{"id":"https://openalex.org/W2111727122","doi":"https://doi.org/10.1145/1516360.1516498","title":"High-performance information extraction with AliBaba","display_name":"High-performance information extraction with AliBaba","publication_year":2009,"publication_date":"2009-03-24","ids":{"openalex":"https://openalex.org/W2111727122","doi":"https://doi.org/10.1145/1516360.1516498","mag":"2111727122"},"language":"en","primary_location":{"id":"doi:10.1145/1516360.1516498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1516360.1516498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","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/A5067194946","display_name":"Peter Palaga","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Peter Palaga","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055236937","display_name":"Ulf Leser","orcid":"https://orcid.org/0000-0003-2166-9582"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Leser","raw_affiliation_strings":["Humboldt-Universit\u00e4t zu Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Humboldt-Universit\u00e4t zu Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034893893","display_name":"J\u00f6rg Hakenberg","orcid":"https://orcid.org/0000-0001-8781-7766"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Hakenberg","raw_affiliation_strings":["Arizona State University, Tempe, Arizona"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067194946"],"corresponding_institution_ids":["https://openalex.org/I39343248"],"apc_list":null,"apc_paid":null,"fwci":1.9684,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.86066352,"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":"1140","last_page":"1143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9958000183105469,"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":0.9878000020980835,"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":0.87024986743927},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.7086634635925293},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6602269411087036},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.641706109046936},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5520230531692505},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5415828824043274},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5371113419532776},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.47885772585868835},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45451590418815613},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36041519045829773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35433730483055115},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18023359775543213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.87024986743927},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7086634635925293},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6602269411087036},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.641706109046936},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5520230531692505},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5415828824043274},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5371113419532776},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.47885772585868835},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45451590418815613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36041519045829773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35433730483055115},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18023359775543213},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1516360.1516498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1516360.1516498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1526618214","https://openalex.org/W1604957788","https://openalex.org/W1965685479","https://openalex.org/W2013723863","https://openalex.org/W2022760666","https://openalex.org/W2063256947","https://openalex.org/W2120736575","https://openalex.org/W2121844933","https://openalex.org/W2156930958","https://openalex.org/W2158714788","https://openalex.org/W2159203162","https://openalex.org/W2161936973","https://openalex.org/W2163980860","https://openalex.org/W2168091548","https://openalex.org/W4234286773","https://openalex.org/W4240689716"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2943461603","https://openalex.org/W3210429500","https://openalex.org/W3217252310","https://openalex.org/W4286894112"],"abstract_inverted_index":{"A":[0],"wealth":[1],"of":[2,36,50,91,102,108,148],"information":[3,14,68],"is":[4,18,53,110],"available":[5],"only":[6],"in":[7,172],"web":[8],"pages,":[9],"patents,":[10],"publications":[11],"etc.":[12],"Extracting":[13],"from":[15,70],"such":[16],"sources":[17,49],"challenging,":[19],"both":[20,79],"due":[21],"to":[22,31,40,115],"the":[23,32,63,88,96,146,149],"typically":[24],"complex":[25],"language":[26,118],"processing":[27],"steps":[28],"required":[29],"and":[30,82,85,127],"potentially":[33],"large":[34],"number":[35],"texts":[37],"that":[38,137],"need":[39],"be":[41,170],"analyzed.":[42],"Furthermore,":[43],"integrating":[44],"extracted":[45],"data":[46],"with":[47],"other":[48,75,174],"knowledge":[51],"often":[52],"mandatory":[54],"for":[55,66,100,120,162],"subsequent":[56],"analysis.":[57],"In":[58],"this":[59],"demo,":[60],"we":[61],"present":[62],"AliBaba":[64,77,109,158],"system":[65,150],"scalable":[67],"extraction":[69,81,84,122,155],"biomedical":[71,163],"documents.":[72,104],"Unlike":[73],"many":[74],"systems,":[76],"performs":[78],"entity":[80],"relationship":[83,121],"graphically":[86],"visualizes":[87],"resulting":[89],"network":[90],"inter-connected":[92],"objects.":[93],"It":[94],"leverages":[95],"PubMed":[97],"search":[98],"engine":[99],"selection":[101],"relevant":[103],"The":[105],"technical":[106],"novelty":[107],"twofold:":[111],"(a)":[112],"its":[113,129,154,165],"ability":[114],"automatically":[116],"learn":[117],"patterns":[119],"without":[123,152],"an":[124],"annotated":[125],"corpus,":[126],"(b)":[128],"high":[130],"performance":[131],"pattern":[132,142],"matching":[133],"algorithm.":[134],"We":[135],"show":[136],"a":[138],"simple":[139],"yet":[140],"effective":[141],"filtering":[143],"technique":[144],"improves":[145],"runtime":[147],"drastically":[151],"harming":[153],"effectiveness.":[156],"Although":[157],"has":[159],"been":[160],"implemented":[161],"texts,":[164],"underlying":[166],"principles":[167],"should":[168],"also":[169],"applicable":[171],"any":[173],"domain.":[175]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}