{"id":"https://openalex.org/W2799231549","doi":"https://doi.org/10.18653/v1/p18-2059","title":"Sparse and Constrained Attention for Neural Machine Translation","display_name":"Sparse and Constrained Attention for Neural Machine Translation","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2799231549","doi":"https://doi.org/10.18653/v1/p18-2059","mag":"2799231549"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2059","pdf_url":"https://www.aclweb.org/anthology/P18-2059.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","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/P18-2059.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037500486","display_name":"Chaitanya Malaviya","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chaitanya Malaviya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085854894","display_name":"Pedro Ferreira","orcid":"https://orcid.org/0000-0003-2369-0115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Ferreira","raw_affiliation_strings":[],"affiliations":[]},{"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":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037500486"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.59568738,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7182913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"370","last_page":"376"},"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":0.9990000128746033,"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":0.9866999983787537,"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/computer-science","display_name":"Computer science","score":0.6862831711769104},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6456164717674255},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6012622714042664},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5668647289276123},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5645109415054321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5182373523712158},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5129527449607849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3645555377006531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3631601929664612},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16818436980247498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6862831711769104},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6456164717674255},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6012622714042664},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5668647289276123},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5645109415054321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182373523712158},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5129527449607849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3645555377006531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3631601929664612},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16818436980247498},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/p18-2059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2059","pdf_url":"https://www.aclweb.org/anthology/P18-2059.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.08241","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.08241","pdf_url":"https://arxiv.org/pdf/1805.08241","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:2799231549","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1805.08241","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.1805.08241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.08241","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2059","pdf_url":"https://www.aclweb.org/anthology/P18-2059.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2799231549.pdf","grobid_xml":"https://content.openalex.org/works/W2799231549.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1996641400","https://openalex.org/W2006969979","https://openalex.org/W2061211758","https://openalex.org/W2252239149","https://openalex.org/W2410539690","https://openalex.org/W2552838200","https://openalex.org/W2552839021","https://openalex.org/W2574872930","https://openalex.org/W2576713500","https://openalex.org/W2619353065","https://openalex.org/W2625092622","https://openalex.org/W2626778328","https://openalex.org/W2949335953","https://openalex.org/W2949888546","https://openalex.org/W2963123301","https://openalex.org/W2963699608","https://openalex.org/W2964298349","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2997517014","https://openalex.org/W2971524460","https://openalex.org/W3136302691","https://openalex.org/W3214537789","https://openalex.org/W2756303778","https://openalex.org/W2257123346","https://openalex.org/W2988880832","https://openalex.org/W2787108264","https://openalex.org/W2980170136","https://openalex.org/W3154414470","https://openalex.org/W2682503061","https://openalex.org/W3213169547","https://openalex.org/W3021335241","https://openalex.org/W1605608070","https://openalex.org/W2804243936","https://openalex.org/W3017357710","https://openalex.org/W2614371818","https://openalex.org/W3177343494","https://openalex.org/W2997512706","https://openalex.org/W2899189400"],"abstract_inverted_index":{"In":[0],"NMT,":[1],"words":[2],"are":[3],"sometimes":[4],"dropped":[5],"from":[6],"the":[7,13,21,27,40],"source":[8,35],"or":[9],"generated":[10],"repeatedly":[11],"in":[12,72],"translation.":[14],"We":[15,46],"explore":[16],"novel":[17],"strategies":[18],"to":[19,34,38,63],"address":[20],"coverage":[22],"problem":[23],"that":[24],"change":[25],"only":[26],"attention":[28,41,53],"transformation.":[29],"Our":[30],"approach":[31],"allocates":[32],"fertilities":[33],"words,":[36],"used":[37],"bound":[39],"each":[42],"word":[43],"can":[44],"receive.":[45],"experiment":[47],"with":[48],"various":[49],"sparse":[50],"and":[51,55,66],"constrained":[52,60],"transformations":[54],"propose":[56],"a":[57],"new":[58],"one,":[59],"sparsemax,":[61],"shown":[62],"be":[64],"differentiable":[65],"sparse.":[67],"Empirical":[68],"evaluation":[69],"is":[70],"provided":[71],"three":[73],"languages":[74],"pairs.":[75]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}