{"id":"https://openalex.org/W2062552201","doi":"https://doi.org/10.1109/nlpke.2010.5587860","title":"Extraction of purpose data using surface text patterns","display_name":"Extraction of purpose data using surface text patterns","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2062552201","doi":"https://doi.org/10.1109/nlpke.2010.5587860","mag":"2062552201"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2010.5587860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5111448122","display_name":"P. Kiran Mayee","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P Kiran Mayee","raw_affiliation_strings":["Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, Andhra Pradesh, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103605566","display_name":"Rajeev Sangal","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajeev Sangal","raw_affiliation_strings":["Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, Andhra Pradesh, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100683998","display_name":"Soma Paul","orcid":"https://orcid.org/0000-0002-2504-4419"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soma Paul","raw_affiliation_strings":["Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Research Centre, International Institute of Information Technology, Hyderabad, Andhra Pradesh, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1751301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.9977999925613403,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8158968687057495},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7183310985565186},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5852293968200684},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5465795397758484},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4646017253398895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4642411470413208},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4138382375240326},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4092139005661011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3343287706375122},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16875621676445007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0702643096446991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158968687057495},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7183310985565186},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5852293968200684},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5465795397758484},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4646017253398895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4642411470413208},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4138382375240326},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4092139005661011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3343287706375122},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16875621676445007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0702643096446991},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2010.5587860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2010.5587860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Natural Language Processing and Knowledge Engineering(NLPKE-2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W73633278","https://openalex.org/W938539187","https://openalex.org/W1511749302","https://openalex.org/W1525766883","https://openalex.org/W1990061958","https://openalex.org/W2108312008","https://openalex.org/W2124634352","https://openalex.org/W2136309948","https://openalex.org/W2167435923","https://openalex.org/W2790812272","https://openalex.org/W6603039616","https://openalex.org/W6630585684","https://openalex.org/W6678794661"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W2027108423","https://openalex.org/W1855666948","https://openalex.org/W2758561209","https://openalex.org/W1548095260","https://openalex.org/W2594414941","https://openalex.org/W2781711915","https://openalex.org/W2112817590","https://openalex.org/W1555291398"],"abstract_inverted_index":{"This":[0,59],"paper":[1],"presents":[2],"the":[3,14,40,69,83,106],"concept":[4],"of":[5,23,50,79],"surface":[6],"text":[7],"patterns":[8,33,65,93],"for":[9,30,86,103],"extracting":[10],"purpose":[11,32,52,99],"data":[12],"from":[13,39,68,105],"web.":[15],"In":[16],"order":[17],"to":[18,54,97],"obtain":[19],"an":[20],"optimal":[21],"set":[22],"patterns,":[24],"we":[25],"have":[26,108],"developed":[27],"a":[28,46,55],"method":[29],"learning":[31],"automatically.":[34],"A":[35],"corpus":[36,60],"was":[37,61],"downloaded":[38],"Internet":[41],"using":[42],"bootstrapping":[43],"by":[44,72],"providing":[45],"few":[47],"hand-crafted":[48],"examples":[49],"each":[51,80,87],"pattern":[53,81],"generic":[56],"search":[57],"engine.":[58],"then":[62,95],"tagged":[63],"and":[64,75,82],"were":[66,89,94],"extracted":[67,92],"returned":[70],"documents":[71],"automated":[73],"means":[74],"standardized.":[76],"The":[77,91,101],"precision":[78,85],"average":[84],"group":[88],"computed.":[90],"used":[96],"extract":[98],"data.":[100],"results":[102],"extraction":[104],"web":[107],"been":[109],"reported.":[110]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
