{"id":"https://openalex.org/W410181177","doi":null,"title":"Factorizing information extraction from text corpora","display_name":"Factorizing information extraction from text corpora","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W410181177","mag":"410181177"},"language":"en","primary_location":{"id":"mag:410181177","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=1414912","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},"volume":null,"type":"article","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/A5060225743","display_name":"Eduard H. Hovy","orcid":"https://orcid.org/0000-0002-3270-7903","observed_orcids":["https://orcid.org/0000-0002-3270-7903"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["University of Southern California"],"raw_orcid":"https://orcid.org/0000-0002-3270-7903","affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113652594","display_name":"Donghui Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghui Feng","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.5756999850273132,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.5756999850273132,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.13570000231266022,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.10899999737739563,"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/automatic-information-extraction","display_name":"automatic information extraction","score":0.8489999771118164},{"id":"https://openalex.org/keywords/web-corpus","display_name":"web corpus","score":0.7110000252723694},{"id":"https://openalex.org/keywords/biomedical-literature","display_name":"biomedical literature","score":0.43799999356269836},{"id":"https://openalex.org/keywords/discussion-threads","display_name":"discussion threads","score":0.5680000185966492},{"id":"https://openalex.org/keywords/topic-classification","display_name":"topic classification","score":0.8880000114440918},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.890999972820282},{"id":"https://openalex.org/keywords/information-overload","display_name":"information overload","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376504182815552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6527737975120544},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5891107320785522},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5835825204849243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5605813264846802},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5522713661193848},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5374532341957092},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5254099369049072},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4401176869869232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40199774503707886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39290106296539307},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:410181177","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=1414912","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":123,"referenced_works":["https://openalex.org/W14532928","https://openalex.org/W28150129","https://openalex.org/W73274768","https://openalex.org/W101519434","https://openalex.org/W110397465","https://openalex.org/W128995279","https://openalex.org/W198220271","https://openalex.org/W348133106","https://openalex.org/W1485852130","https://openalex.org/W1488777300","https://openalex.org/W1493949745","https://openalex.org/W1502749598","https://openalex.org/W1521842739","https://openalex.org/W1525595230","https://openalex.org/W1534730506","https://openalex.org/W1544923801","https://openalex.org/W1565175571","https://openalex.org/W1572970401","https://openalex.org/W1576632330","https://openalex.org/W1592796124","https://openalex.org/W1616576116","https://openalex.org/W1626945812","https://openalex.org/W1736698085","https://openalex.org/W1754818811","https://openalex.org/W1833785989","https://openalex.org/W1846312950","https://openalex.org/W1963521651","https://openalex.org/W1965605789","https://openalex.org/W1968499222","https://openalex.org/W1973103963","https://openalex.org/W1973483159","https://openalex.org/W1980949147","https://openalex.org/W1991862576","https://openalex.org/W1991983805","https://openalex.org/W1993473376","https://openalex.org/W2008711674","https://openalex.org/W2011948397","https://openalex.org/W2015551056","https://openalex.org/W2018557178","https://openalex.org/W2027869740","https://openalex.org/W2033709196","https://openalex.org/W2040737344","https://openalex.org/W2045738181","https://openalex.org/W2050071812","https://openalex.org/W2057576132","https://openalex.org/W2060410220","https://openalex.org/W2065064981","https://openalex.org/W2066636486","https://openalex.org/W2068882115","https://openalex.org/W2069005751","https://openalex.org/W2074560964","https://openalex.org/W2076031315","https://openalex.org/W2080278171","https://openalex.org/W2081798681","https://openalex.org/W2083581617","https://openalex.org/W2085989833","https://openalex.org/W2087347434","https://openalex.org/W2089765404","https://openalex.org/W2091908673","https://openalex.org/W2096028768","https://openalex.org/W2096152098","https://openalex.org/W2096452218","https://openalex.org/W2096496923","https://openalex.org/W2098034778","https://openalex.org/W2098766443","https://openalex.org/W2099685860","https://openalex.org/W2100023649","https://openalex.org/W2100111574","https://openalex.org/W2100873065","https://openalex.org/W2103090613","https://openalex.org/W2104848109","https://openalex.org/W2104984614","https://openalex.org/W2106308476","https://openalex.org/W2110279753","https://openalex.org/W2110693578","https://openalex.org/W2114524997","https://openalex.org/W2114663556","https://openalex.org/W2118612506","https://openalex.org/W2119730684","https://openalex.org/W2119788759","https://openalex.org/W2122978558","https://openalex.org/W2124324386","https://openalex.org/W2124634352","https://openalex.org/W2125055259","https://openalex.org/W2125464431","https://openalex.org/W2130581319","https://openalex.org/W2136370143","https://openalex.org/W2137079713","https://openalex.org/W2137881949","https://openalex.org/W2138621811","https://openalex.org/W2139664619","https://openalex.org/W2143473782","https://openalex.org/W2143666849","https://openalex.org/W2144270295","https://openalex.org/W2145222333","https://openalex.org/W2145687948","https://openalex.org/W2147880316","https://openalex.org/W2148527697","https://openalex.org/W2149033849","https://openalex.org/W2150721933","https://openalex.org/W2150969560","https://openalex.org/W2151873722","https://openalex.org/W2152211274","https://openalex.org/W2152336513","https://openalex.org/W2154124206","https://openalex.org/W2154407881","https://openalex.org/W2154762253","https://openalex.org/W2156641871","https://openalex.org/W2159083595","https://openalex.org/W2161936474","https://openalex.org/W2163844356","https://openalex.org/W2164530124","https://openalex.org/W2164547069","https://openalex.org/W2164949130","https://openalex.org/W2165400255","https://openalex.org/W2167435923","https://openalex.org/W2168822971","https://openalex.org/W2426031434","https://openalex.org/W2435251607","https://openalex.org/W2786781790","https://openalex.org/W2913785658","https://openalex.org/W4251179747","https://openalex.org/W7095901647"],"related_works":["https://openalex.org/W2154531419","https://openalex.org/W4206405097","https://openalex.org/W3093876375","https://openalex.org/W2174011386","https://openalex.org/W194032648","https://openalex.org/W7100581572","https://openalex.org/W1831001034","https://openalex.org/W2094989391","https://openalex.org/W4312353061","https://openalex.org/W1535549842"],"abstract_inverted_index":{"Automatic":[0],"information":[1,12,29],"extraction":[2],"(IE)":[3],"from":[4,175,198,244,315,329,377],"unstructured":[5],"text":[6,16,196,296],"is":[7,58,189,341],"critical":[8],"for":[9,203,291,311,369],"solving":[10],"the":[11,53,112,135,176,218,225,236,245,252,272,303,321,325,333,343,349,394],"overload":[13],"problem.":[14],"As":[15],"formats":[17],"become":[18,25,39],"ever":[19],"more":[20,26,40,87],"varied":[21],"and":[22,34,42,89,102,114,130,144,150,154,182,270,309,362],"IE