{"id":"https://openalex.org/W2970392338","doi":"https://doi.org/10.18653/v1/w19-5207","title":"Hierarchical Document Encoder for Parallel Corpus Mining","display_name":"Hierarchical Document Encoder for Parallel Corpus Mining","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970392338","doi":"https://doi.org/10.18653/v1/w19-5207","mag":"2970392338"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5207","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5207","pdf_url":"https://www.aclweb.org/anthology/W19-5207.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 Fourth Conference on Machine Translation (Volume 1: Research 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/W19-5207.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004864409","display_name":"Mandy Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mandy Guo","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112593580","display_name":"Yinfei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinfei Yang","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060065053","display_name":"Keith Stevens","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keith Stevens","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073726152","display_name":"Daniel Cer","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Cer","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049042872","display_name":"Heming Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Ge","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113807382","display_name":"Yun-Hsuan Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-hsuan Sung","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001487094","display_name":"Brian Strope","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Strope","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004215755","display_name":"Ray Kurzweil","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ray Kurzweil","raw_affiliation_strings":["Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI 1600 Amphitheatre Parkway Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5004864409"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.1003,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90405839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9970999956130981,"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":0.7623452544212341},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7105592489242554},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.662063479423523},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6509982943534851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5300901532173157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5132186412811279},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.508098840713501},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5004432201385498},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.46979817748069763},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4248276650905609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623452544212341},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7105592489242554},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.662063479423523},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6509982943534851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5300901532173157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5132186412811279},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.508098840713501},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5004432201385498},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.46979817748069763},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4248276650905609},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-5207","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5207","pdf_url":"https://www.aclweb.org/anthology/W19-5207.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5207","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5207","pdf_url":"https://www.aclweb.org/anthology/W19-5207.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 Fourth Conference on Machine Translation (Volume 1: Research Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970392338.pdf","grobid_xml":"https://content.openalex.org/works/W2970392338.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W145107721","https://openalex.org/W200075660","https://openalex.org/W941230081","https://openalex.org/W2047295649","https://openalex.org/W2101096097","https://openalex.org/W2107695330","https://openalex.org/W2131744502","https://openalex.org/W2140903445","https://openalex.org/W2145251161","https://openalex.org/W2218595819","https://openalex.org/W2250473257","https://openalex.org/W2250929565","https://openalex.org/W2308899597","https://openalex.org/W2463885964","https://openalex.org/W2470673105","https://openalex.org/W2572474373","https://openalex.org/W2734330123","https://openalex.org/W2759183967","https://openalex.org/W2786148476","https://openalex.org/W2794365787","https://openalex.org/W2798389157","https://openalex.org/W2886198413","https://openalex.org/W2891534142","https://openalex.org/W2962735107","https://openalex.org/W2963403868","https://openalex.org/W2964028602","https://openalex.org/W2964093087","https://openalex.org/W2965538726","https://openalex.org/W2970618241","https://openalex.org/W4301633306","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W1950940422","https://openalex.org/W4283822356","https://openalex.org/W2129146436","https://openalex.org/W2032507829"],"abstract_inverted_index":{"We":[0],"explore":[1],"using":[2],"multilingual":[3,25,39],"document":[4,19,33,40,52,96,109],"embeddings":[5,20,53,97],"for":[6,61,114,119],"nearest":[7],"neighbor":[8],"mining":[9],"of":[10],"parallel":[11,108],"data.":[12,77],"Three":[13],"document-level":[14,71],"representations":[15],"are":[16,58,72,84],"investigated:":[17],"(i)":[18],"generated":[21],"by":[22],"simply":[23],"averaging":[24,57],"sentence":[26,92],"embeddings;":[27],"(ii)":[28],"a":[29,37],"neural":[30],"bagof-words":[31],"(BoW)":[32],"encoding":[34],"model;":[35],"(iii)":[36],"hierarchical":[38,82],"encoder":[41],"(HiDE)":[42],"that":[43],"builds":[44],"on":[45,75,104],"our":[46,81],"sentence-level":[47,56],"model.":[48],"The":[49],"results":[50],"show":[51],"derived":[54],"from":[55],"surprisingly":[59],"effective":[60,74],"clean":[62],"datasets,":[63],"but":[64],"suggest":[65],"models":[66,83],"trained":[67,98],"hierarchically":[68],"at":[69],"the":[70,90],"more":[73],"noisy":[76],"Analysis":[78],"experiments":[79],"demonstrate":[80],"very":[85],"robust":[86],"to":[87],"variations":[88],"in":[89],"underlying":[91],"embedding":[93],"quality.":[94],"Using":[95],"with":[99],"HiDE":[100],"achieves":[101],"state-of-the-art":[102],"performance":[103],"United":[105],"Nations":[106],"(UN)":[107],"mining,":[110],"94.9%":[111],"P@1":[112,118],"1":[113],"en-fr":[115],"and":[116],"97.3%":[117],"en-es.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}