{"id":"https://openalex.org/W4384641077","doi":"https://doi.org/10.1145/3539618.3591910","title":"The BETTER Cross-Language Datasets","display_name":"The BETTER Cross-Language Datasets","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384641077","doi":"https://doi.org/10.1145/3539618.3591910"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5053747568","display_name":"Ian Soboroff","orcid":"https://orcid.org/0000-0003-2363-3014"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ian Soboroff","raw_affiliation_strings":["National Institute of Standards and Technology, Gaithersburg, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Institute of Standards and Technology, Gaithersburg, MD, USA","institution_ids":["https://openalex.org/I1321296531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053747568"],"corresponding_institution_ids":["https://openalex.org/I1321296531"],"apc_list":null,"apc_paid":null,"fwci":0.9163,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79087845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3047","last_page":"3053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9986000061035156,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9969000220298767,"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":0.86419677734375},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6654288172721863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6377739906311035},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6255086660385132},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6001565456390381},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5983225107192993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5065568685531616},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45832929015159607},{"id":"https://openalex.org/keywords/cross-language-information-retrieval","display_name":"Cross-language information retrieval","score":0.4213530123233795},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.198237806558609},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0638023316860199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86419677734375},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6654288172721863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6377739906311035},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6255086660385132},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6001565456390381},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5983225107192993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5065568685531616},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45832929015159607},{"id":"https://openalex.org/C2778842860","wikidata":"https://www.wikidata.org/wiki/Q986551","display_name":"Cross-language information retrieval","level":3,"score":0.4213530123233795},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.198237806558609},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0638023316860199},{"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:10.1145/3539618.3591910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2037140704","https://openalex.org/W2058896506","https://openalex.org/W2069870183","https://openalex.org/W2075893676","https://openalex.org/W2132314908","https://openalex.org/W2523074985","https://openalex.org/W4309453583"],"related_works":["https://openalex.org/W2250358209","https://openalex.org/W2571755499","https://openalex.org/W2317595117","https://openalex.org/W1788528807","https://openalex.org/W2394022102","https://openalex.org/W1488266984","https://openalex.org/W2725657302","https://openalex.org/W2393978999","https://openalex.org/W2153799433","https://openalex.org/W1590308178"],"abstract_inverted_index":{"The":[0],"IARPA":[1],"BETTER":[2],"(Better":[3],"Extraction":[4],"from":[5,42],"Text":[6],"Through":[7],"Enhanced":[8],"Retrieval)":[9],"program":[10],"held":[11],"three":[12],"evaluations":[13],"of":[14,79],"information":[15,19,52,74],"retrieval":[16,39],"(IR)":[17],"and":[18,40,47,51,81,92],"extraction":[20,41,53],"(IE).":[21],"For":[22],"both":[23],"tasks,":[24],"the":[25,77,86],"only":[26],"training":[27],"data":[28],"available":[29,67],"was":[30],"in":[31,71],"English,":[32],"but":[33],"systems":[34],"had":[35],"to":[36,57,68],"perform":[37],"cross-language":[38,72],"Arabic,":[43],"Farsi,":[44],"Chinese,":[45],"Russian,":[46],"Korean.":[48],"Pooled":[49],"assessment":[50],"annotation":[54],"were":[55,90],"used":[56,97],"create":[58],"reusable":[59],"IR":[60,80],"test":[61],"collections.":[62],"These":[63],"datasets":[64],"are":[65],"freely":[66],"researchers":[69],"working":[70],"retrieval,":[73],"extraction,":[75],"or":[76],"conjunction":[78],"IE.":[82],"This":[83],"paper":[84],"describes":[85],"datasets,":[87],"how":[88,93],"they":[89,94],"constructed,":[91],"might":[95],"be":[96],"by":[98],"researchers.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}