{"id":"https://openalex.org/W2122661071","doi":"https://doi.org/10.1145/1135777.1135898","title":"WebKhoj","display_name":"WebKhoj","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2122661071","doi":"https://doi.org/10.1145/1135777.1135898","mag":"2122661071"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5043358048","display_name":"Prasad Pingali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasad Pingali","raw_affiliation_strings":["Language Technologies Research Centre, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Research Centre, Hyderabad, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079876535","display_name":"Jagadeesh Jagarlamudi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh Jagarlamudi","raw_affiliation_strings":["Language Technologies Research Centre, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Research Centre, Hyderabad, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073786634","display_name":"Vasudeva Varma","orcid":"https://orcid.org/0000-0003-1923-1725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasudeva Varma","raw_affiliation_strings":["Language Technologies Research Centre, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Research Centre, Hyderabad, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.3329,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98759813,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9923999905586243,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9753000140190125,"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":0.8014430999755859},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.724890410900116},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7168667316436768},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5621790885925293},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5331892967224121},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.47943252325057983},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.46992790699005127},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4508197605609894},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.42614901065826416},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4234272837638855},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.39701640605926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014430999755859},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.724890410900116},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7168667316436768},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5621790885925293},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5331892967224121},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.47943252325057983},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.46992790699005127},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4508197605609894},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.42614901065826416},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4234272837638855},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.39701640605926514}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1135898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1797354850","https://openalex.org/W1978394996","https://openalex.org/W1997211290","https://openalex.org/W2002806357","https://openalex.org/W2007842132","https://openalex.org/W2017726337","https://openalex.org/W2029500199","https://openalex.org/W2033630752","https://openalex.org/W2038619519","https://openalex.org/W2057338453","https://openalex.org/W2085219562","https://openalex.org/W2120176502","https://openalex.org/W2168965629"],"related_works":["https://openalex.org/W1994958611","https://openalex.org/W2402678663","https://openalex.org/W3199173531","https://openalex.org/W2277785728","https://openalex.org/W2379145789","https://openalex.org/W4200125296","https://openalex.org/W2610451498","https://openalex.org/W2945544759","https://openalex.org/W2109463504","https://openalex.org/W1547088227"],"abstract_inverted_index":{"Today":[0],"web":[1,26,35,118],"search":[2,56,64],"engines":[3],"provide":[4],"the":[5,12,25,51,80,89,101,107],"easiest":[6],"way":[7],"to":[8,31,93],"reach":[9],"information":[10],"on":[11,24,79,115],"web.":[13,81],"In":[14,58,100],"this":[15,59],"scenario,":[16],"more":[17],"than":[18],"95%":[19],"of":[20,34,37,47,71,96,106],"Indian":[21,76,97,116],"language":[22,77,85,117],"content":[23,52,78],"is":[27,69],"not":[28],"searchable":[29],"due":[30],"multiple":[32],"encodings":[33,39],"pages.Most":[36],"these":[38],"are":[40],"proprietary":[41],"and":[42,74,88],"hence":[43],"need":[44],"some":[45,105],"kind":[46],"standardization":[48],"for":[49],"making":[50],"accessible":[53],"via":[54],"a":[55,63,84],"engine.":[57],"paper":[60],"we":[61,103],"present":[62],"engine":[65],"called":[66],"WebKhoj":[67],"which":[68],"capable":[70],"searching":[72],"multi-script":[73],"multi-encoded":[75],"We":[82],"describe":[83],"focused":[86],"crawler":[87],"transcoding":[90],"processes":[91],"involved":[92],"achieve":[94],"accessibility":[95],"langauge":[98],"content.":[99,119],"end":[102],"report":[104],"experiments":[108],"that":[109],"were":[110],"conducted":[111],"along":[112],"with":[113],"results":[114]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}