{"id":"https://openalex.org/W2948554505","doi":"https://doi.org/10.18653/v1/w19-4308","title":"Pitfalls in the Evaluation of Sentence Embeddings","display_name":"Pitfalls in the Evaluation of Sentence Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948554505","doi":"https://doi.org/10.18653/v1/w19-4308","mag":"2948554505"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4308","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4308","pdf_url":"https://www.aclweb.org/anthology/W19-4308.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4308.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053947568","display_name":"Steffen Eger","orcid":"https://orcid.org/0000-0003-4663-8336"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Eger","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA)  Research Training Group AIPHES Department of Computer Science, Technische Universitt Darmstadt  www","Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA)  Research Training Group AIPHES Department of Computer Science, Technische Universitt Darmstadt  www","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014688346","display_name":"Andreas R\u00fcckl\u00e9","orcid":"https://orcid.org/0000-0002-4962-0556"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas R\u00fcckl\u00e9","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA)  Research Training Group AIPHES Department of Computer Science, Technische Universitt Darmstadt  www","Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA)  Research Training Group AIPHES Department of Computer Science, Technische Universitt Darmstadt  www","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36578641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T13629","display_name":"Text Readability and Simplification","score":0.9976999759674072,"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/sentence","display_name":"Sentence","score":0.8370010852813721},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7707716226577759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7489002346992493},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6206559538841248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6031408905982971},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5137723684310913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4509418308734894},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35163214802742004}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8370010852813721},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7707716226577759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489002346992493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6206559538841248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6031408905982971},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5137723684310913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4509418308734894},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35163214802742004},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.18653/v1/w19-4308","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4308","pdf_url":"https://www.aclweb.org/anthology/W19-4308.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.01575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01575","pdf_url":"https://arxiv.org/pdf/1906.01575","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,"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":"mag:2948554505","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.01575","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,"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":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:113757","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/113757/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:114538","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/114538/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},{"id":"doi:10.48550/arxiv.1906.01575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.01575","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4308","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4308","pdf_url":"https://www.aclweb.org/anthology/W19-4308.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G3424576390","display_name":null,"funder_award_id":"GRK 1994","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G481299621","display_name":null,"funder_award_id":"GRK 1994/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5741896422","display_name":null,"funder_award_id":"RI 803/12-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6215165406","display_name":null,"funder_award_id":"GU 798/18-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948554505.pdf","grobid_xml":"https://content.openalex.org/works/W2948554505.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2067438047","https://openalex.org/W2088960431","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2295584157","https://openalex.org/W2602024037","https://openalex.org/W2605035112","https://openalex.org/W2752172973","https://openalex.org/W2794557536","https://openalex.org/W2808681756","https://openalex.org/W2881747041","https://openalex.org/W2888159079","https://openalex.org/W2907849599","https://openalex.org/W2914484425","https://openalex.org/W2950726992","https://openalex.org/W2963090765","https://openalex.org/W2963419157","https://openalex.org/W2963532001","https://openalex.org/W2963748792","https://openalex.org/W2963918774","https://openalex.org/W2963940534","https://openalex.org/W2964165804","https://openalex.org/W2964204621","https://openalex.org/W3104033643"],"related_works":["https://openalex.org/W2970958079","https://openalex.org/W1576954243","https://openalex.org/W2892354174","https://openalex.org/W3028659139","https://openalex.org/W2740358059","https://openalex.org/W2962914241","https://openalex.org/W2808681756","https://openalex.org/W3131094205","https://openalex.org/W2724648934","https://openalex.org/W2530085701","https://openalex.org/W2572064709","https://openalex.org/W2997418355","https://openalex.org/W2976980910","https://openalex.org/W2587764909","https://openalex.org/W3105681983","https://openalex.org/W2619688110","https://openalex.org/W3159153780","https://openalex.org/W2963372062","https://openalex.org/W3134551411","https://openalex.org/W2955515572"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"continuously":[3],"break":[4],"new":[5],"records":[6],"across":[7],"different":[8,47],"NLP":[9,37],"tasks.":[10,62],"At":[11],"the":[12,42,53,68],"same":[13],"time,":[14],"their":[15],"success":[16],"exposes":[17],"weaknesses":[18],"of":[19,28,30,44,46,50,71,96],"model":[20],"evaluation.":[21],"Here,":[22],"we":[23,87],"compile":[24],"several":[25],"key":[26],"pitfalls":[27,40],"evaluation":[29,70],"sentence":[31,72,97],"embeddings,":[32,51],"a":[33],"currently":[34],"very":[35],"popular":[36],"paradigm.":[38],"These":[39],"include":[41],"comparison":[43],"embeddings":[45,73],"sizes,":[48],"normalization":[49],"and":[52,60,74],"low":[54],"(and":[55],"diverging)":[56],"correlations":[57],"between":[58],"transfer":[59],"probing":[61],"Our":[63],"motivation":[64],"is":[65],"to":[66,75],"challenge":[67],"current":[69],"provide":[76],"an":[77],"easy-to-access":[78],"reference":[79],"for":[80,92],"future":[81,94],"research.":[82],"Based":[83],"on":[84],"our":[85],"insights,":[86],"also":[88],"recommend":[89],"better":[90,93],"practices":[91],"evaluations":[95],"embeddings.":[98]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
