{"id":"https://openalex.org/W2950858167","doi":"https://doi.org/10.18653/v1/p19-1146","title":"Sparse Sequence-to-Sequence Models","display_name":"Sparse Sequence-to-Sequence Models","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2950858167","doi":"https://doi.org/10.18653/v1/p19-1146","mag":"2950858167"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1146","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1146","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002087731","display_name":"Ben Peters","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Ben Peters","raw_affiliation_strings":["Instituto de Telecomunicac \u00b8\u00f5es, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunicac \u00b8\u00f5es, Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064085103","display_name":"Vlad Niculae","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Vlad Niculae","raw_affiliation_strings":["Instituto de Telecomunicac \u00b8\u00f5es, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunicac \u00b8\u00f5es, Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051693368","display_name":"Andr\u00e9 F. T. Martins","orcid":"https://orcid.org/0000-0001-8282-625X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 F. T. Martins","raw_affiliation_strings":["Unbabel, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Unbabel, Lisbon, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002087731"],"corresponding_institution_ids":["https://openalex.org/I4210120471"],"apc_list":null,"apc_paid":null,"fwci":13.8757,"has_fulltext":false,"cited_by_count":182,"citation_normalized_percentile":{"value":0.99057705,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1504","last_page":"1519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/softmax-function","display_name":"Softmax function","score":0.8480820655822754},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7528257369995117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6655920743942261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5100463032722473},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5007197856903076},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4900185167789459},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45356059074401855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3843112885951996},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.11692452430725098}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8480820655822754},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7528257369995117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6655920743942261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100463032722473},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5007197856903076},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4900185167789459},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45356059074401855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3843112885951996},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.11692452430725098},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1146","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1146","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W183625566","https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1983874169","https://openalex.org/W2005895359","https://openalex.org/W2017697298","https://openalex.org/W2056385679","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2115807064","https://openalex.org/W2120340025","https://openalex.org/W2133564696","https://openalex.org/W2152808281","https://openalex.org/W2180180824","https://openalex.org/W2251171258","https://openalex.org/W2253795368","https://openalex.org/W2418388682","https://openalex.org/W2467173223","https://openalex.org/W2510905642","https://openalex.org/W2512924740","https://openalex.org/W2550821151","https://openalex.org/W2574872930","https://openalex.org/W2619122421","https://openalex.org/W2625720409","https://openalex.org/W2740599975","https://openalex.org/W2787693176","https://openalex.org/W2889368791","https://openalex.org/W2899302455","https://openalex.org/W2899771611","https://openalex.org/W2904683980","https://openalex.org/W2934842096","https://openalex.org/W2951025380","https://openalex.org/W2952332047","https://openalex.org/W2962784628","https://openalex.org/W2962801832","https://openalex.org/W2962839844","https://openalex.org/W2963062480","https://openalex.org/W2963123301","https://openalex.org/W2963212250","https://openalex.org/W2963403868","https://openalex.org/W2963502387","https://openalex.org/W2963913768","https://openalex.org/W2964095938","https://openalex.org/W2964121744","https://openalex.org/W2964190861","https://openalex.org/W2964308564","https://openalex.org/W3005389111","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2912971006"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"models":[1,36,98],"are":[2,99],"a":[3,11,57,111],"powerful":[4],"workhorse":[5],"of":[6,60,114],"NLP.":[7],"Most":[8],"variants":[9],"employ":[10],"softmax":[12,65],"transformation":[13],"in":[14,56],"both":[15],"their":[16,88],"attention":[17],"mechanism":[18],"and":[19,26,39,66,71,87,105,126],"output":[20,29],"layer,":[21],"leading":[22],"to":[23,43,83,101,106,110],"dense":[24,133],"alignments":[25,104],"strictly":[27],"positive":[28],"probabilities.":[30],"This":[31],"density":[32],"is":[33,72],"wasteful,":[34],"making":[35],"less":[37],"interpretable":[38],"assigning":[40],"probability":[41,109],"mass":[42],"many":[44],"implausible":[45],"outputs.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"sparse":[52,73,103],"sequence-to-sequence":[53],"models,":[54],"rooted":[55],"new":[58],"family":[59],"\ud835\udefc-entmax":[61],"transformations,":[62],"which":[63,90],"includes":[64],"sparsemax":[67],"as":[68],"particular":[69],"cases,":[70],"for":[74,93],"any":[75],"\ud835\udefc":[76],">":[77],"1.":[78],"We":[79],"provide":[80],"fast":[81],"algorithms":[82],"evaluate":[84],"these":[85],"transformations":[86],"gradients,":[89],"scale":[91],"well":[92],"large":[94],"vocabulary":[95],"sizes.":[96],"Our":[97],"able":[100],"produce":[102],"assign":[107],"nonzero":[108],"short":[112],"list":[113],"plausible":[115],"outputs,":[116],"sometimes":[117],"rendering":[118],"beam":[119],"search":[120],"exact.":[121],"Experiments":[122],"on":[123],"morphological":[124],"inflection":[125],"machine":[127],"translation":[128],"reveal":[129],"consistent":[130],"gains":[131],"over":[132],"models.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}