{"id":"https://openalex.org/W2898427945","doi":"https://doi.org/10.18653/v1/k18-1002","title":"Continuous Word Embedding Fusion via Spectral Decomposition","display_name":"Continuous Word Embedding Fusion via Spectral Decomposition","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2898427945","doi":"https://doi.org/10.18653/v1/k18-1002","mag":"2898427945"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k18-1002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k18-1002","pdf_url":"https://www.aclweb.org/anthology/K18-1002.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 22nd Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K18-1002.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003226543","display_name":"Tianfan Fu","orcid":"https://orcid.org/0000-0002-5574-2541"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianfan Fu","raw_affiliation_strings":["Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439666","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0002-8640-9370"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Microsoft Research Cambridge Cambridge, CB1 2FB, UK"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Cambridge Cambridge, CB1 2FB, UK","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036302820","display_name":"Stephan Mandt","orcid":"https://orcid.org/0000-0001-7836-7839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Mandt","raw_affiliation_strings":["Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Los Angeles, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003226543"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68197842,"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":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.9987000226974487,"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/fusion","display_name":"Fusion","score":0.6304534077644348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6017226576805115},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5941656827926636},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5832154154777527},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5701478719711304},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49184083938598633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46886661648750305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3843647837638855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37278568744659424},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22044289112091064},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12748226523399353},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09057053923606873}],"concepts":[{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6304534077644348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017226576805115},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5941656827926636},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5832154154777527},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5701478719711304},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49184083938598633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46886661648750305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3843647837638855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37278568744659424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22044289112091064},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12748226523399353},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09057053923606873},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/k18-1002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k18-1002","pdf_url":"https://www.aclweb.org/anthology/K18-1002.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 22nd Conference on Computational Natural Language Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k18-1002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k18-1002","pdf_url":"https://www.aclweb.org/anthology/K18-1002.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 22nd Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2898427945.pdf","grobid_xml":"https://content.openalex.org/works/W2898427945.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1485446097","https://openalex.org/W1486649854","https://openalex.org/W1614298861","https://openalex.org/W1871665132","https://openalex.org/W1981745143","https://openalex.org/W1994616650","https://openalex.org/W2028742638","https://openalex.org/W2106433837","https://openalex.org/W2118090838","https://openalex.org/W2125031621","https://openalex.org/W2131744502","https://openalex.org/W2134432876","https://openalex.org/W2141418759","https://openalex.org/W2153579005","https://openalex.org/W2166465139","https://openalex.org/W2167433878","https://openalex.org/W2167680278","https://openalex.org/W2251491951","https://openalex.org/W2262907013","https://openalex.org/W2264074007","https://openalex.org/W2475611006","https://openalex.org/W2493916176","https://openalex.org/W2738734060","https://openalex.org/W2949447796","https://openalex.org/W2950577311","https://openalex.org/W2962739339","https://openalex.org/W2963781962","https://openalex.org/W2964198102","https://openalex.org/W2964231305","https://openalex.org/W4237284205","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W947140380","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,97],"have":[2],"become":[3],"a":[4,59,78,103],"mainstream":[5],"tool":[6],"in":[7],"statistical":[8],"natural":[9],"language":[10],"processing.":[11],"Practitioners":[12],"often":[13,48],"use":[14],"pre-trained":[15,35,62,85],"word":[16,36,63,87,96],"vectors,":[17],"which":[18,27],"were":[19],"trained":[20],"on":[21,31,91,110],"large":[22],"generic":[23,86],"text":[24],"corpora,":[25],"and":[26,54,143],"are":[28],"readily":[29],"available":[30],"the":[32,52,92,125,130],"web.":[33],"However,":[34],"vectors":[37],"oftentimes":[38],"lack":[39],"important":[40],"words":[41,57,76,127],"from":[42,77],"specific":[43],"domains.":[44],"It":[45],"is":[46,121,140],"therefore":[47],"desirable":[49],"to":[50,101,123,135],"extend":[51],"vocabulary":[53],"embed":[55,124],"new":[56,75,82,126],"into":[58,84,129],"set":[60],"of":[61,95],"vectors.":[64],"In":[65],"this":[66,107],"paper,":[67],"we":[68],"present":[69,102],"an":[70],"efficient":[71],"method":[72,120,139],"for":[73,106],"including":[74],"specialized":[79,115],"corpus,":[80],"containing":[81],"words,":[83],"embeddings.":[88],"We":[89],"build":[90],"established":[93],"view":[94],"as":[98],"matrix":[99],"factorizations":[100],"spectral":[104],"algorithm":[105],"task.":[108],"Experiments":[109],"several":[111],"domain-specific":[112],"corpora":[113],"with":[114],"vocabularies":[116],"demonstrate":[117],"that":[118],"our":[119,138],"able":[122],"efficiently":[128],"original":[131],"embedding":[132],"space.":[133],"Compared":[134],"competing":[136],"methods,":[137],"faster,":[141],"parameter-free,":[142],"deterministic.":[144]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}