{"id":"https://openalex.org/W184559685","doi":null,"title":"Information extraction from unstructured web text","display_name":"Information extraction from unstructured web text","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W184559685","mag":"184559685"},"language":"en","primary_location":{"id":"mag:184559685","doi":null,"is_oa":false,"landing_page_url":"http://turing.cs.washington.edu/papers/popescu.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},"volume":null,"type":"article","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/A5110184338","display_name":"Oren Etzioni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oren Etzioni","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080992296","display_name":"Ana-Maria Popescu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ana-Maria Popescu","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":10.7232,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97912154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9940999746322632,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9940999746322632,"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":0.002400000113993883,"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":0.0007999999797903001,"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/information-extraction","display_name":"information extraction","score":0.9620000123977661},{"id":"https://openalex.org/keywords/search-engines","display_name":"search engines","score":0.5649999976158142},{"id":"https://openalex.org/keywords/lexico-syntactic-patterns","display_name":"lexico-syntactic patterns","score":0.9900000095367432},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.8880000114440918},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/customer-reviews","display_name":"customer reviews","score":0.8019999861717224},{"id":"https://openalex.org/keywords/user-opinions","display_name":"user opinions","score":0.8669999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929807305335999},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6988298892974854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6221295595169067},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6047450304031372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46997660398483276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46498507261276245},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.44450825452804565},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.42581623792648315},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32937508821487427}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:184559685","doi":null,"is_oa":false,"landing_page_url":"http://turing.cs.washington.edu/papers/popescu.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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":106,"referenced_works":["https://openalex.org/W11295630","https://openalex.org/W41718274","https://openalex.org/W42631803","https://openalex.org/W73274768","https://openalex.org/W77146693","https://openalex.org/W80619934","https://openalex.org/W119080155","https://openalex.org/W136235661","https://openalex.org/W147727067","https://openalex.org/W157725869","https://openalex.org/W197270748","https://openalex.org/W202303397","https://openalex.org/W1480810164","https://openalex.org/W1486093399","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1493719847","https://openalex.org/W1496163732","https://openalex.org/W1499578805","https://openalex.org/W1503501517","https://openalex.org/W1505839237","https://openalex.org/W1509595041","https://openalex.org/W1527110714","https://openalex.org/W1549016832","https://openalex.org/W1553019137","https://openalex.org/W1558641428","https://openalex.org/W1564124598","https://openalex.org/W1567365482","https://openalex.org/W1607723633","https://openalex.org/W1637538661","https://openalex.org/W1754931551","https://openalex.org/W1820727892","https://openalex.org/W1846742003","https://openalex.org/W1932345741","https://openalex.org/W1941378325","https://openalex.org/W1963354518","https://openalex.org/W1963844708","https://openalex.org/W1964654922","https://openalex.org/W1976909068","https://openalex.org/W1986398135","https://openalex.org/W1994563080","https://openalex.org/W1995279738","https://openalex.org/W1999595522","https://openalex.org/W2007756016","https://openalex.org/W2012179495","https://openalex.org/W2022204871","https://openalex.org/W2030639709","https://openalex.org/W2033709196","https://openalex.org/W2038783111","https://openalex.org/W2044520606","https://openalex.org/W2046858497","https://openalex.org/W2048679005","https://openalex.org/W2068737686","https://openalex.org/W2081375810","https://openalex.org/W2089065004","https://openalex.org/W2095603291","https://openalex.org/W2096765155","https://openalex.org/W2098136027","https://openalex.org/W2102968264","https://openalex.org/W2103931177","https://openalex.org/W2104009457","https://openalex.org/W2107792892","https://openalex.org/W2112422413","https://openalex.org/W2114524997","https://openalex.org/W2115023510","https://openalex.org/W2115461474","https://openalex.org/W2122029987","https://openalex.org/W2126854223","https://openalex.org/W2129712609","https://openalex.org/W2130947465","https://openalex.org/W2131165428","https://openalex.org/W2134415318","https://openalex.org/W2134517267","https://openalex.org/W2137023796","https://openalex.org/W2139193890","https://openalex.org/W2139578439","https://openalex.org/W2140785063","https://openalex.org/W2141790691","https://openalex.org/W2142321231","https://openalex.org/W2143349571","https://openalex.org/W2144108169","https://openalex.org/W2148540243","https://openalex.org/W2148572968","https://openalex.org/W2149997683","https://openalex.org/W2152197045","https://openalex.org/W2152455533","https://openalex.org/W2156136571","https://openalex.org/W2159637323","https://openalex.org/W2160587453","https://openalex.org/W2160660844","https://openalex.org/W2162340487","https://openalex.org/W2162586529","https://openalex.org/W2164949130","https://openalex.org/W2165405828","https://openalex.org/W2166706824","https://openalex.org/W2168625136","https://openalex.org/W2169463693","https://openalex.org/W2170340596","https://openalex.org/W2171472464","https://openalex.org/W2273547634","https://openalex.org/W2618567416","https://openalex.org/W2785349534","https://openalex.org/W2787893582","https://openalex.org/W3089010864","https://openalex.org/W3089162859","https://openalex.org/W3146306708"],"related_works":["https://openalex.org/W2247412337","https://openalex.org/W4230081854","https://openalex.org/W1553229631","https://openalex.org/W158294556","https://openalex.org/W2273795931","https://openalex.org/W1999361961","https://openalex.org/W3007862094","https://openalex.org/W2279357934","https://openalex.org/W4385571731","https://openalex.org/W2404634788"],"abstract_inverted_index":{"In":[0],"the":[1,5,21,39,55,58,68,109,124,130,133],"past":[2],"few":[3],"years":[4],"World":[6],"Wide":[7],"Web":[8,43,131],"has":[9,85],"emerged":[10],"as":[11],"an":[12,29],"important":[13],"source":[14],"of":[15,18,23,38,42,57,64,70,96,111,126,135],"data,":[16],"much":[17],"it":[19],"in":[20,51,90],"form":[22],"unstructured":[24],"text.":[25],"This":[26],"thesis":[27],"describes":[28],"extensible":[30],"model":[31,84],"for":[32,132],"information":[33,82,98,128],"extraction":[34,83,99],"that":[35],"takes":[36],"advantage":[37],"unique":[40],"characteristics":[41],"text":[44],"and":[45,75,88,102,115,122],"leverages":[46],"existent":[47],"search":[48],"engine":[49],"technology":[50],"order":[52,91],"to":[53,92],"ensure":[54],"quality":[56],"extracted":[59],"information.":[60],"The":[61],"key":[62],"features":[63,114],"our":[65],"approach":[66],"are":[67],"use":[69],"lexico-syntactic":[71],"patterns,":[72],"Web-scale":[73],"statistics":[74],"unsupervised":[76],"or":[77],"semi-supervised":[78],"learning":[79],"methods.":[80],"Our":[81],"been":[86],"instantiated":[87],"extended":[89],"solve":[93],"a":[94],"set":[95],"diverse":[97],"tasks:":[100],"subclass":[101],"related":[103],"class":[104],"extraction,":[105],"relation":[106],"property":[107],"learning,":[108],"acquisition":[110],"salient":[112],"product":[113],"corresponding":[116],"user":[117],"opinions":[118],"from":[119,129],"customer":[120],"reviews":[121],"finally,":[123],"mining":[125],"commonsense":[127],"benefit":[134],"integrated":[136],"AI":[137],"systems.":[138]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2016-06-24T00:00:00"}