{"id":"https://openalex.org/W2963013168","doi":"https://doi.org/10.48550/arxiv.1812.08718","title":"RNNs Implicitly Implement Tensor Product Representations","display_name":"RNNs Implicitly Implement Tensor Product Representations","alternate_titles":[],"publication_year":2018,"publication_date":"2018-12-20","ids":{"openalex":"https://openalex.org/W2963013168","doi":"https://doi.org/10.48550/arxiv.1812.08718","mag":"2963013168"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1812.08718","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.08718","pdf_url":"https://arxiv.org/pdf/1812.08718","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"parent_works":[],"lineage":["https://openalex.org/W2963013168"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.08718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003082850","display_name":"Richard Thomas McCoy","orcid":"https://orcid.org/0000-0001-9383-4079","observed_orcids":["https://orcid.org/0000-0001-9383-4079"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"McCoy, R. Thomas","raw_affiliation_strings":["Department of Cognitive Science , Johns Hopkins University","JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Science , Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081824828","display_name":"Tal Linzen","orcid":"https://orcid.org/0000-0003-0435-6912","observed_orcids":["https://orcid.org/0000-0003-0435-6912"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linzen, Tal","raw_affiliation_strings":["Department of Cognitive Science , Johns Hopkins University","JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Science , Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069239428","display_name":"Ewan Dunbar","orcid":"https://orcid.org/0000-0001-9603-953X","observed_orcids":["https://orcid.org/0000-0001-9603-953X"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I204730241","https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I4210114212","display_name":"Laboratoire de Linguistique Formelle","ror":"https://ror.org/0223bz716","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210114212","https://openalex.org/I4210150854"]},{"id":"https://openalex.org/I4387154366","display_name":"Universit\u00e9 Paris Diderot","ror":"https://ror.org/02n7qrg46","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241","https://openalex.org/I4387154366"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dunbar, Ewan","raw_affiliation_strings":["Laboratoire de Linguistique Formelle , CNRS - Universit\u00e9 Paris Diderot -Sorbonne Paris Cit\u00e9","CoML - Apprentissage machine et d\u00e9veloppement cognitif (France)","LLF - UMR7110 - Laboratoire de Linguistique Formelle (8 Rue Albert Einstein, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de Linguistique Formelle , CNRS - Universit\u00e9 Paris Diderot -Sorbonne Paris Cit\u00e9","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4210091437","https://openalex.org/I4210114212","https://openalex.org/I4387154366"]},{"raw_affiliation_string":"CoML - Apprentissage machine et d\u00e9veloppement cognitif (France)","institution_ids":[]},{"raw_affiliation_string":"LLF - UMR7110 - Laboratoire de Linguistique Formelle (8 Rue Albert Einstein, 75013 Paris - France)","institution_ids":["https://openalex.org/I4210114212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088217655","display_name":"Paul Smolensky","orcid":"https://orcid.org/0000-0003-2420-182X","observed_orcids":["https://orcid.org/0000-0003-2420-182X"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Smolensky, Paul","raw_affiliation_strings":["Department of Cognitive Science , Johns Hopkins University","Microsoft Research AI , Redmond , WA USA","JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)","Microsoft Research [Redmond] (One Microsoft Way Redmond, WA 98052-6399 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Science , Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Microsoft Research AI , Redmond , WA USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Microsoft Research [Redmond] (One Microsoft Way Redmond, WA 98052-6399 - United States)","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6859999895095825,"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":0.6859999895095825,"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/T10320","display_name":"Neural Networks and Applications","score":0.19099999964237213,"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":0.01640000008046627,"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/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.9700000286102295},{"id":"https://openalex.org/keywords/tensor-products-of-representations","display_name":"tensor