{"id":"https://openalex.org/W2586148577","doi":"https://doi.org/10.18653/v1/p17-1057","title":"Representations of language in a model of visually grounded speech signal","display_name":"Representations of language in a model of visually grounded speech signal","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2586148577","doi":"https://doi.org/10.18653/v1/p17-1057","mag":"2586148577"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1057","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1057","pdf_url":"https://www.aclweb.org/anthology/P17-1057.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1057.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022698890","display_name":"Grzegorz Chrupa\u0142a","orcid":"https://orcid.org/0000-0001-9498-6912"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Grzegorz Chrupa\u0142a","raw_affiliation_strings":["Tilburg University"],"affiliations":[{"raw_affiliation_string":"Tilburg University","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000074624","display_name":"Lieke Gelderloos","orcid":null},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lieke Gelderloos","raw_affiliation_strings":["Tilburg University"],"affiliations":[{"raw_affiliation_string":"Tilburg University","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047382001","display_name":"Afra Alishahi","orcid":null},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Afra Alishahi","raw_affiliation_strings":["Tilburg University"],"affiliations":[{"raw_affiliation_string":"Tilburg University","institution_ids":["https://openalex.org/I193700539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022698890"],"corresponding_institution_ids":["https://openalex.org/I193700539"],"apc_list":null,"apc_paid":null,"fwci":6.5668,"has_fulltext":true,"cited_by_count":135,"citation_normalized_percentile":{"value":0.97937143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"613","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522540092468262},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6214008927345276},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.602988600730896},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6003929376602173},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5881355404853821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.544836163520813},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5431787371635437},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5380423069000244},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5019180774688721},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.498974084854126},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48551106452941895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46679526567459106},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44465896487236023},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4238082468509674},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3854040503501892},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1465139091014862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522540092468262},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6214008927345276},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.602988600730896},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6003929376602173},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5881355404853821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.544836163520813},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5431787371635437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5380423069000244},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5019180774688721},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.498974084854126},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48551106452941895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46679526567459106},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44465896487236023},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4238082468509674},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3854040503501892},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1465139091014862},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/p17-1057","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1057","pdf_url":"https://www.aclweb.org/anthology/P17-1057.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:tilburguniversity.edu:openaire/3116595c-e8f8-4d60-aa78-0a172ed07654","is_oa":true,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/3116595c-e8f8-4d60-aa78-0a172ed07654","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chrupala, G, Gelderloos, L & Alishahi, A 2017, Representations of language in a model of visually grounded speech signal. in Proceedings of the 55th of the Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pp. 613\u2013622 , Annual Meeting of the Association for Computational Linguistics 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-1057","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1702.01991","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1702.01991","pdf_url":"https://arxiv.org/pdf/1702.01991","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1057","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1057","pdf_url":"https://www.aclweb.org/anthology/P17-1057.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2586148577.pdf","grobid_xml":"https://content.openalex.org/works/W2586148577.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W385555557","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2107917162","https://openalex.org/W2117539524","https://openalex.org/W2123815913","https://openalex.org/W2127438782","https://openalex.org/W2134670479","https://openalex.org/W2137010615","https://openalex.org/W2143623448","https://openalex.org/W2155889433","https://openalex.org/W2160783091","https://openalex.org/W2172888184","https://openalex.org/W2194775991","https://openalex.org/W2250790822","https://openalex.org/W2251861449","https://openalex.org/W2282219577","https://openalex.org/W2292919134","https://openalex.org/W2396384435","https://openalex.org/W2471839888","https://openalex.org/W2473934411","https://openalex.org/W2515741950","https://openalex.org/W2524611247","https://openalex.org/W2531381952","https://openalex.org/W2556930864","https://openalex.org/W2562979205","https://openalex.org/W2580178245","https://openalex.org/W2951674897","https://openalex.org/W2952020226","https://openalex.org/W2953177656","https://openalex.org/W2953188482","https://openalex.org/W2953318193","https://openalex.org/W2962753610","https://openalex.org/W2962776659","https://openalex.org/W2962835968","https://openalex.org/W2962862718","https://openalex.org/W2963899908","https://openalex.org/W2964121744","https://openalex.org/W3213502289","https://openalex.org/W4237938692","https://openalex.org/W4245833664","https://openalex.org/W4294555862","https://openalex.org/W4297826211","https://openalex.org/W4299801216","https://openalex.org/W4394453761"],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W962203960","https://openalex.org/W2026999166","https://openalex.org/W1996802783","https://openalex.org/W2509431957","https://openalex.org/W4211007821","https://openalex.org/W2802395037","https://openalex.org/W4389565704","https://openalex.org/W1976216854","https://openalex.org/W3207031006"],"abstract_inverted_index":{"We":[0,20,52],"present":[1],"a":[2,16,22],"visually":[3],"grounded":[4],"model":[5,28,68],"of":[6,32,58,65,73,86,90,93],"speech":[7],"perception":[8],"which":[9],"projects":[10],"spoken":[11,33],"utterances":[12],"and":[13,35,44,69,101],"images":[14],"to":[15,27,40,77,98],"joint":[17],"semantic":[18,74],"space.":[19],"use":[21],"multi-layer":[23],"recurrent":[24],"highway":[25],"network":[26],"the":[29,49,59,66,84,94],"temporal":[30],"nature":[31],"speech,":[34],"show":[36,70],"that":[37,71],"it":[38],"learns":[39],"extract":[41],"both":[42],"form":[43],"meaningbased":[45],"linguistic":[46],"knowledge":[47],"from":[48],"input":[50,96],"signal.":[51],"carry":[53],"out":[54],"an":[55],"in-depth":[56],"analysis":[57],"representations":[60],"used":[61],"by":[62],"different":[63],"components":[64],"trained":[67],"encoding":[72,89],"aspects":[75,92],"tends":[76,97],"become":[78],"richer":[79],"as":[80],"we":[81],"go":[82],"up":[83],"hierarchy":[85],"layers,":[87],"whereas":[88],"formrelated":[91],"language":[95],"initially":[99],"increase":[100],"then":[102],"plateau":[103],"or":[104],"decrease.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2017-02-17T00:00:00"}
