{"id":"https://openalex.org/W2251841523","doi":"https://doi.org/10.3115/v1/e14-3002","title":"Unsupervised Relation Extraction of In-Domain Data from Focused Crawls","display_name":"Unsupervised Relation Extraction of In-Domain Data from Focused Crawls","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251841523","doi":"https://doi.org/10.3115/v1/e14-3002","mag":"2251841523"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-3002","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-3002","pdf_url":"https://aclanthology.org/E14-3002.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/E14-3002.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033413102","display_name":"Steffen Remus","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Steffen Remus","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt,"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt,","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033413102"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":3.1556,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93212338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.992900013923645,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9900000095367432,"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":0.8067072629928589},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7472535371780396},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6675736308097839},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6287854313850403},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6251096129417419},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5689067840576172},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5613817572593689},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4804770052433014},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4472259283065796},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4398422837257385},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42917773127555847},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4180114269256592},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3960344195365906},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3740537762641907},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3424605131149292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24010667204856873},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23468351364135742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067072629928589},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7472535371780396},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6675736308097839},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6287854313850403},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6251096129417419},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5689067840576172},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5613817572593689},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4804770052433014},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4472259283065796},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4398422837257385},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42917773127555847},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4180114269256592},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3960344195365906},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3740537762641907},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3424605131149292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24010667204856873},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23468351364135742},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/e14-3002","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-3002","pdf_url":"https://aclanthology.org/E14-3002.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/e14-3002","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-3002","pdf_url":"https://aclanthology.org/E14-3002.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251841523.pdf","grobid_xml":"https://content.openalex.org/works/W2251841523.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W165237679","https://openalex.org/W806995027","https://openalex.org/W1489992655","https://openalex.org/W1512387364","https://openalex.org/W1516346799","https://openalex.org/W1535206496","https://openalex.org/W1654905138","https://openalex.org/W1662133657","https://openalex.org/W1848279521","https://openalex.org/W1934041838","https://openalex.org/W1965605789","https://openalex.org/W1982697162","https://openalex.org/W2048679005","https://openalex.org/W2059031628","https://openalex.org/W2062837929","https://openalex.org/W2068737686","https://openalex.org/W2097606805","https://openalex.org/W2098688754","https://openalex.org/W2103018059","https://openalex.org/W2103318667","https://openalex.org/W2103986443","https://openalex.org/W2107598941","https://openalex.org/W2118928552","https://openalex.org/W2127978399","https://openalex.org/W2130158090","https://openalex.org/W2133322356","https://openalex.org/W2135891920","https://openalex.org/W2144036807","https://openalex.org/W2151007976","https://openalex.org/W2152358231","https://openalex.org/W2154507487","https://openalex.org/W2155870214","https://openalex.org/W2157302829","https://openalex.org/W2158952118","https://openalex.org/W2181042685","https://openalex.org/W2188533213","https://openalex.org/W2251384727","https://openalex.org/W2252133428","https://openalex.org/W2252238828","https://openalex.org/W2796493717","https://openalex.org/W2882319491"],"related_works":["https://openalex.org/W842810586","https://openalex.org/W4319940250","https://openalex.org/W2352298027","https://openalex.org/W2092919065","https://openalex.org/W3138801416","https://openalex.org/W4236762297","https://openalex.org/W2444550338","https://openalex.org/W2369351710","https://openalex.org/W2594363579","https://openalex.org/W2169232658"],"abstract_inverted_index":{"This":[0],"thesis":[1],"proposal":[2,38],"approaches":[3],"unsupervised":[4,97],"relation":[5,98,158],"extraction":[6,99],"from":[7,23],"web":[8,20,46,62,76,80],"data,":[9],"which":[10],"is":[11,39,82],"collected":[12,79],"by":[13,100,138],"crawling":[14,63,142],"only":[15],"those":[16],"parts":[17],"of":[18,36,45,74,113,135],"the":[19,24,42,72,102,133,147],"that":[21,65],"are":[22,150],"same":[25],"domain":[26,51,134],"as":[27,119],"a":[28,49,54,59],"relatively":[29],"small":[30],"reference":[31],"corpus.":[32],"The":[33,78],"first":[34],"part":[35],"this":[37],"concerned":[40],"with":[41],"efficient":[43],"discovery":[44],"documents":[47,69],"for":[48,124,132],"particular":[50,55],"and":[52,70,121,160],"in":[53,85,146],"language.":[56],"We":[57,106,128,149],"create":[58],"combined,":[60],"focused":[61],"system":[64,131],"automatically":[66],"collects":[67],"relevant":[68],"minimizes":[71],"amount":[73],"irrelevant":[75],"content.":[77],"data":[81],"semantically":[83],"processed":[84],"order":[86],"to":[87,152],"acquire":[88],"rich":[89],"in-domain":[90],"knowledge.":[91],"Here,":[92],"we":[93,161],"focus":[94],"on":[95,116,141,157],"fully":[96],"employing":[101],"extended":[103],"distributional":[104,108],"hypothesis.":[105],"use":[107],"similarities":[109],"between":[110],"two":[111],"pairs":[112],"nominals":[114],"based":[115],"dependency":[117],"paths":[118],"context":[120],"vice":[122],"versa":[123],"identifying":[125],"relational":[126],"structure.":[127],"apply":[129],"our":[130],"educational":[136,144],"sciences":[137],"focusing":[139],"primarily":[140],"scientific":[143],"publications":[145],"web.":[148],"able":[151],"produce":[153],"promising":[154],"initial":[155],"results":[156],"identification":[159],"will":[162],"discuss":[163],"future":[164],"directions.":[165]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}