{"id":"https://openalex.org/W2107330157","doi":"https://doi.org/10.3115/1118693.1118706","title":"From words to corpora","display_name":"From words to corpora","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W2107330157","doi":"https://doi.org/10.3115/1118693.1118706","mag":"2107330157"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118706","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118706","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118706","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118706","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088517824","display_name":"Noah A. Smith","orcid":"https://orcid.org/0000-0002-2310-6380"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Noah A. Smith","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD","Johns Hopkins University, baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088517824"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.4038,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.82373057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"95","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9945999979972839,"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":0.8167056441307068},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7324419617652893},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7124277353286743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6906220316886902},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6599667072296143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426274180412292},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5925132632255554},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5120170712471008},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49250516295433044},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.48709630966186523},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4671074151992798},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1606622040271759},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1474463939666748},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09100991487503052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167056441307068},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7324419617652893},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7124277353286743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6906220316886902},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6599667072296143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426274180412292},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5925132632255554},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5120170712471008},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49250516295433044},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.48709630966186523},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4671074151992798},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1606622040271759},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1474463939666748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09100991487503052},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1118693.1118706","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118706","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118706","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118706","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118706","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118706","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308782","display_name":"Hertz Foundation","ror":"https://ror.org/01ycgxf29"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2107330157.pdf","grobid_xml":"https://content.openalex.org/works/W2107330157.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W157432847","https://openalex.org/W1496351660","https://openalex.org/W1581740421","https://openalex.org/W1647729745","https://openalex.org/W1977545325","https://openalex.org/W2024181699","https://openalex.org/W2078396547","https://openalex.org/W2138753018","https://openalex.org/W2139403546","https://openalex.org/W2145080939","https://openalex.org/W2152565070","https://openalex.org/W2422872931","https://openalex.org/W2500014740","https://openalex.org/W3104029765","https://openalex.org/W4253090545"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2359614599"],"abstract_inverted_index":{"This":[0,31],"paper":[1],"presents":[2],"a":[3,17,27,64,71],"technique":[4],"for":[5,66],"discovering":[6],"translationally":[7],"equivalent":[8],"texts.":[9],"It":[10],"is":[11,47],"comprised":[12],"of":[13,16,24,43,53,81,84,94],"the":[14,107],"application":[15],"matching":[18,67],"algorithm":[19],"at":[20],"two":[21,62],"different":[22],"levels":[23,52],"analysis":[25],"and":[26,79],"well-founded":[28],"similarity":[29],"score.":[30],"approach":[32],"can":[33],"be":[34,92],"applied":[35],"to":[36,50,106],"any":[37,41],"multilingual":[38,54],"corpus":[39,72],"using":[40],"kind":[42],"translation":[44],"lexicon;":[45],"it":[46],"therefore":[48],"adaptable":[49],"varying":[51],"resource":[55],"availability.":[56],"Experimental":[57],"results":[58,99],"are":[59,76],"shown":[60],"on":[61],"tasks:":[63],"search":[65],"thirty-word":[68],"segments":[69,75],"in":[70],"where":[73],"some":[74],"mutual":[77],"translations,":[78],"classification":[80],"candidate":[82],"pairs":[83],"web":[85],"pages":[86],"that":[87],"may":[88,90],"or":[89],"not":[91],"translations":[93],"each":[95],"other.":[96],"The":[97],"latter":[98],"compare":[100],"competitively":[101],"with":[102],"previous,":[103],"document-structure-based":[104],"approaches":[105],"same":[108],"problem.":[109]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}