{"id":"https://openalex.org/W2170722465","doi":"https://doi.org/10.1109/icassp.2009.4960710","title":"Incorporating monolingual corpora into bilingual latent semantic analysis for crosslingual LM adaptation","display_name":"Incorporating monolingual corpora into bilingual latent semantic analysis for crosslingual LM adaptation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2170722465","doi":"https://doi.org/10.1109/icassp.2009.4960710","mag":"2170722465"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033756912","display_name":"Wilson Tam","orcid":"https://orcid.org/0000-0003-0641-3060"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yik-Cheung Tam","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033756912"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4516,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75975033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4821","last_page":"4824"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.8215130567550659},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.6907927393913269},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6870337724685669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6434776186943054},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6345581412315369},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.6083043813705444},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5667731761932373},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.42518144845962524},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.15797004103660583},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09925827383995056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8215130567550659},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.6907927393913269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6870337724685669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434776186943054},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6345581412315369},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.6083043813705444},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5667731761932373},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.42518144845962524},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.15797004103660583},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09925827383995056},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4960710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.8632","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.8632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.ira.uka.de/fileadmin/media/publication_files/TamSchultz-ICASSP2009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.453.3580","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.453.3580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~yct/papers/icassp09_blda.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W92412080","https://openalex.org/W182840523","https://openalex.org/W1880262756","https://openalex.org/W2104042555","https://openalex.org/W2105577415","https://openalex.org/W2139989135","https://openalex.org/W2542068976","https://openalex.org/W3197037075","https://openalex.org/W6639619044","https://openalex.org/W6680623075","https://openalex.org/W6800030257"],"related_works":["https://openalex.org/W2381926679","https://openalex.org/W2611300636","https://openalex.org/W2082644203","https://openalex.org/W3165040664","https://openalex.org/W2007009951","https://openalex.org/W2350539780","https://openalex.org/W2002351209","https://openalex.org/W3122652148","https://openalex.org/W1583866266","https://openalex.org/W2123926498"],"abstract_inverted_index":{"The":[0,57],"major":[1],"limitation":[2],"in":[3,72,78],"bilingual":[4],"latent":[5],"semantic":[6],"analysis":[7],"(bLSA)":[8],"is":[9,46,83],"the":[10,39,49,87],"requirement":[11],"of":[12,38],"parallel":[13,33,40,59],"training":[14,25],"corpora.":[15,30,91],"Motivated":[16],"by":[17],"semi-supervised":[18],"learning,":[19],"we":[20],"propose":[21],"a":[22,68],"clusterbased":[23],"bLSA":[24],"approach":[26],"to":[27,48,53,66,86],"incorporate":[28],"monolingual":[29,44,90],"Treating":[31],"each":[32,43],"document":[34,41,45,60],"pair":[35],"as":[36,64],"centroids":[37],"clusters,":[42],"associated":[47],"closest":[50],"centroid":[51],"according":[52],"their":[54],"topic":[55,70],"similarity.":[56],"resulting":[58],"clusters":[61],"are":[62],"used":[63],"constraints":[65],"enforce":[67],"one-to-one":[69],"correspondence":[71],"variational":[73],"EM.":[74],"Slight":[75],"performance":[76],"improvement":[77],"crosslingual":[79],"language":[80],"model":[81],"adaptation":[82],"observed":[84],"compared":[85],"baseline":[88],"without":[89]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}