product representations","score":0.9850000143051147},{"id":"https://openalex.org/keywords/compositional-representations","display_name":"compositional representations","score":0.7459999918937683},{"id":"https://openalex.org/keywords/vector-representation","display_name":"vector representation","score":0.4269999861717224},{"id":"https://openalex.org/keywords/analogy","display_name":"analogy","score":0.5640000104904175},{"id":"https://openalex.org/keywords/sentence-representation-learning","display_name":"sentence representation learning","score":0.765999972820282},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6589999794960022},{"id":"https://openalex.org/keywords/symbolic-structures","display_name":"symbolic structures","score":0.41200000047683716},{"id":"https://openalex.org/keywords/bag-of-words","display_name":"bag-of-words","score":0.7049999833106995}],"concepts":[{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.6448273062705994},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.593798816204071},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5524269938468933},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5294420719146729},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5103713870048523},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5008046627044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4818890690803528},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4516751170158386},{"id":"https://openalex.org/C180623205","wikidata":"https://www.wikidata.org/wiki/Q1268589","display_name":"Outer product","level":3,"score":0.4231819212436676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.422821581363678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3690589964389801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34482836723327637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.276078462600708},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.18893656134605408},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1812.08718","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.08718","pdf_url":"https://arxiv.org/pdf/1812.08718","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"pmh:oai:HAL:hal-02274498v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-02274498","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICLR 2019 - International Conference on Learning Representations, May 2019, New Orleans, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1812.08718","doi":"https://doi.org/10.48550/arxiv.1812.08718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.08718","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.08718","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.08718","pdf_url":"https://arxiv.org/pdf/1812.08718","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2339331049","display_name":"Empirical Foundations of Linguistics : data, methods, models","funder_award_id":"ANR-10-LABX-0083","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G2658974192","display_name":"Paris Sciences et Lettres","funder_award_id":"ANR-10-IDEX-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4426423708","display_name":null,"funder_award_id":"ANR-11- IDEX-0005","funder_id":"https://openalex.org/F4320325834","funder_display_name":"Universit\u00e9 Sorbonne Paris Cit\u00e9"},{"id":"https://openalex.org/G5268781400","display_name":"Speech perception and learning in the geometric typology of phonological inventories","funder_award_id":"ANR-17-CE28-0009","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5280230632","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1746891","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5397893844","display_name":"Institute of Cognitive Studies of Ecole normale superieure","funder_award_id":"ANR-10-LABX-0087","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G782245399","display_name":null,"funder_award_id":"IDEX-0001-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8336719376","display_name":"Universit\u00e9 Sorbonne Paris Cit\u00e9","funder_award_id":"ANR-11-IDEX-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8890336727","display_name":"INSPIRE Track 1:  Gradient Symbolic Computation","funder_award_id":"1344269","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"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320325834","display_name":"Universit\u00e9 Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963013168.pdf","grobid_xml":"https://content.openalex.org/works/W2963013168.