{"id":"https://openalex.org/W2124732071","doi":null,"title":"Large Scale Acquisition of Paraphrases for Learning Surface Patterns","display_name":"Large Scale Acquisition of Paraphrases for Learning Surface Patterns","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2124732071","mag":"2124732071"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.7444","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.7444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P08/P08-1077.pdf","raw_type":"text"},"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/A5086631105","display_name":"Rahul Bhagat","orcid":"https://orcid.org/0009-0001-9783-9317","observed_orcids":["https://orcid.org/0009-0001-9783-9317"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahul Bhagat","raw_affiliation_strings":["[Information Sciences Institute]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Information Sciences Institute]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073610500","display_name":"Deepak Ravichandran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepak Ravichandran","raw_affiliation_strings":["Google\u2020#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google\u2020#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.3118,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.99165773,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.004399999976158142,"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":0.00019999999494757503,"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/monolingual-corpora","display_name":"monolingual corpora","score":0.8429999947547913},{"id":"https://openalex.org/keywords/surface-patterns","display_name":"surface patterns","score":0.6480000019073486},{"id":"https://openalex.org/keywords/relation-extraction","display_name":"relation extraction","score":0.9419999718666077},{"id":"https://openalex.org/keywords/paraphrase-generation","display_name":"paraphrase generation","score":0.5149999856948853}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9777378439903259},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9353469610214233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824007511138916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7611331343650818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7147126197814941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6421202421188354},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.638954758644104},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.4954904317855835},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4429141581058502},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4406013488769531},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.41215047240257263},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3430459499359131},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3324376046657562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09446293115615845},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.7444","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.7444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P08/P08-1077.pdf","raw_type":"text"},{"id":"mag:2124732071","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/P/P08/P08-1077.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Meeting of the Association for Computational Linguistics","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":23,"referenced_works":["https://openalex.org/W99075841","https://openalex.org/W137105571","https://openalex.org/W1965605789","https://openalex.org/W1980776243","https://openalex.org/W2002664886","https://openalex.org/W2012833704","https://openalex.org/W2068737686","https://openalex.org/W2094028551","https://openalex.org/W2099111195","https://openalex.org/W2107130271","https://openalex.org/W2112740777","https://openalex.org/W2118733980","https://openalex.org/W2122056984","https://openalex.org/W2124323636","https://openalex.org/W2125464431","https://openalex.org/W2129468719","https://openalex.org/W2135843243","https://openalex.org/W2143927888","https://openalex.org/W2145685230","https://openalex.org/W2147444342","https://openalex.org/W2160587453","https://openalex.org/W2167435923","https://openalex.org/W2882319491"],"related_works":["https://openalex.org/W2129111595","https://openalex.org/W2288348255","https://openalex.org/W7097981153","https://openalex.org/W191017350","https://openalex.org/W2003677545","https://openalex.org/W7098727088","https://openalex.org/W2107130271","https://openalex.org/W7098255700","https://openalex.org/W2251044566","https://openalex.org/W2902340330"],"abstract_inverted_index":{"Paraphrases":[0],"have":[1],"proved":[2],"to":[3,71],"be":[4],"useful":[5],"in":[6],"many":[7],"applications,":[8],"including":[9],"Machine":[10],"Translation,":[11],"Question":[12],"Answering,":[13],"Summarization,":[14],"and":[15,95],"Information":[16],"Retrieval.":[17],"Paraphrase":[18],"acquisition":[19,60],"methods":[20],"that":[21,65],"use":[22,68],"a":[23,34,41,89],"single":[24],"monolingual":[25,46],"corpus":[26],"often":[27],"produce":[28],"only":[29],"syntactic":[30],"paraphrases.":[31],"We":[32,62],"present":[33],"method":[35,49],"for":[36,75,105],"obtaining":[37],"surface":[38,73],"paraphrases,":[39],"using":[40,88],"150GB":[42],"(25":[43],"billion":[44],"words)":[45],"corpus.":[47],"Our":[48,78],"achieves":[50],"an":[51],"accuracy":[52],"of":[53,91,107],"around":[54],"70":[55],"%":[56,103],"on":[57],"the":[58,92,108],"paraphrase":[59],"task.":[61],"further":[63],"show":[64],"we":[66],"can":[67,96],"these":[69],"paraphrases":[70],"generate":[72],"patterns":[74,79],"relation":[76],"extraction.":[77],"are":[80],"much":[81],"more":[82,100],"precise":[83],"than":[84,101],"those":[85],"obtained":[86],"by":[87],"state":[90],"art":[93],"baseline":[94],"extract":[97],"relations":[98],"with":[99],"80":[102],"precision":[104],"each":[106],"test":[109],"relations.":[110],"1":[111]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":14}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}