{"id":"https://openalex.org/W1654545971","doi":null,"title":"Feature Engineering for Domain Independent Named EntityRecognition and Biomedical Text Mining Applications","display_name":"Feature Engineering for Domain Independent Named EntityRecognition and Biomedical Text Mining Applications","publication_year":2008,"publication_date":"2008-11-24","ids":{"openalex":"https://openalex.org/W1654545971","mag":"1654545971"},"language":"en","primary_location":{"id":"pmh:oai:doktori.bibl.u-szeged.hu:1195","doi":null,"is_oa":false,"landing_page_url":"https://doktori.bibl.u-szeged.hu/id/eprint/1195/24/2008_szarvas_gyorgy_melleklet.tgz","pdf_url":null,"source":{"id":"https://openalex.org/S4306401984","display_name":"SZTE Repository of Dissertations (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Disszert\u00e1ci\u00f3"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5011272289","display_name":"Gy\u00f6rgy Szarvas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gy\u00f6rgy Szarvas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5011272289"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.44679999351501465,"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/T10028","display_name":"Topic Modeling","score":0.44679999351501465,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.3747999966144562,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.07530000060796738,"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/feature-engineering","display_name":"feature engineering","score":0.8510000109672546},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.9459999799728394},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"biomedical text mining","score":0.9470000267028809},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.6930000185966492},{"id":"https://openalex.org/keywords/feature-construction","display_name":"feature construction","score":0.8299999833106995},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.8059999942779541},{"id":"https://openalex.org/keywords/medical-records","display_name":"medical records","score":0.6700000166893005},{"id":"https://openalex.org/keywords/scientific-articles","display_name":"scientific articles","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953199148178101},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5175542235374451},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5084063410758972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5075737237930298},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4989898204803467},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4981706142425537},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4976864159107208},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47622591257095337},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.46679410338401794},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.46629756689071655},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4539754390716553},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45146799087524414},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44722145795822144},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4307405352592468},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41942059993743896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36910364031791687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3632969558238983},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30312106013298035},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.11190038919448853},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:doktori.bibl.u-szeged.hu:1195","doi":null,"is_oa":false,"landing_page_url":"https://doktori.bibl.u-szeged.hu/id/eprint/1195/24/2008_szarvas_gyorgy_melleklet.tgz","pdf_url":null,"source":{"id":"https://openalex.org/S4306401984","display_name":"SZTE Repository of Dissertations (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Disszert\u00e1ci\u00f3"},{"id":"mag:1654545971","doi":null,"is_oa":false,"landing_page_url":"http://doktori.bibl.u-szeged.hu/1195/1/szgy_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W19235523","https://openalex.org/W23149702","https://openalex.org/W86887328","https://openalex.org/W171093852","https://openalex.org/W273036708","https://openalex.org/W1232886308","https://openalex.org/W1262131959","https://openalex.org/W1482032864","https://openalex.org/W1505083828","https://openalex.org/W1516748551","https://openalex.org/W1526146785","https://openalex.org/W1527478795","https://openalex.org/W1529097724","https://openalex.org/W1532548519","https://openalex.org/W1540056032","https://openalex.org/W1540934181","https://openalex.org/W1543515964","https://openalex.org/W1570214144","https://openalex.org/W1570448133","https://openalex.org/W1594104561","https://openalex.org/W1602694398","https://openalex.org/W1664780981","https://openalex.org/W1870686808","https://openalex.org/W1974957625","https://openalex.org/W1986566473","https://openalex.org/W1989099747","https://openalex.org/W2007666495","https://openalex.org/W2007894602","https://openalex.org/W2023920482","https://openalex.org/W2026429670","https://openalex.org/W2038041099","https://openalex.org/W2041614298","https://openalex.org/W2043335066","https://openalex.org/W2049240985","https://openalex.org/W2056357537","https://openalex.org/W2056451646","https://openalex.org/W2066560058","https://openalex.org/W2068882115","https://openalex.org/W2075635421","https://openalex.org/W2086294181