{"id":"https://openalex.org/W83522546","doi":null,"title":"Training Continuous Space Language Models: Some Practical Issues","display_name":"Training Continuous Space Language Models: Some Practical Issues","publication_year":2010,"publication_date":"2010-10-09","ids":{"openalex":"https://openalex.org/W83522546","mag":"83522546"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.3290","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.3290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/D/D10/D10-1076.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5015693566","display_name":"Hai-Son Le","orcid":"https://orcid.org/0009-0003-2240-0451","observed_orcids":["https://orcid.org/0009-0003-2240-0451"]},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hai Son Le","raw_affiliation_strings":["Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051652099","display_name":"Alexandre Allauzen","orcid":"https://orcid.org/0000-0002-8627-1965","observed_orcids":["https://orcid.org/0000-0002-8627-1965"]},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Allauzen","raw_affiliation_strings":["Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-8627-1965","affiliations":[{"raw_affiliation_string":"Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670630","display_name":"Guillaume Wisniewski","orcid":"https://orcid.org/0000-0002-4445-080X","observed_orcids":["https://orcid.org/0000-0002-4445-080X"]},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Wisniewski","raw_affiliation_strings":["Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030615769","display_name":"Fran\u00e7ois Yvon","orcid":"https://orcid.org/0000-0002-7972-7442","observed_orcids":["https://orcid.org/0000-0002-7972-7442"]},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Yvon","raw_affiliation_strings":["Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-7972-7442","affiliations":[{"raw_affiliation_string":"Univ. Paris-Sud, France and LIMSI/CNRS, Orsay Cedex#TAB#","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1343,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95100328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"778","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7993000149726868,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7993000149726868,"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":0.1096000000834465,"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":0.08780000358819962,"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/word-embeddings","display_name":"word embeddings","score":0.8629999756813049},{"id":"https://openalex.org/keywords/convergence-issues","display_name":"convergence issues","score":0.6330000162124634},{"id":"https://openalex.org/keywords/weight-initialization","display_name":"weight initialization","score":0.7419999837875366},{"id":"https://openalex.org/keywords/training-algorithms","display_name":"training algorithms","score":0.6589999794960022},{"id":"https://openalex.org/keywords/perplexity","display_name":"perplexity","score":0.871999979019165},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.9490000009536743}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9365799427032471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8655882477760315},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7803026437759399},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7510949373245239},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.750573992729187},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7211312055587769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6257939338684082},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6171233057975769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5248156785964966},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5022802352905273},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.49371251463890076},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4844055771827698},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48036274313926697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46262311935424805},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4577525854110718},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45765814185142517},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.41245758533477783},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26638951897621155},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.12308451533317566},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.3290","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.3290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/D/D10/D10-1076.pdf","raw_type":"text"},{"id":"mag:83522546","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/D10-1076.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W180685247","https://openalex.org/W1577724162","https://openalex.org/W1916559533","https://openalex.org/W1970689298","https://openalex.org/W1996903695","https://openalex.org/W2056590938","https://openalex.org/W2066558940","https://openalex.org/W2091812280","https://openalex.org/W2100495367","https://openalex.org/W2101105183","https://openalex.org/W2103078213","https://openalex.org/W2106459246","https://openalex.org/W2117130368","https://openalex.org/W2121227244","https://openalex.org/W2124807415","https://openalex.org/W2131462252","https://openalex.org/W2132339004","https://openalex.org/W2142843952","https://openalex.org/W2144790469","https://openalex.org/W2146574666","https://openalex.org/W2154099718","https://openalex.org/W2915109751","https://openalex.org/W2950186769"],"related_works":["https://openalex.org/W7096296490","https://openalex.org/W2250379827","https://openalex.org/W2251098065","https://openalex.org/W2399981156","https://openalex.org/W2083545877","https://openalex.org/W2398269847","https://openalex.org/W6906695172","https://openalex.org/W2089745520","https://openalex.org/W72866721","https://openalex.org/W2137680139"],"abstract_inverted_index":{"Using":[0],"multi-layer":[1],"neural":[2,64],"networks":[3],"to":[4,45,70,112,119],"estimate":[5],"the":[6,46,58,76,94,115],"probabilities":[7],"of":[8,62,75,126],"word":[9,82],"sequences":[10],"is":[11,37],"a":[12,130],"promising":[13],"research":[14],"area":[15],"in":[16,22,124],"statistical":[17,26,65],"language":[18,66],"modeling,":[19],"with":[20],"applications":[21],"speech":[23],"recognition":[24],"and":[25,60,101,118,128],"machine":[27],"translation.":[28],"However,":[29],"training":[30,78,103,116],"such":[31],"models":[32,67],"for":[33,84],"large":[34],"vocabulary":[35],"tasks":[36],"computationally":[38],"challenging":[39],"which":[40],"does":[41],"not":[42],"scale":[43],"easily":[44],"huge":[47],"corpora":[48],"that":[49],"are":[50,87,105,110],"nowadays":[51],"available.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"study":[57],"performance":[59],"behavior":[61],"two":[63],"so":[68],"as":[69],"highlight":[71],"some":[72],"important":[73],"caveats":[74],"classical":[77],"algorithms.":[79],"The":[80],"induced":[81],"embeddings":[83],"extreme":[85],"cases":[86],"also":[88],"analysed,":[89],"thus":[90],"providing":[91],"insight":[92],"into":[93],"convergence":[95],"issues.":[96],"A":[97],"new":[98,102],"initialization":[99],"scheme":[100],"techniques":[104],"then":[106],"introduced.":[107],"These":[108],"methods":[109],"shown":[111],"greatly":[113],"reduce":[114],"time":[117],"significantly":[120],"improve":[121],"performance,":[122],"both":[123],"terms":[125],"perplexity":[127],"on":[129],"large-scale":[131],"translation":[132],"task.":[133],"1":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":8}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}