{"id":"https://openalex.org/W4383175703","doi":"https://doi.org/10.1145/3580305.3599907","title":"SMILE: Evaluation and Domain Adaptation for Social Media Language Understanding","display_name":"SMILE: Evaluation and Domain Adaptation for Social Media Language Understanding","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4383175703","doi":"https://doi.org/10.1145/3580305.3599907"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.00135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000704130","display_name":"Vasilisa Bashlovkina","orcid":"https://orcid.org/0009-0005-0235-304X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vasilisa Bashlovkina","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512282","display_name":"R.E.F. MATTHEWS","orcid":"https://orcid.org/0009-0000-7634-7076"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riley Matthews","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039049453","display_name":"Zhaobin Kuang","orcid":"https://orcid.org/0000-0001-9295-4669"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaobin Kuang","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106425585","display_name":"Simon Baumgartner","orcid":"https://orcid.org/0009-0005-8746-5787"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Baumgartner","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032248436","display_name":"Michael Bendersky","orcid":"https://orcid.org/0000-0002-2941-6240"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bendersky","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000704130"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.5219,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70843198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3737","last_page":"3749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9847000241279602,"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":0.9739999771118164,"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/computer-science","display_name":"Computer science","score":0.7794108390808105},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.7087636590003967},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6312589049339294},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5970176458358765},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5265329480171204},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5254351496696472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4851847290992737},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4750211834907532},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45929139852523804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4557880461215973},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44967299699783325},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22870498895645142},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16865134239196777},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08089068531990051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794108390808105},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7087636590003967},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6312589049339294},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5970176458358765},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5265329480171204},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5254351496696472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4851847290992737},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4750211834907532},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45929139852523804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4557880461215973},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44967299699783325},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22870498895645142},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16865134239196777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08089068531990051},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580305.3599907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2307.00135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.00135","pdf_url":"https://arxiv.org/pdf/2307.00135","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.00135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.00135","pdf_url":"https://arxiv.org/pdf/2307.00135","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383175703.pdf","grobid_xml":"https://content.openalex.org/works/W4383175703.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1664671319","https://openalex.org/W2154652894","https://openalex.org/W2170240176","https://openalex.org/W2257408573","https://openalex.org/W2531638282","https://openalex.org/W2573266127","https://openalex.org/W2591697267","https://openalex.org/W2752843002","https://openalex.org/W2803361751","https://openalex.org/W2809005566","https://openalex.org/W2896457183","https://openalex.org/W2897160652","https://openalex.org/W2899386490","https://openalex.org/W2920807444","https://openalex.org/W2923014074","https://openalex.org/W2943552823","https://openalex.org/W2945145546","https://openalex.org/W2963250244","https://openalex.org/W2963748441","https://openalex.org/W2965373594","https://openalex.org/W2970771982","https://openalex.org/W2997929389","https://openalex.org/W3001279689","https://openalex.org/W3016240002","https://openalex.org/W3031498513","https://openalex.org/W3034323190","https://openalex.org/W3046375318","https://openalex.org/W3085139254","https://openalex.org/W3099215402","https://openalex.org/W3104186312","https://openalex.org/W3129493035","https://openalex.org/W3130335560","https://openalex.org/W3164045210","https://openalex.org/W3169483174","https://openalex.org/W3170325272","https://openalex.org/W3171460770","https://openalex.org/W3174418826","https://openalex.org/W3190965961","https://openalex.org/W3195577433","https://openalex.org/W3209409148","https://openalex.org/W3212559860","https://openalex.org/W4211148787","https://openalex.org/W4214823418","https://openalex.org/W4224308101","https://openalex.org/W4224442590","https://openalex.org/W4226399820","https://openalex.org/W4281690148","https://openalex.org/W4281758439","https://openalex.org/W4287200699","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4296405183","https://openalex.org/W4297253404","https://openalex.org/W4300466035","https://openalex.org/W4309793872","https://openalex.org/W4312220150","https://openalex.org/W4321593177","https://openalex.org/W4378189609","https://openalex.org/W4385245566","https://openalex.org/W4385573158"],"related_works":["https://openalex.org/W4304700937","https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223"],"abstract_inverted_index":{"We":[0,41],"study":[1],"the":[2,43,57,115,123],"ability":[3],"of":[4,29,64,69,104],"transformer-based":[5],"language":[6,17,49,53,109],"models":[7],"(LMs)":[8],"to":[9,45],"understand":[10],"social":[11,47,105],"media":[12,15,48,106],"language.":[13],"Social":[14,79],"(SM)":[16],"is":[18,59],"distinct":[19],"from":[20,51],"standard":[21],"written":[22],"language,":[23],"yet":[24],"existing":[25],"benchmarks":[26],"fall":[27],"short":[28],"capturing":[30],"LM":[31,112],"performance":[32],"in":[33,62],"this":[34],"socially,":[35],"economically,":[36],"and":[37,54,67,89,99,107],"politically":[38],"important":[39],"domain.":[40],"quantify":[42],"degree":[44],"which":[46],"differs":[50],"conventional":[52,108],"conclude":[55],"that":[56,84,95,113],"difference":[58],"significant":[60],"both":[61],"terms":[63],"token":[65],"distribution":[66],"rate":[68],"linguistic":[70],"shift.":[71],"Next,":[72],"we":[73,93],"introduce":[74],"a":[75,97,102],"new":[76],"benchmark":[77],"for":[78],"MedIa":[80],"Language":[81],"Evaluation":[82],"(SMILE)":[83],"covers":[85],"four":[86],"SM":[87],"platforms":[88],"eleven":[90],"tasks.":[91],"Finally,":[92],"show":[94],"learning":[96],"tokenizer":[98],"pretraining":[100],"on":[101,122],"mix":[103],"yields":[110],"an":[111],"outperforms":[114],"best":[116],"similar-sized":[117],"alternative":[118],"by":[119],"4.2":[120],"points":[121],"overall":[124],"SMILE":[125],"score.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}