{"id":"https://openalex.org/W2538545555","doi":"https://doi.org/10.1109/icsda.2014.7051433","title":"Building a free, general-domain paraphrase database for Japanese","display_name":"Building a free, general-domain paraphrase database for Japanese","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2538545555","doi":"https://doi.org/10.1109/icsda.2014.7051433","mag":"2538545555"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2014.7051433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051433","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","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/A5108393420","display_name":"Masahiro Mizukami","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Mizukami","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma-shi, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108393420"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":2.5371,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91682441,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9876999855041504,"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/paraphrase","display_name":"Paraphrase","score":0.9443627595901489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.83259516954422},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7376095056533813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6898720860481262},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.587472140789032},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5512344837188721},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5355033874511719},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5037118792533875},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.49265533685684204},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.488603413105011},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.44224080443382263},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.43537843227386475},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2795775532722473},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.22818085551261902}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9443627595901489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83259516954422},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7376095056533813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6898720860481262},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.587472140789032},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5512344837188721},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5355033874511719},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5037118792533875},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.49265533685684204},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.488603413105011},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.44224080443382263},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.43537843227386475},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2795775532722473},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.22818085551261902},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":2,"locations":[{"id":"doi:10.1109/icsda.2014.7051433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051433","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.726.5272","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.726.5272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isw3.naist.jp/%7Emasahiro-mi/paper/ma14cocosda.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W44751112","https://openalex.org/W191017350","https://openalex.org/W1596437659","https://openalex.org/W1975879668","https://openalex.org/W2126664467","https://openalex.org/W2127863960","https://openalex.org/W2133280805","https://openalex.org/W2136544838","https://openalex.org/W2143927888","https://openalex.org/W2145685230","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2164777277","https://openalex.org/W2170205828","https://openalex.org/W2170716095","https://openalex.org/W2251044566","https://openalex.org/W2988037059","https://openalex.org/W6601783721","https://openalex.org/W6607718353","https://openalex.org/W6678628757","https://openalex.org/W6679101406","https://openalex.org/W6680267823","https://openalex.org/W6682383452","https://openalex.org/W6685203456","https://openalex.org/W6691444529","https://openalex.org/W6770189741"],"related_works":["https://openalex.org/W3142119062","https://openalex.org/W131522978","https://openalex.org/W159209093","https://openalex.org/W589103562","https://openalex.org/W1991220724","https://openalex.org/W2251234095","https://openalex.org/W2250768577","https://openalex.org/W2160717663","https://openalex.org/W2117607680","https://openalex.org/W1619002"],"abstract_inverted_index":{"Previous":[0],"works":[1],"have":[2,30],"used":[3,105],"parallel":[4],"corpora":[5],"and":[6,16,48,65,73,78,89,124],"alignment":[7],"techniques":[8],"from":[9,62],"phrase-based":[10],"statistical":[11],"machine":[12],"translation":[13],"to":[14,85,95],"extract":[15,90],"generate":[17],"paraphrases.":[18],"In":[19,69],"Japanese,":[20,47],"paraphrases":[21,91,110],"for":[22,130],"a":[23,43,126],"number":[24],"of":[25,38,60,128],"paraphrase":[26,54],"categories":[27],"or":[28,117],"domains":[29],"been":[31],"extracted":[32,97],"by":[33],"this":[34,87],"method.":[35],"However,":[36],"most":[37],"these":[39],"resources":[40,55],"focus":[41],"on":[42],"particular":[44],"phenomenon":[45],"in":[46,76,93,106,113],"there":[49],"are":[50,66],"still":[51],"no":[52],"Japanese":[53,72,109],"that":[56],"cover":[57],"all":[58],"varieties":[59],"phrases":[61],"several":[63],"domains,":[64],"freely":[67],"available.":[68],"addition,":[70],"because":[71],"English":[74],"vary":[75],"grammar":[77],"word":[79],"ordering,":[80],"we":[81],"perform":[82],"syntax-based":[83],"preprocessing":[84],"reduce":[86],"mismatch":[88],"similar":[92,100],"quality":[94],"those":[96],"using":[98],"more":[99],"language":[101],"pairs.":[102],"The":[103],"data":[104],"creating":[107],"the":[108,114,120],"is":[111],"either":[112],"public":[115],"domain,":[116],"available":[118],"under":[119],"Creative":[121],"Commons":[122],"license,":[123],"spans":[125],"variety":[127],"genres":[129],"wide":[131],"coverage.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
