{"id":"https://openalex.org/W157432847","doi":null,"title":"BITS: a method for bilingual text search over the Web","display_name":"BITS: a method for bilingual text search over the Web","publication_year":1999,"publication_date":"1999-09-13","ids":{"openalex":"https://openalex.org/W157432847","mag":"157432847"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.589.8944","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.589.8944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/MTS-1999-Ma-2.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/A5101857436","display_name":"Xiaoyi Ma","orcid":"https://orcid.org/0000-0001-6958-1593","observed_orcids":["https://orcid.org/0000-0001-6958-1593"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyi Ma","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":"https://orcid.org/0000-0001-6958-1593","affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024","observed_orcids":["https://orcid.org/0000-0002-8605-9024"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":"https://orcid.org/0000-0002-8605-9024","affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.7551,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.74476287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9467999935150146,"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":0.9467999935150146,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.049300000071525574,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.002199999988079071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.5410000085830688},{"id":"https://openalex.org/keywords/multilingual-text-retrieval","display_name":"multilingual text retrieval","score":0.8489999771118164},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.5519999861717224},{"id":"https://openalex.org/keywords/german-english-translation","display_name":"German-English translation","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992130517959595},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6255294680595398},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6106738448143005},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5556840896606445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.539098858833313},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5118173956871033},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5091263651847839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48351600766181946},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4668090343475342},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4521872103214264},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.2648633122444153},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23616960644721985},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.589.8944","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.589.8944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/MTS-1999-Ma-2.pdf","raw_type":"text"},{"id":"mag:157432847","doi":null,"is_oa":false,"landing_page_url":"https://www.ldc.upenn.edu/sites/www.ldc.upenn.edu/files/mtsummitVII-bits.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":10,"referenced_works":["https://openalex.org/W1489181569","https://openalex.org/W1554769004","https://openalex.org/W1588612820","https://openalex.org/W1608419360","https://openalex.org/W1969178697","https://openalex.org/W2097333193","https://openalex.org/W2097921974","https://openalex.org/W2114930830","https://openalex.org/W2154384676","https://openalex.org/W2950921009"],"related_works":["https://openalex.org/W7096132514","https://openalex.org/W2399204373","https://openalex.org/W1591008750","https://openalex.org/W7160324084","https://openalex.org/W4404778235","https://openalex.org/W1636405317","https://openalex.org/W200075660","https://openalex.org/W2145080939","https://openalex.org/W407354569","https://openalex.org/W7100283990"],"abstract_inverted_index":{"Parallel":[0],"corpus":[1],"are":[2,42],"valuable":[3],"resource":[4],"for":[5,17],"machine":[6],"translation,":[7],"multi-lingual":[8],"text":[9],"retrieval,":[10],"language":[11,92],"education":[12],"and":[13,94],"other":[14],"applications,":[15],"but":[16],"various":[18],"reasons,":[19],"its":[20],"availability":[21],"is":[22,33,85,111],"very":[23,112],"limited":[24],"at":[25],"present.":[26],"Noticed":[27],"that":[28,108],"the":[29,48,74,101,109],"World":[30,75],"Word":[31],"Web":[32,49,77],"a":[34,54,67],"potential":[35],"source":[36],"to":[37,46,52,88,90],"mine":[38],"parallel":[39],"text,":[40],"researchers":[41],"making":[43],"their":[44],"efforts":[45],"explore":[47],"in":[50],"order":[51],"get":[53],"big":[55],"collection":[56],"of":[57,100],"bitext.":[58],"This":[59],"paper":[60],"presents":[61],"BITS":[62],"(Bilingual":[63],"Internet":[64],"Text":[65],"Search),":[66],"system":[68],"which":[69],"harvests":[70],"multilingual":[71],"texts":[72],"over":[73],"Wide":[76],"with":[78,95],"virtually":[79],"no":[80],"human":[81],"intervention.":[82],"The":[83,98],"technique":[84],"simple,":[86],"easy":[87],"port":[89],"any":[91],"pairs,":[93],"high":[96],"accuracy.":[97],"results":[99],"experiments":[102],"on":[103],"German-":[104],"English":[105],"pair":[106],"proved":[107],"method":[110],"successful.":[113],"1":[114]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}
