{"id":"https://openalex.org/W2518598732","doi":"https://doi.org/10.18653/v1/w16-2371","title":"Using Term Position Similarity and Language Modeling for Bilingual Document Alignment","display_name":"Using Term Position Similarity and Language Modeling for Bilingual Document Alignment","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2518598732","doi":"https://doi.org/10.18653/v1/w16-2371","mag":"2518598732"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2371","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2371","pdf_url":"https://www.aclweb.org/anthology/W16-2371.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2371.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044046333","display_name":"Thanh Hoa Le","orcid":"https://orcid.org/0000-0003-3841-368X"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Thanh Le","raw_affiliation_strings":["Charles University in Prague","Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Charles University in Prague","institution_ids":["https://openalex.org/I21250087"]},{"raw_affiliation_string":"Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037899273","display_name":"Hoa Trong Vu","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Hoa Trong Vu","raw_affiliation_strings":["Charles University in Prague","Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Charles University in Prague","institution_ids":["https://openalex.org/I21250087"]},{"raw_affiliation_string":"Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076132510","display_name":"Jonathan Oberl\u00e4nder","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jonathan Oberl\u00e4nder","raw_affiliation_strings":["Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics","Charles University in Prague"],"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics","institution_ids":[]},{"raw_affiliation_string":"Charles University in Prague","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077746237","display_name":"Ond\u0159ej Bojar","orcid":"https://orcid.org/0000-0002-0606-0050"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Bojar","raw_affiliation_strings":["Charles University in Prague","Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Charles University in Prague","institution_ids":["https://openalex.org/I21250087"]},{"raw_affiliation_string":"Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044046333"],"corresponding_institution_ids":["https://openalex.org/I21250087"],"apc_list":null,"apc_paid":null,"fwci":1.7738,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89521451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"710","last_page":"716"},"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8274831771850586},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7685075998306274},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7179300785064697},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6683312654495239},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6269665360450745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5803768634796143},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5761374831199646},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5593321323394775},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5074905753135681},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48874831199645996},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4361405074596405},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41439956426620483},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.16217660903930664},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.08861187100410461},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06954064965248108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274831771850586},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7685075998306274},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7179300785064697},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6683312654495239},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6269665360450745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5803768634796143},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5761374831199646},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5593321323394775},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5074905753135681},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48874831199645996},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4361405074596405},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41439956426620483},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.16217660903930664},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.08861187100410461},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06954064965248108},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w16-2371","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2371","pdf_url":"https://www.aclweb.org/anthology/W16-2371.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:biblio.ufal.mff.cuni.cz:-872610391033538824","is_oa":true,"landing_page_url":"http://hdl.handle.net/11346/BIBLIO@id=-872610391033538824","pdf_url":null,"source":{"id":"https://openalex.org/S4306401077","display_name":"Institute of Formal and Applied Linguistics (\u00daFAL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2371","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2371","pdf_url":"https://www.aclweb.org/anthology/W16-2371.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2972937806","display_name":null,"funder_award_id":"LM2015085","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5011736886","display_name":null,"funder_award_id":"M2015","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6103127259","display_name":null,"funder_award_id":"Project No. LM2015085","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G614262777","display_name":null,"funder_award_id":"CERIT-Scientific Cloud (Project No. LM2015085)","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G7176010443","display_name":null,"funder_award_id":"LM2015042","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8900516709","display_name":"Health in my Language","funder_award_id":"644402","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2518598732.pdf","grobid_xml":"https://content.openalex.org/works/W2518598732.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W157432847","https://openalex.org/W630532510","https://openalex.org/W1524068846","https://openalex.org/W1597533204","https://openalex.org/W1965555277","https://openalex.org/W2057900969","https://openalex.org/W2065565011","https://openalex.org/W2085086335","https://openalex.org/W2093390569","https://openalex.org/W2102749417","https://openalex.org/W2116042738","https://openalex.org/W2136542423","https://openalex.org/W2148708890","https://openalex.org/W2152925220","https://openalex.org/W4206765718","https://openalex.org/W4240913316","https://openalex.org/W4393371996"],"related_works":["https://openalex.org/W2950268498","https://openalex.org/W1505906253","https://openalex.org/W2102443632","https://openalex.org/W2007540612","https://openalex.org/W2461708070","https://openalex.org/W1982055477","https://openalex.org/W1815899388","https://openalex.org/W2061135126","https://openalex.org/W2463404432","https://openalex.org/W2162102353"],"abstract_inverted_index":{"The":[0,26,38,55],"WMT":[1],"Bilingual":[2],"Document":[3],"Alignment":[4],"Task":[5],"requires":[6,41],"systems":[7],"to":[8,12,61],"assign":[9],"source":[10,80],"pages":[11],"their":[13],"\"translations\",":[14],"in":[15],"a":[16],"big":[17],"space":[18],"of":[19,45,64,71,79],"possible":[20],"pairs.":[21,37],"We":[22],"present":[23],"four":[24],"methods:":[25],"first":[27,88],"one":[28],"uses":[29],"the":[30,46,53,65,69,72,76,87],"term":[31],"position":[32],"similarity":[33,78],"between":[34],"candidate":[35,83],"document":[36],"second":[39],"method":[40],"automatically":[42],"translated":[43],"versions":[44],"target":[47],"text,":[48],"and":[49,57,82,85],"matches":[50],"them":[51],"with":[52],"candidates.":[54],"third":[56],"fourth":[58],"methods":[59],"try":[60],"overcome":[62],"some":[63],"challenges":[66],"presented":[67],"by":[68,74],"nature":[70],"corpus,":[73],"considering":[75],"string":[77],"URL":[81],"URL,":[84],"combining":[86],"two":[89],"approaches.":[90]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}
