{"id":"https://openalex.org/W2593438968","doi":"https://doi.org/10.1142/s0218213017600028","title":"XML Clustering by Structure-Constrained Phrases: A Fully-Automatic Approach Using Contextualized N-Grams","display_name":"XML Clustering by Structure-Constrained Phrases: A Fully-Automatic Approach Using Contextualized N-Grams","publication_year":2017,"publication_date":"2017-02-01","ids":{"openalex":"https://openalex.org/W2593438968","doi":"https://doi.org/10.1142/s0218213017600028","mag":"2593438968"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213017600028","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213017600028","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-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/A5076708603","display_name":"Gianni Costa","orcid":"https://orcid.org/0000-0003-2267-9280"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianni Costa","raw_affiliation_strings":["Istituto di Calcolo e Reti ad Alte Prestazioni \u2014 National Research Council I87036 Rende (CS), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Calcolo e Reti ad Alte Prestazioni \u2014 National Research Council I87036 Rende (CS), Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078466922","display_name":"Riccardo Ortale","orcid":"https://orcid.org/0000-0002-1763-9121"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Riccardo Ortale","raw_affiliation_strings":["Istituto di Calcolo e Reti ad Alte Prestazioni \u2014 National Research Council I87036 Rende (CS), Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Calcolo e Reti ad Alte Prestazioni \u2014 National Research Council I87036 Rende (CS), Italy","institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078466922"],"corresponding_institution_ids":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"],"apc_list":null,"apc_paid":null,"fwci":0.548,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.62647454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"01","first_page":"1760002","last_page":"1760002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8763645887374878},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.8243459463119507},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.7498865127563477},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.69211345911026},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5796346664428711},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.5779415965080261},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5580626130104065},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.502460241317749},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.5014259815216064},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48890939354896545},{"id":"https://openalex.org/keywords/xml-encryption","display_name":"XML Encryption","score":0.44101908802986145},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.4283466637134552},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.4282882809638977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3962230682373047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3385314345359802},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12835785746574402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8763645887374878},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.8243459463119507},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.7498865127563477},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.69211345911026},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5796346664428711},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.5779415965080261},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5580626130104065},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.502460241317749},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.5014259815216064},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48890939354896545},{"id":"https://openalex.org/C173242113","wikidata":"https://www.wikidata.org/wiki/Q607488","display_name":"XML Encryption","level":4,"score":0.44101908802986145},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.4283466637134552},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4282882809638977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3962230682373047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3385314345359802},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12835785746574402}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213017600028","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213017600028","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W152176684","https://openalex.org/W204086241","https://openalex.org/W1535627680","https://openalex.org/W1572083646","https://openalex.org/W1575391024","https://openalex.org/W1925007459","https://openalex.org/W1975486252","https://openalex.org/W1998995129","https://openalex.org/W2004539934","https://openalex.org/W2015515391","https://openalex.org/W2020836195","https://openalex.org/W2025288138","https://openalex.org/W2042961901","https://openalex.org/W2047260621","https://openalex.org/W2066680326","https://openalex.org/W2071106922","https://openalex.org/W2086834050","https://openalex.org/W2092559720","https://openalex.org/W2098162425","https://openalex.org/W2103069411","https://openalex.org/W2116020486","https://openalex.org/W2128381480","https://openalex.org/W2139081439","https://openalex.org/W2148744937","https://openalex.org/W2160873337","https://openalex.org/W2165612380","https://openalex.org/W2246695077","https://openalex.org/W2295281749","https://openalex.org/W2335920051"],"related_works":["https://openalex.org/W2536894089","https://openalex.org/W2357844625","https://openalex.org/W2047342127","https://openalex.org/W2038564770","https://openalex.org/W2385975321","https://openalex.org/W1509918510","https://openalex.org/W801203902","https://openalex.org/W2106024890","https://openalex.org/W2124122806","https://openalex.org/W2997449093"],"abstract_inverted_index":{"Using":[0],"the":[1,6,24,39,45,51,69,72,82,101,104,114,130,163,197,205,220],"bag-of-word":[2],"model":[3,86],"to":[4,81,93,124,181],"represent":[5],"textual":[7,29,74,127,174],"data":[8],"of":[9,26,47,71,76,100,103,120,126,132,143,162,172,200,207,219],"XML":[10,17,33,56,77,115,121,144,164,183,194,208],"documents":[11,34,116,165],"may":[12,35],"not":[13],"be":[14],"beneficial":[15],"in":[16,50,129],"clustering":[18,57,89,209],"by":[19,44,58,79,210],"content":[20],"and":[21,97,169,213],"structure.":[22],"Indeed,":[23],"occurrence":[25,49],"similar":[27],"structure-constrained":[28,59,73,211],"items":[30,75,128],"across":[31],"distinct":[32],"enforce":[36],"relatedness,":[37],"despite":[38],"possibly":[40],"different":[41],"meaning":[42,70],"implied":[43],"order":[46,92],"item":[48],"respective":[52],"contexts.":[53],"We":[54],"propose":[55],"phrases.":[60],"It":[61],"is":[62,148,179,223],"a":[63,109,118,141],"new":[64],"method":[65],"that":[66,112],"better":[67],"captures":[68],"documents,":[78],"resorting":[80],"more":[83],"accurate":[84],"bag-of-phrase":[85],"for":[87,139],"improved":[88],"effectiveness.":[90],"In":[91],"conduct":[94],"an":[95,151],"in-depth":[96],"systematic":[98],"study":[99],"validity":[102],"proposed":[105],"method,":[106],"we":[107],"develop":[108],"parameter-free":[110],"approach,":[111],"projects":[113],"into":[117],"space":[119],"features":[122,184],"corresponding":[123],"sequences":[125,171],"context":[131],"root-to-leaf":[133],"paths.":[134],"Automatic":[135],"feature":[136],"selection":[137],"allows":[138],"choosing":[140],"subset":[142],"features,":[145],"whose":[146],"relevance":[147],"assessed":[149],"through":[150],"innovative":[152],"scoring":[153],"scheme.":[154],"The":[155,217],"devised":[156,221],"approach":[157,222],"can":[158],"operate":[159],"with":[160,185],"representations":[161],"over":[166],"both":[167],"fixed-":[168],"mixed-length":[170],"contextualized":[173],"items.":[175],"A":[176,188],"novel":[177],"criterion":[178],"presented":[180],"combine":[182],"mixed":[186],"lengths.":[187],"comparative":[189],"experimentation":[190],"on":[191],"real-world":[192],"benchmark":[193],"corpora":[195],"reveals":[196],"overcoming":[198],"effectiveness":[199],"our":[201],"approach.":[202],"This":[203],"highlights":[204],"potential":[206],"phrases":[212],"fosters":[214],"further":[215],"efforts.":[216],"scalability":[218],"also":[224],"investigated.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}