{"id":"https://openalex.org/W2217454595","doi":"https://doi.org/10.1109/bigdata.2015.7363801","title":"SyntacticDiff: Operator-based transformation for comparative text mining","display_name":"SyntacticDiff: Operator-based transformation for comparative text mining","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2217454595","doi":"https://doi.org/10.1109/bigdata.2015.7363801","mag":"2217454595"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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/A5077883199","display_name":"Sean Massung","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sean Massung","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028518494","display_name":"ChengXiang Zhai","orcid":"https://orcid.org/0000-0002-6434-3702"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ChengXiang Zhai","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077883199"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77073499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"571","last_page":"580"},"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":0.9997000098228455,"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/T10260","display_name":"Software Engineering Research","score":0.9965999722480774,"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":0.8708105087280273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.718895673751831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6549322009086609},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5870604515075684},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5748896598815918},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.523554265499115},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49862241744995117},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4833804965019226},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.481231689453125},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.45439910888671875},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45344147086143494},{"id":"https://openalex.org/keywords/text-simplification","display_name":"Text simplification","score":0.4433017373085022},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4427659213542938},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.43001994490623474},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4165472388267517},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35855528712272644},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14072257280349731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8708105087280273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.718895673751831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6549322009086609},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5870604515075684},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5748896598815918},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.523554265499115},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49862241744995117},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4833804965019226},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.481231689453125},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.45439910888671875},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45344147086143494},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.4433017373085022},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4427659213542938},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.43001994490623474},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4165472388267517},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35855528712272644},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14072257280349731},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W224064951","https://openalex.org/W627347790","https://openalex.org/W1641025018","https://openalex.org/W1880262756","https://openalex.org/W2023450550","https://openalex.org/W2032175749","https://openalex.org/W2093931624","https://openalex.org/W2097726431","https://openalex.org/W2098297786","https://openalex.org/W2112247328","https://openalex.org/W2126385423","https://openalex.org/W2129468719","https://openalex.org/W2130670943","https://openalex.org/W2170527467","https://openalex.org/W2181262297","https://openalex.org/W2251109422","https://openalex.org/W2917881729","https://openalex.org/W4205184193","https://openalex.org/W4231510805","https://openalex.org/W6608848962","https://openalex.org/W6619888917","https://openalex.org/W6639619044","https://openalex.org/W6685309151","https://openalex.org/W6691572788"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W3151736118","https://openalex.org/W2077104824","https://openalex.org/W2168778844","https://openalex.org/W2293063786","https://openalex.org/W2911292476","https://openalex.org/W2116246834"],"abstract_inverted_index":{"We":[0],"describe":[1],"SyntacticDiff,":[2],"a":[3,16,37,104,118],"novel,":[4],"general,":[5],"and":[6,62,64,78,97,112,122,135],"efficient":[7],"edit-based":[8],"method":[9,121],"for":[10,125],"transforming":[11],"sequences":[12],"of":[13,40],"words":[14],"given":[15],"reference":[17,105],"text":[18,34,41,86,106,127],"collection.":[19],"These":[20],"transformations":[21],"can":[22,27,79],"be":[23,28,81],"used":[24],"directly":[25],"or":[26],"employed":[29],"as":[30],"features":[31],"to":[32,50,84,99],"represent":[33],"data":[35,87],"in":[36,71,88],"wide":[38],"variety":[39],"mining":[42,128],"applications.":[43],"As":[44],"case":[45],"studies,":[46],"we":[47],"apply":[48],"SyntacticDiff":[49,74],"three":[51],"quite":[52],"different":[53],"tasks,":[54],"including":[55],"grammatical":[56],"error":[57],"correction,":[58],"student":[59],"essay":[60],"clustering":[61],"analysis,":[63],"native":[65],"language":[66],"identification,":[67],"showing":[68],"its":[69],"benefit":[70],"each":[72],"case.":[73],"is":[75,93],"completely":[76],"general":[77],"thus":[80],"potentially":[82],"applied":[83],"any":[85,89],"natural":[90],"language.":[91],"It":[92],"highly":[94],"efficient,":[95],"customizable,":[96],"able":[98],"capture":[100],"syntactic":[101],"differences":[102],"from":[103],"collection":[107],"at":[108],"the":[109],"sentence,":[110],"document,":[111],"subcollection":[113],"levels.":[114],"This":[115],"enables":[116],"both":[117],"rich":[119],"translation":[120],"feature":[123],"representation":[124],"many":[126],"tasks":[129],"that":[130],"deal":[131],"with":[132],"word":[133],"usage":[134],"syntax":[136],"beyond":[137],"bag-of-words.":[138]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}