":[23,37,56,67,105,163,170,227,254,304,312,344],"requirements":[24],"demanding,":[27],"target":[28],"becomes":[30],"harder":[31],"to":[32,68,84,99,159,216,260,275,283,347,359,392],"define":[33,101],"extract.":[35],"Therefore,":[36],"procedures":[38,305],"complex":[41],"generally":[43],"require":[44],"an":[45],"iterative":[46],"cycle":[47],"involving":[48],"multiple":[49],"factors,":[50],"such":[51,139],"as":[52,140,213],"simple":[54,169],"traditional":[55,294],"framework":[57,83,132,228,345],"no":[59],"longer":[60],"adequate.":[61],"However,":[62],"a":[63,82,86,97,127,168,179,280,356,370,378,384],"new":[64,104,128,157,226,316],"paradigm":[65],"of":[66,92,116,124,187,220,238,323,351,397],"address":[69,320],"these":[70],"issues":[71],"has":[72,346],"not":[73,300],"been":[74],"formalized":[75],"yet.":[76],"\r\nIn":[77],"this":[78,108],"thesis,":[79],"we":[80,110,234,256],"develop":[81],"formalize":[85],"general":[88],"powerful":[90],"procedure":[91],"IE.":[93],"Our":[94,191],"formalization":[95],"provides":[96],"method":[98],"rapidly":[100],"structure":[103],"tasks.":[106,164,232],"For":[107],"procedure,":[109,185],"analyze":[111],"role":[113],"impact":[115],"each":[117],"factor.":[118],"This":[119],"thesis":[120],"makes":[121],"two":[122,230],"kinds":[123],"contributions:":[125],"first,":[126],"high-level":[129],"expressive":[131],"that":[133,365],"shows":[134],"relationships":[136],"between":[137,335],"activities":[138],"domain":[141],"knowledge":[142,214,340,375],"modeling":[143],"representation,":[145],"annotation,":[146],"system":[147,192],"building,":[148],"evaluation,":[149],"feedback":[151],"adjustment,":[152],"etc.,":[153],"second,":[155],"several":[156],"approaches":[158,259,298],"performing":[160],"various":[161],"level":[162],"\r\nWe":[165,222],"start":[166],"with":[167,251,388],"task,":[171],"extracting":[172,239,324],"biographical":[173,205],"facts":[174],"web.":[177],"Here":[178],"traditional,":[180],"straightforward,":[181],"one-pass":[183],"problem-solving":[184],"consisting":[186],"definition-learning-testing,":[188],"sufficient.":[190],"automatically":[193],"learns":[194],"surface":[195],"patterns":[197],"dynamic":[199],"flat":[200],"web":[201],"corpora":[202],"answering":[204],"queries.":[206,221],"In":[207,249],"addition,":[208],"sentence":[209],"fragments":[210],"can":[211],"serve":[212],"indicators":[215],"guide":[217],"handling":[219],"then":[223],"demonstrate":[224],"using":[229,373],"more-complex":[231],"First,":[233],"investigate":[235],"problem":[237],"data":[240],"records":[241],"(individual":[242],"experiments)":[243],"biomedical":[246],"research":[247],"literature.":[248],"conformance":[250],"elaborated":[253],"framework,":[255],"have":[257],"developed":[258],"labeling":[261],"individual":[262,267],"sentences,":[263],"grouping":[264],"fields":[265],"into":[266],"meaningful":[268],"objects,":[269],"scaling":[271],"results":[273],"up":[274],"large":[276],"corpora.":[277],"We":[278,319,354,381],"design":[279],"novel":[281,357,385],"solution":[282],"segment":[284],"semantic":[285,289],"objects":[286],"based":[287],"on":[288],"analysis,":[290],"cases":[292],"where":[293],"word-similarity-based":[295],"segmentation":[297],"do":[299],"work.":[301],"\r\nSecond,":[302],"need":[306],"be":[307],"adapted":[308],"extended":[310],"problems":[313],"emerging":[314],"media":[317],"formats.":[318],"task":[322],"most":[326],"informative":[327],"message(s)":[328],"discussion":[330,398],"threads.":[331,399],"Since":[332],"relationship":[334],"thread":[336,363],"messages":[337],"characterizes":[338],"how":[339],"spread,":[342],"accommodate":[348],"analysis":[350],"source":[352],"structure.":[353],"describe":[355],"way":[358],"classify":[360],"message":[361],"topics":[364],"requires":[366],"zero":[367],"annotation":[368],"supervised":[371],"approach,":[372],"ontological":[374],"induced":[376],"canonical":[379],"text.":[380],"also":[382],"invent":[383],"HITS-style":[386],"algorithm":[387],"link":[389],"generation":[390],"functions":[391],"extract":[393],"conversation":[395],"focus":[396]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}