","https://openalex.org/W2087347434","https://openalex.org/W2087556608","https://openalex.org/W2096175520","https://openalex.org/W2098136027","https://openalex.org/W2098908879","https://openalex.org/W2099724779","https://openalex.org/W2104949078","https://openalex.org/W2109206523","https://openalex.org/W2110866393","https://openalex.org/W2117273822","https://openalex.org/W2117772341","https://openalex.org/W2118020653","https://openalex.org/W2119421810","https://openalex.org/W2123107826","https://openalex.org/W2124657827","https://openalex.org/W2124738354","https://openalex.org/W2125055259","https://openalex.org/W2126596035","https://openalex.org/W2133341045","https://openalex.org/W2133362931","https://openalex.org/W2136134253","https://openalex.org/W2139865360","https://openalex.org/W2140663467","https://openalex.org/W2143345705","https://openalex.org/W2144578941","https://openalex.org/W2154582566","https://openalex.org/W2158473064","https://openalex.org/W2160987310","https://openalex.org/W2164474247","https://openalex.org/W2164549731","https://openalex.org/W2168020168","https://openalex.org/W2168044158","https://openalex.org/W2169296994","https://openalex.org/W2295973201","https://openalex.org/W2395991145","https://openalex.org/W2398591267","https://openalex.org/W2758799719","https://openalex.org/W2786972369","https://openalex.org/W2915429162"],"related_works":["https://openalex.org/W6991136392","https://openalex.org/W7098478939","https://openalex.org/W2387500216","https://openalex.org/W2524496664","https://openalex.org/W7095731160","https://openalex.org/W6991071754","https://openalex.org/W88727358","https://openalex.org/W2559153168","https://openalex.org/W2750432769","https://openalex.org/W2004111828"],"abstract_inverted_index":{"Information":[0],"searches":[1],"in":[2,14,70,103,138,310,317],"unstructered":[3],"data":[4],"formats":[5],"like":[6],"text":[7,72,239,300],"documents":[8],"are":[9,20,30,44,308],"often":[10],"performed":[11],"by":[12,128],"humans":[13,316],"many":[15],"fields.":[16],"Since":[17],"such":[18],"tasks":[19,59,96,102,254,302],"usually":[21],"beyond":[22],"the":[23,63,71,78,139,176,194,212,223,293],"capability":[24],"of":[25,65,117,142,196,225,235,253],"keyword-lookup":[26],"based":[27,86],"processing,":[28],"they":[29,124],"laborious":[31],"and":[32,38,80,107,136,144,265,296,312],"time":[33],"consuming":[34],"to":[35,50,148,221,261,274,284,292],"do":[36],"manually":[37],"thus":[39,211],"computer-assisted":[40],"or":[41,130,159,199],"automatic":[42],"solutions":[43,52,201],"desperately":[45],"needed.":[46],"Text":[47,57],"Mining":[48,58],"attempts":[49],"provide":[51],"for":[53,202,298],"these":[54,203],"tasks.":[55,204],"Typical":[56],"are:":[60],"\u2022":[61,76,168,179,205],"Finding":[62],"names":[64],"relevant":[66],"objects":[67],"/":[68,92,277],"entities":[69],"(Named":[73],"Entity":[74],"Recognition)":[75],"Evaluating":[77],"document":[79,263],"carrying":[81],"out":[82],"a":[83,115,231,250],"certain":[84],"action":[85],"on":[87,121,217],"its":[88],"content":[89],"(Text":[90],"Categorisation":[91],"Document":[93],"Classification)":[94],"These":[95],"can":[97,125,156,304],"be":[98,126,157],"formulated":[99],"as":[100],"classification":[101,264],"Machine":[104],"Learning":[105],"terminology":[106],"this":[108,146,166],"means":[109],"that":[110,133,173,192,286,297,307],"\u2013":[111,123],"when":[112],"we":[113,169,180,206,215],"have":[114],"set":[116,141],"pre-processed":[118],"(labeled)":[119],"examples":[120,143],"hand":[122],"solved":[127],"statistical":[129,198],"rule-based":[131,200],"systems":[132,306],"discover":[134],"patterns":[135],"regularities":[137],"labeled":[140],"exploit":[145],"knowledge":[147],"process":[149],"new":[150],"documents.":[151],"This":[152],"way":[153],"human":[154],"labour":[155],"replaced":[158],"at":[160],"least":[161],"made":[162],"more":[163],"efficient.":[164],"In":[165],"thesis":[167],"address":[170],"specific":[171,299],"problems":[172],"fall":[174],"into":[175],"above-mentioned":[177],"categories.":[178],"design":[181],"an":[182],"appropriate":[183],"feature":[184,188,213,232,288],"space":[185],"representation":[186,233],"(via":[187],"generation,":[189],"selection,":[190],"etc.)":[191],"permits":[193],"development":[195],"efficient":[197],"evaluate":[207],"our":[208,226],"models":[209],"(and":[210],"representations":[214],"developed)":[216],"standard":[218],"evaluation":[219],"datasets":[220],"demonstrate":[222,285],"usefulness":[224],"systems.":[227],"We":[228],"present":[229],"from":[230,255],"point":[234],"view,":[236],"several":[237],"practical":[238],"mining":[240,301],"applications":[241,247],"developed":[242],"together":[243],"with":[244,315],"colleagues.":[245],"The":[246],"themselves":[248],"cover":[249,267],"wide":[251],"range":[252],"entity":[256],"recognition":[257],"(word":[258],"sequence":[259],"labelling)":[260],"multi-label":[262],"also":[266],"different":[268],"domains":[269],"(from":[270],"business":[271],"news":[272],"texts":[273],"medical":[275],"records":[276],"biological":[278],"scientific":[279],"articles).":[280],"Our":[281],"aim":[282],"was":[283],"task-specific":[287],"engineering":[289],"is":[290],"beneficial":[291],"overall":[294],"performance":[295],"one":[303],"construct":[305],"useful":[309],"practice":[311],"even":[313],"compete":[314],"processing":[318],"textual":[319],"data.":[320],"Gyorgy":[321],"Szarvas,":[322],"June":[323],"2008.":[324]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}