{"id":"https://openalex.org/W2964263959","doi":"https://doi.org/10.18653/v1/p18-1173","title":"Backpropagating through Structured Argmax using a SPIGOT","display_name":"Backpropagating through Structured Argmax using a SPIGOT","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2964263959","doi":"https://doi.org/10.18653/v1/p18-1173","mag":"2964263959"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1173","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1173","pdf_url":"https://www.aclweb.org/anthology/P18-1173.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 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1173.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100740618","display_name":"Hao Peng","orcid":"https://orcid.org/0000-0001-7422-630X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"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":"Hao Peng","raw_affiliation_strings":["School of Computer Science & Engineering, University of Washington \u2663 School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington \u2663 School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048087523","display_name":"Sam Thomson","orcid":"https://orcid.org/0009-0004-3099-5050"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"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":"Sam Thomson","raw_affiliation_strings":["School of Computer Science & Engineering, University of Washington  School of Computer Science, Carnegie Mellon University","School of Computer Science & Engineering, University of Washington \u2663 School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington  School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington \u2663 School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088517824","display_name":"Noah A. Smith","orcid":"https://orcid.org/0000-0002-2310-6380"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"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":"Noah A. Smith","raw_affiliation_strings":["School of Computer Science & Engineering, University of Washington  School of Computer Science, Carnegie Mellon University","School of Computer Science & Engineering, University of Washington \u2663 School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington  School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington \u2663 School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5086,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94939789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1863","last_page":"1873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"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":0.8907352089881897},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.7500914335250854},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7065808773040771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6567448973655701},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6276441216468811},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6167562007904053},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.6034559011459351},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4846980571746826},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.44446611404418945},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4366070330142975},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4291606843471527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4283254146575928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33821436762809753},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.267541766166687},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14029377698898315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8907352089881897},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.7500914335250854},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7065808773040771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6567448973655701},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6276441216468811},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6167562007904053},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6034559011459351},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4846980571746826},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.44446611404418945},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4366070330142975},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4291606843471527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4283254146575928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33821436762809753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.267541766166687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14029377698898315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1173","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1173","pdf_url":"https://www.aclweb.org/anthology/P18-1173.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 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1173","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1173","pdf_url":"https://www.aclweb.org/anthology/P18-1173.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 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G7750423253","display_name":null,"funder_award_id":"IIS-1562364","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8533175095","display_name":"RI: Medium: Broad-Coverage Semantic Parsing: Linguistic Representation Learning from Crowd-Scale Data","funder_award_id":"1562364","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964263959.pdf","grobid_xml":"https://content.openalex.org/works/W2964263959.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W237364718","https://openalex.org/W1517853909","https://openalex.org/W1566346388","https://openalex.org/W1586368951","https://openalex.org/W1592580816","https://openalex.org/W1632114991","https://openalex.org/W1676470423","https://openalex.org/W1762430620","https://openalex.org/W1970163214","https://openalex.org/W1978119584","https://openalex.org/W2047706513","https://openalex.org/W2052449326","https://openalex.org/W2098617596","https://openalex.org/W2100976324","https://openalex.org/W2117130368","https://openalex.org/W2126176114","https://openalex.org/W2130391193","https://openalex.org/W2131698806","https://openalex.org/W2143170264","https://openalex.org/W2148862211","https://openalex.org/W2158108973","https://openalex.org/W2162258831","https://openalex.org/W2186629860","https://openalex.org/W2187061624","https://openalex.org/W2189472871","https://openalex.org/W2242818861","https://openalex.org/W2250473257","https://openalex.org/W2251495238","https://openalex.org/W2251939518","https://openalex.org/W2253795368","https://openalex.org/W2266946488","https://openalex.org/W2293517743","https://openalex.org/W2296260950","https://openalex.org/W2301095666","https://openalex.org/W2311095070","https://openalex.org/W2397198482","https://openalex.org/W2423636506","https://openalex.org/W2429412974","https://openalex.org/W2429914308","https://openalex.org/W2505728881","https://openalex.org/W2516255829","https://openalex.org/W2547875792","https://openalex.org/W2556468274","https://openalex.org/W2577255746","https://openalex.org/W2579057432","https://openalex.org/W2586050494","https://openalex.org/W2586597293","https://openalex.org/W2613332842","https://openalex.org/W2619122421","https://openalex.org/W2728192282","https://openalex.org/W2736296425","https://openalex.org/W2740765036","https://openalex.org/W2765185632","https://openalex.org/W2787063232","https://openalex.org/W2787693176","https://openalex.org/W2949847915","https://openalex.org/W2950415592","https://openalex.org/W2962731964","https://openalex.org/W2962836003","https://openalex.org/W2963123301","https://openalex.org/W2963355447","https://openalex.org/W2963451457","https://openalex.org/W2963479222","https://openalex.org/W2963502387","https://openalex.org/W2963851958","https://openalex.org/W2963872035","https://openalex.org/W2963899396","https://openalex.org/W2963970238","https://openalex.org/W2964015378","https://openalex.org/W2964076774","https://openalex.org/W2964084097","https://openalex.org/W2964095938","https://openalex.org/W2964113829","https://openalex.org/W2964205912","https://openalex.org/W2964217331","https://openalex.org/W3004985245","https://openalex.org/W4230563027","https://openalex.org/W4241738801","https://openalex.org/W4292230442","https://openalex.org/W4293316651","https://openalex.org/W4293541669","https://openalex.org/W4293652773","https://openalex.org/W4293865263","https://openalex.org/W4301496368"],"related_works":["https://openalex.org/W2251084681","https://openalex.org/W2098784136","https://openalex.org/W4241489294","https://openalex.org/W287510790","https://openalex.org/W3117798239","https://openalex.org/W63925617","https://openalex.org/W2968543375","https://openalex.org/W4288558800","https://openalex.org/W2888625260","https://openalex.org/W2953770453"],"abstract_inverted_index":{"We":[0],"introduce":[1],"the":[2,69],"structured":[3,22,35],"projection":[4],"of":[5],"intermediate":[6,27,50,70],"gradients":[7],"optimization":[8],"technique":[9],"(SPIGOT),":[10],"a":[11,66],"new":[12],"method":[13],"for":[14],"backpropagating":[15],"through":[16],"neural":[17],"networks":[18,37],"that":[19],"include":[20],"hard-decision":[21],"predictions":[23],"(e.g.,":[24],"parsing)":[25],"in":[26],"layers.":[28],"SPIGOT":[29,44],"requires":[30],"no":[31],"marginal":[32],"inference,":[33],"unlike":[34],"attention":[36],"Like":[38],"socalled":[39],"straight-through":[40],"estimators":[41],"(Hinton,":[42],"2012),":[43],"defines":[45],"gradient-like":[46],"quantities":[47],"associated":[48],"with":[49],"nondifferentiable":[51],"operations,":[52],"allowing":[53],"backpropagation":[54],"before":[55],"and":[56],"after":[57,65],"them;":[58],"SPIGOT's":[59],"proxy":[60],"aims":[61],"to":[62],"ensure":[63],"that,":[64],"parameter":[67],"update,":[68],"structure":[71],"will":[72],"remain":[73],"well-formed.":[74]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}