{"id":"https://openalex.org/W2955263739","doi":"https://doi.org/10.18653/v1/w19-4327","title":"Best Practices for Learning Domain-Specific Cross-Lingual Embeddings","display_name":"Best Practices for Learning Domain-Specific Cross-Lingual Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2955263739","doi":"https://doi.org/10.18653/v1/w19-4327","mag":"2955263739"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4327","pdf_url":"https://www.aclweb.org/anthology/W19-4327.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4327.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005186935","display_name":"Lena Shakurova","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lena Shakurova","raw_affiliation_strings":["Radboud University, Nijmegen, Netherlands","Textkernel B.V., Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Textkernel B.V., Amsterdam, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085266948","display_name":"Beata Nyari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beata Nyari","raw_affiliation_strings":["Textkernel B.V., Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Textkernel B.V., Amsterdam, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114182123","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-3131-2723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Textkernel B.V., Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Textkernel B.V., Amsterdam, Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090585637","display_name":"Mihai Rotaru","orcid":"https://orcid.org/0000-0002-4847-1923"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihai Rotaru","raw_affiliation_strings":["Textkernel B.V., Amsterdam, Netherlands","University of Pittsburgh, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Textkernel B.V., Amsterdam, Netherlands","institution_ids":[]},{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, United States","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57018263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9866999983787537,"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":0.7896898984909058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7007928490638733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6415232419967651},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5613787174224854},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5451064705848694},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4949912428855896},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.46274545788764954},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4578898847103119},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.44604459404945374},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4122438430786133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12168583273887634},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08733421564102173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896898984909058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7007928490638733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6415232419967651},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5613787174224854},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5451064705848694},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4949912428855896},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.46274545788764954},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4578898847103119},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.44604459404945374},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4122438430786133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12168583273887634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08733421564102173},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-4327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4327","pdf_url":"https://www.aclweb.org/anthology/W19-4327.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.03112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.03112","pdf_url":"https://arxiv.org/pdf/1907.03112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2955263739","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.03112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.03112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.03112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4327","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4327","pdf_url":"https://www.aclweb.org/anthology/W19-4327.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2955263739.pdf","grobid_xml":"https://content.openalex.org/works/W2955263739.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W1614298861","https://openalex.org/W1940872118","https://openalex.org/W2099196804","https://openalex.org/W2126725946","https://openalex.org/W2171082019","https://openalex.org/W2229725139","https://openalex.org/W2250646737","https://openalex.org/W2250741688","https://openalex.org/W2251033195","https://openalex.org/W2251804196","https://openalex.org/W2270364989","https://openalex.org/W2294774419","https://openalex.org/W2508069829","https://openalex.org/W2561995736","https://openalex.org/W2594021297","https://openalex.org/W2626534681","https://openalex.org/W2765961751","https://openalex.org/W2788353357","https://openalex.org/W2889574253","https://openalex.org/W2950133940","https://openalex.org/W2951562155","https://openalex.org/W2964222437"],"related_works":["https://openalex.org/W2970485487","https://openalex.org/W3098553890","https://openalex.org/W2551361256","https://openalex.org/W2885340293","https://openalex.org/W3197618824","https://openalex.org/W2970397112","https://openalex.org/W2995268090","https://openalex.org/W3051275803","https://openalex.org/W3034469191","https://openalex.org/W2787361398","https://openalex.org/W3089118967","https://openalex.org/W2889191148","https://openalex.org/W2947015347","https://openalex.org/W3023305215","https://openalex.org/W3174617982","https://openalex.org/W2913282339","https://openalex.org/W2946451995","https://openalex.org/W3117092952","https://openalex.org/W2952289666","https://openalex.org/W3203813575"],"abstract_inverted_index":{"Cross-lingual":[0],"embeddings":[1,48,53,90,127],"aim":[2],"to":[3,28,39,45,50],"represent":[4],"words":[5,151],"in":[6,9,152,177,199],"multiple":[7,29],"languages":[8,30,35],"a":[10,22,60,68,76,121,143],"shared":[11,69],"vector":[12],"space":[13],"by":[14,31],"capturing":[15],"semantic":[16],"similarities":[17],"across":[18],"languages.":[19,41],"They":[20],"are":[21,82,197],"crucial":[23,198],"component":[24],"for":[25,55,92,115,120],"scaling":[26],"tasks":[27],"transferring":[32],"knowledge":[33],"from":[34,63],"with":[36],"rich":[37],"resources":[38],"low-resource":[40,179],"A":[42],"common":[43],"approach":[44],"learning":[46,203],"cross-lingual":[47,89],"is":[49,97,175],"train":[51],"monolingual":[52,65],"separately":[54],"each":[56],"language":[57,94],"and":[58,87,137,156,190],"learn":[59],"linear":[61],"projection":[62],"the":[64,72,112,117,126,129,140,146,149,153,157,165,171,178,181,183,186,195,200],"spaces":[66],"into":[67],"space,":[70],"where":[71],"mapping":[73],"relies":[74],"on":[75,100,104,128],"small":[77],"seed":[78,85,118],"dictionary.":[79],"While":[80],"there":[81,96],"high-quality":[83],"generic":[84],"dictionaries":[86],"pretrained":[88],"available":[91,176],"many":[93],"pairs,":[95],"little":[98],"research":[99],"how":[101],"they":[102],"perform":[103],"specialised":[105],"tasks.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110],"investigate":[111],"best":[113],"practices":[114],"constructing":[116],"dictionary":[119,150,188],"specific":[122],"domain.":[123],"We":[124,167],"evaluate":[125],"sequence":[130],"labelling":[131],"task":[132],"of":[133,142,148,159,185,194],"Curriculum":[134],"Vitae":[135],"parsing":[136],"show":[138,169],"that":[139,170,192],"size":[141],"bilingual":[144,187],"dictionary,":[145],"frequency":[147],"domain":[154],"corpora":[155],"source":[158],"data":[160,174],"(task-specific":[161],"vs":[162],"generic)":[163],"influence":[164],"performance.":[166],"also":[168],"less":[172],"training":[173],"language,":[180],"more":[182],"construction":[184],"matters,":[189],"demonstrate":[191],"some":[193],"choices":[196],"zero-shot":[201],"transfer":[202],"case.":[204]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}