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1840435438","https://openalex.org/W1971844566","https://openalex.org/W1980776243","https://openalex.org/W2007251230","https://openalex.org/W2013494846","https://openalex.org/W2051394476","https://openalex.org/W2053987251","https://openalex.org/W2062183687","https://openalex.org/W2100779717","https://openalex.org/W2104246439","https://openalex.org/W2105724942","https://openalex.org/W2118373646","https://openalex.org/W2123923307","https://openalex.org/W2130259898","https://openalex.org/W2130666447","https://openalex.org/W2130942839","https://openalex.org/W2131691213","https://openalex.org/W2131774270","https://openalex.org/W2138451337","https://openalex.org/W2141599568","https://openalex.org/W2157306293","https://openalex.org/W2157331557","https://openalex.org/W2170653751","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2292919134","https://openalex.org/W2308720496","https://openalex.org/W2324076434","https://openalex.org/W2413794162","https://openalex.org/W2525332836","https://openalex.org/W2549835527","https://openalex.org/W2563574619","https://openalex.org/W2605717780","https://openalex.org/W2612953412","https://openalex.org/W2626778328","https://openalex.org/W2739351760","https://openalex.org/W2770406504","https://openalex.org/W2786028390","https://openalex.org/W2786865417","https://openalex.org/W2787237356","https://openalex.org/W2788124503","https://openalex.org/W2798905273","https://openalex.org/W2805516822","https://openalex.org/W2856110280","https://openalex.org/W2891585150","https://openalex.org/W2898996181","https://openalex.org/W2952467640","https://openalex.org/W2963090675","https://openalex.org/W2963888305","https://openalex.org/W2964121744","https://openalex.org/W2964165804","https://openalex.org/W2984488235","https://openalex.org/W7099875597"],"related_works":["https://openalex.org/W2891585150","https://openalex.org/W2996725261","https://openalex.org/W2980827866","https://openalex.org/W2984488235","https://openalex.org/W2619959423","https://openalex.org/W2188000357","https://openalex.org/W2898996181","https://openalex.org/W4415724501","https://openalex.org/W2963688311","https://openalex.org/W4404752287"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2],"(RNNs)":[3],"can":[4,91,137,170],"learn":[5],"continuous":[6],"vector":[7,82,164],"representations":[8,18,42,103,128,174],"of":[9,51,129,144],"symbolic":[10,37],"structures":[11,38],"such":[12,33,117],"as":[13],"sequences":[14],"and":[15,58,95,166],"sentences;":[16],"these":[17,102],"often":[19],"exhibit":[20,104],"linear":[21,94],"regularities":[22,25,34],"(analogies).":[23],"Such":[24],"motivate":[26],"our":[27],"hypothesis":[28],"that":[29,31,89,101,112,126,156,167,175],"RNNs":[30,114,169],"show":[32,125],"implicitly":[35],"compile":[36],"into":[39],"tensor":[40,49],"product":[41],"(TPRs;":[43],"Smolensky,":[44],"1990),":[45],"which":[46,76],"additively":[47],"combine":[48],"products":[50],"vectors":[52,59],"representing":[53,60],"roles":[54],"(e.g.,":[55,62],"sequence":[56,173],"positions)":[57],"fillers":[61],"particular":[63],"words).":[64],"To":[65],"test":[66],"this":[67],"hypothesis,":[68],"we":[69,108],"introduce":[70],"Tensor":[71],"Product":[72],"Decomposition":[73],"Networks":[74],"(TPDNs),":[75],"use":[77],"TPRs":[78],"to":[79,115,133],"approximate":[80,93],"existing":[81,186],"representations.":[83,119,201],"We":[84,154],"demonstrate":[85],"using":[86],"synthetic":[87],"data":[88],"TPDNs":[90,157],"successfully":[92],"tree-based":[96],"RNN":[97],"autoencoder":[98],"representations,":[99,165],"suggesting":[100],"interpretable":[105],"compositional":[106,172],"structure;":[107],"explore":[109],"the":[110,127,183],"settings":[111],"lead":[113],"induce":[116,171],"structure-sensitive":[118],"By":[120],"contrast,":[121],"further":[122],"TPDN":[123],"experiments":[124],"four":[130],"models":[131],"trained":[132],"encode":[134],"naturally-occurring":[135],"sentences":[136],"be":[138,195],"largely":[139],"approximated":[140,179],"with":[141,146],"a":[142,159],"bag":[143],"words,":[145],"only":[147],"marginal":[148],"improvements":[149],"from":[150],"more":[151],"sophisticated":[152],"structures.":[153],"conclude":[155],"provide":[158],"powerful":[160],"method":[161],"for":[162,189,197],"interpreting":[163],"standard":[168],"are":[176],"remarkably":[177],"well":[178],"by":[180],"TPRs;":[181],"at":[182],"same":[184],"time,":[185],"training":[187],"tasks":[188],"sentence":[190],"representation":[191],"learning":[192],"may":[193],"not":[194],"sufficient":[196],"inducing":[198],"robust":[199],"structural":[200]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2963013168","counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6}],"updated_date":"2026-11-17T12:49:18.490984","created_date":"2019-07-30T00:00:00"}
