{"id":"https://openalex.org/W2061118075","doi":"https://doi.org/10.3115/1118693.1118730","title":"Processing comparable corpora with Bilingual Suffix Trees","display_name":"Processing comparable corpora with Bilingual Suffix Trees","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W2061118075","doi":"https://doi.org/10.3115/1118693.1118730","mag":"2061118075"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118730","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118730","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118730","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/10.3115/1118693.1118730","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072829860","display_name":"Dragos Stefan Munteanu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dragos Stefan Munteanu","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA","Univ. of Southern California, Marina del Rey, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]},{"raw_affiliation_string":"Univ. of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005020376","display_name":"Daniel Marcu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Marcu","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA","Univ. of Southern California, Marina del Rey, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]},{"raw_affiliation_string":"Univ. of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.123,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.78080981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"289","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.995199978351593,"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":0.8605951070785522},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.8521718978881836},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7620059251785278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7451307773590088},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.6001251935958862},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5703399777412415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32129967212677},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2915801405906677},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2041706144809723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605951070785522},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.8521718978881836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7620059251785278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7451307773590088},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6001251935958862},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5703399777412415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32129967212677},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2915801405906677},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2041706144809723},{"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":"doi:10.3115/1118693.1118730","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118730","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118730","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.4508","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.4508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/~marcu/papers/biling-suffix-trees-emnlp2002.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118730","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118730","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118730","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2061118075.pdf","grobid_xml":"https://content.openalex.org/works/W2061118075.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W24831934","https://openalex.org/W136035420","https://openalex.org/W1889220380","https://openalex.org/W1990061958","https://openalex.org/W2006969979","https://openalex.org/W2021809202","https://openalex.org/W2030962049","https://openalex.org/W2041232209","https://openalex.org/W2049652268","https://openalex.org/W2059513841","https://openalex.org/W2102749417","https://openalex.org/W2107079154","https://openalex.org/W2138247936","https://openalex.org/W2139812240","https://openalex.org/W2274925578","https://openalex.org/W2533248932"],"related_works":["https://openalex.org/W2296205523","https://openalex.org/W2143927888","https://openalex.org/W2242707303","https://openalex.org/W2757753881","https://openalex.org/W2123678043","https://openalex.org/W2125885330","https://openalex.org/W2902262852","https://openalex.org/W37319627","https://openalex.org/W1572297637","https://openalex.org/W2251265917"],"abstract_inverted_index":{"We":[0,16],"introduce":[1],"Bilingual":[2],"Suffix":[3],"Trees":[4],"(BST),":[5],"a":[6,39,48,58,76],"data":[7],"structure":[8],"that":[9,19,43],"is":[10],"suitable":[11],"for":[12],"exploiting":[13],"comparable":[14,35,77],"corpora.":[15,36],"discuss":[17],"algorithms":[18],"use":[20],"BSTs":[21],"in":[22],"order":[23],"to":[24],"create":[25],"parallel":[26,52,62],"corpora":[27],"and":[28,69],"learn":[29],"translations":[30,74],"of":[31,50,60,64,79],"unseen":[32],"words":[33,81],"from":[34,47,75],"Starting":[37],"with":[38],"small":[40],"bilingual":[41],"dictionary":[42],"was":[44],"derived":[45],"automatically":[46,56],"corpus":[49,59,78],"5.000":[51],"sentences,":[53],"we":[54],"have":[55],"extracted":[57],"33.926":[61],"phrases":[63],"size":[65],"greater":[66],"than":[67],"3,":[68],"learned":[70],"9":[71],"new":[72],"word":[73],"1.3M":[80],"(100.000":[82],"sentences).":[83]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}