian":[174],"Chinese),":[176],"which":[177],"Translation":[185],"system.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}
