{"id":"https://openalex.org/W3166336242","doi":"https://doi.org/10.1145/3447548.3467392","title":"NewsEmbed: Modeling News through Pre-trained Document Representations","display_name":"NewsEmbed: Modeling News through Pre-trained Document Representations","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3166336242","doi":"https://doi.org/10.1145/3447548.3467392","mag":"3166336242"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467392","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467392","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101681241","display_name":"Jialu Liu","orcid":"https://orcid.org/0000-0002-8962-309X"},"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":"Jialu Liu","raw_affiliation_strings":["Google Research, New York City, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, New York City, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618135","display_name":"Tianqi Liu","orcid":"https://orcid.org/0000-0002-0224-045X"},"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":"Tianqi Liu","raw_affiliation_strings":["Google Research, New York City, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, New York City, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043275971","display_name":"Cong Yu","orcid":"https://orcid.org/0000-0001-7331-2345"},"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":"Cong Yu","raw_affiliation_strings":["Google Research, New York City, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, New York City, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.9052,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88421515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1076","last_page":"1086"},"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":0.9988999962806702,"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":0.9986000061035156,"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":0.8456531763076782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5477253794670105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5277351140975952},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5228279829025269},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4764680862426758},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46663743257522583},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4501473903656006},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4413760006427765},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4350457787513733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456531763076782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5477253794670105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5277351140975952},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5228279829025269},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4764680862426758},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46663743257522583},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4501473903656006},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4413760006427765},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4350457787513733},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467392","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467392","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.00590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.00590","pdf_url":"https://arxiv.org/pdf/2106.00590","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"}],"best_oa_location":{"id":"doi:10.1145/3447548.3467392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467392","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467392","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3166336242.pdf","grobid_xml":"https://content.openalex.org/works/W3166336242.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W33276683","https://openalex.org/W168564468","https://openalex.org/W1503398984","https://openalex.org/W1775434803","https://openalex.org/W1840435438","https://openalex.org/W1880262756","https://openalex.org/W1980776243","https://openalex.org/W2033403400","https://openalex.org/W2087294982","https://openalex.org/W2109376948","https://openalex.org/W2110443819","https://openalex.org/W2129250947","https://openalex.org/W2131953535","https://openalex.org/W2149684865","https://openalex.org/W2153579005","https://openalex.org/W2170240176","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2284289336","https://openalex.org/W2410465342","https://openalex.org/W2493916176","https://openalex.org/W2507974895","https://openalex.org/W2509893387","https://openalex.org/W2614237344","https://openalex.org/W2626778328","https://openalex.org/W2739351760","https://openalex.org/W2741943936","https://openalex.org/W2742272831","https://openalex.org/W2759820691","https://openalex.org/W2790235966","https://openalex.org/W2842511635","https://openalex.org/W2885580742","https://openalex.org/W2890798167","https://openalex.org/W2891177506","https://openalex.org/W2896457183","https://openalex.org/W2899204128","https://openalex.org/W2914120296","https://openalex.org/W2937423263","https://openalex.org/W2949691979","https://openalex.org/W2950133940","https://openalex.org/W2950416834","https://openalex.org/W2962739339","https://openalex.org/W2963012544","https://openalex.org/W2963204221","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963846996","https://openalex.org/W2964165804","https://openalex.org/W2970618241","https://openalex.org/W2970641574","https://openalex.org/W2973088264","https://openalex.org/W2981852735","https://openalex.org/W2987656486","https://openalex.org/W2996064239","https://openalex.org/W3005296017","https://openalex.org/W3005680577","https://openalex.org/W3013840636","https://openalex.org/W3024786184","https://openalex.org/W3026732421","https://openalex.org/W3030163527","https://openalex.org/W3030506520","https://openalex.org/W3031781733","https://openalex.org/W3034238904","https://openalex.org/W3034503922","https://openalex.org/W3034696692","https://openalex.org/W3034781633","https://openalex.org/W3034978746","https://openalex.org/W3035060554","https://openalex.org/W3035390927","https://openalex.org/W3035524453","https://openalex.org/W3035579820","https://openalex.org/W3039695075","https://openalex.org/W3082274269","https://openalex.org/W3093517588","https://openalex.org/W3096655658","https://openalex.org/W3100407497","https://openalex.org/W3104033643","https://openalex.org/W3105625590","https://openalex.org/W3210120707","https://openalex.org/W4244030505","https://openalex.org/W4288089799","https://openalex.org/W6600466347","https://openalex.org/W6605862995","https://openalex.org/W6630177651","https://openalex.org/W6639619044","https://openalex.org/W6679554340"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Effectively":[0],"modeling":[1],"text-rich":[2],"fresh":[3,65],"content":[4],"such":[5],"as":[6],"news":[7],"articles":[8],"at":[9],"document-level":[10],"is":[11,29,37],"a":[12,17,23,33,59,78,86,90,95],"challenging":[13],"problem.":[14],"To":[15],"ensure":[16],"content-based":[18],"model":[19,80],"generalize":[20],"well":[21],"to":[22,31,62,93,119],"broad":[24],"range":[25],"of":[26,42,108],"applications,":[27],"it":[28],"critical":[30],"have":[32],"training":[34,112],"dataset":[35],"that":[36,83,101],"large":[38],"beyond":[39],"the":[40,102,130],"scale":[41],"human":[43,73],"labels":[44],"while":[45],"achieving":[46],"desired":[47],"quality.":[48],"In":[49],"this":[50],"work,":[51],"we":[52,76],"address":[53],"those":[54],"two":[55],"challenges":[56],"by":[57],"proposing":[58],"novel":[60],"approach":[61,104],"mine":[63],"semantically-relevant":[64],"documents,":[66],"and":[67,114,148],"their":[68],"topic":[69],"labels,":[70],"with":[71,89],"little":[72],"supervision.":[74],"Meanwhile,":[75],"design":[77],"multitask":[79],"called":[81],"NewsEmbed":[82],"alternatively":[84],"trains":[85],"contrastive":[87],"learning":[88],"multi-label":[91],"classification":[92],"derive":[94],"universal":[96],"document":[97],"encoder.":[98],"We":[99,134],"show":[100],"proposed":[103],"can":[105,115],"provide":[106],"billions":[107],"high":[109],"quality":[110],"organic":[111],"examples":[113],"be":[116],"naturally":[117],"extended":[118],"multilingual":[120],"setting":[121],"where":[122],"texts":[123],"in":[124,129],"different":[125],"languages":[126],"are":[127],"encoded":[128],"same":[131],"semantic":[132],"space.":[133],"experimentally":[135],"demonstrate":[136],"NewsEmbed's":[137],"competitive":[138],"performance":[139],"across":[140],"multiple":[141],"natural":[142],"language":[143],"understanding":[144],"tasks,":[145],"both":[146],"supervised":[147],"unsupervised.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}