{"id":"https://openalex.org/W2036579265","doi":"https://doi.org/10.1109/infrkm.2012.6204988","title":"Information extraction from semi-structured and un-structured documents using probabilistic context free grammar inference","display_name":"Information extraction from semi-structured and un-structured documents using probabilistic context free grammar inference","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2036579265","doi":"https://doi.org/10.1109/infrkm.2012.6204988","mag":"2036579265"},"language":"en","primary_location":{"id":"doi:10.1109/infrkm.2012.6204988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infrkm.2012.6204988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on Information Retrieval & Knowledge Management","raw_type":"proceedings-article"},"type":"article","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/A5101265486","display_name":"Ramesh Thakur","orcid":null},"institutions":[{"id":"https://openalex.org/I138272832","display_name":"Devi Ahilya Vishwavidyalaya","ror":"https://ror.org/05c2p1f98","country_code":"IN","type":"education","lineage":["https://openalex.org/I138272832"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ramesh Thakur","raw_affiliation_strings":["International Institute of Professional Studies, Devi Ahilya Vishwavidyalaya, Indore, India","International Institute of Professional Studies, Devi Ahilya Viswavidyalaya, Indore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Professional Studies, Devi Ahilya Vishwavidyalaya, Indore, India","institution_ids":["https://openalex.org/I138272832"]},{"raw_affiliation_string":"International Institute of Professional Studies, Devi Ahilya Viswavidyalaya, Indore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018100623","display_name":"Suresh Jain","orcid":"https://orcid.org/0000-0002-4092-8298"},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]},{"id":"https://openalex.org/I4210152052","display_name":"Indo Korea Science and Technology","ror":"https://ror.org/03ynzzx94","country_code":"IN","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4210152052","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suresh Jain","raw_affiliation_strings":["Indian Institute of Technology, Indore, India","KCB Technical Academy, Indore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Indore, India","institution_ids":["https://openalex.org/I64295750"]},{"raw_affiliation_string":"KCB Technical Academy, Indore, India","institution_ids":["https://openalex.org/I4210152052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063657461","display_name":"Narendra S. Chaudhari","orcid":"https://orcid.org/0000-0003-3018-400X"},"institutions":[{"id":"https://openalex.org/I4210152052","display_name":"Indo Korea Science and Technology","ror":"https://ror.org/03ynzzx94","country_code":"IN","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4210152052","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]},{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Narendra S. Chaudhari","raw_affiliation_strings":["KCB Technical Academy, Indore, India","Indian Institute of Technology Indore, India;"],"affiliations":[{"raw_affiliation_string":"KCB Technical Academy, Indore, India","institution_ids":["https://openalex.org/I4210152052"]},{"raw_affiliation_string":"Indian Institute of Technology Indore, India;","institution_ids":["https://openalex.org/I64295750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110563774","display_name":"Rahul Singhai","orcid":null},"institutions":[{"id":"https://openalex.org/I138272832","display_name":"Devi Ahilya Vishwavidyalaya","ror":"https://ror.org/05c2p1f98","country_code":"IN","type":"education","lineage":["https://openalex.org/I138272832"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rahul Singhai","raw_affiliation_strings":["International Institute of Professional Studies, Devi Ahilya Vishwavidyalaya, Indore, India","International Institute of Professional Studies, Devi Ahilya Viswavidyalaya, Indore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Professional Studies, Devi Ahilya Vishwavidyalaya, Indore, India","institution_ids":["https://openalex.org/I138272832"]},{"raw_affiliation_string":"International Institute of Professional Studies, Devi Ahilya Viswavidyalaya, Indore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101265486"],"corresponding_institution_ids":["https://openalex.org/I138272832"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09535676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2484","issue":null,"first_page":"273","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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":0.8450358510017395},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.6880906820297241},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.6779245734214783},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6665446758270264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5954776406288147},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5739307403564453},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5616191625595093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5136920809745789},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4763484299182892},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47581130266189575},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4548526406288147},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44172191619873047},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09554654359817505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450358510017395},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.6880906820297241},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.6779245734214783},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6665446758270264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5954776406288147},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5739307403564453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5616191625595093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5136920809745789},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4763484299182892},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47581130266189575},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4548526406288147},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44172191619873047},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09554654359817505},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infrkm.2012.6204988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infrkm.2012.6204988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on Information Retrieval & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W150801922","https://openalex.org/W1496642291","https://openalex.org/W1531769686","https://openalex.org/W1571222235","https://openalex.org/W1579890941","https://openalex.org/W1701438870","https://openalex.org/W1969005071","https://openalex.org/W1990362766","https://openalex.org/W2002582188","https://openalex.org/W2041522124","https://openalex.org/W2051721370","https://openalex.org/W2093647425","https://openalex.org/W2139709458","https://openalex.org/W2146241389","https://openalex.org/W2162724553","https://openalex.org/W3105206394","https://openalex.org/W4252861488","https://openalex.org/W4394638437","https://openalex.org/W6606229216","https://openalex.org/W6637550998","https://openalex.org/W6660981709"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W50079190","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W2511246383","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W1492005981"],"abstract_inverted_index":{"Large":[0],"number":[1],"of":[2,10,54],"research":[3,91],"papers":[4],"are":[5,27],"available":[6],"in":[7,16,42,47,90,116],"the":[8,78,121],"form":[9],"un-structured":[11,17],"(text)":[12],"format.":[13],"Knowledge":[14],"discovery":[15,53],"document":[18,37],"has":[19],"been":[20,74],"recognized":[21],"as":[22,81],"promising":[23],"task.":[24],"These":[25],"documents":[26],"typically":[28],"formatted":[29],"for":[30],"human":[31],"viewing,":[32],"which":[33],"varies":[34],"widely":[35],"from":[36,57,120],"to":[38,76,102],"document.":[39,122],"Frequent":[40],"change":[41],"their":[43],"formatting":[44],"causes":[45],"difficulties":[46],"constructing":[48],"a":[49,60,98],"global":[50],"schema.":[51],"Thus,":[52],"interesting":[55],"rules":[56,105],"it":[58],"is":[59],"complex":[61],"and":[62,70,109],"tedious":[63],"process.":[64],"Recently,":[65],"conditional":[66],"random":[67],"fields":[68],"(CRFs)":[69],"hand-coded":[71],"wrappers":[72],"have":[73],"used":[75],"label":[77],"text":[79],"(such":[80],"Title,":[82],"Author":[83],"Name(s),":[84],"Affiliation,":[85],"Email,":[86],"Contact":[87],"number,":[88],"etc.":[89],"papers).":[92],"In":[93],"this":[94],"paper":[95],"we":[96],"propose":[97],"novel":[99],"hybrid":[100],"approach":[101],"infer":[103],"grammar":[104],"using":[106],"alignment":[107],"similarity":[108],"probabilistic":[110],"context":[111],"free":[112],"grammar.":[113],"It":[114],"helps":[115],"extracting":[117],"desired":[118],"information":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}