{"id":"https://openalex.org/W2792389670","doi":"https://doi.org/10.1145/3172944.3173011","title":"Discovering Surprising Documents with Context-Aware Word Representations","display_name":"Discovering Surprising Documents with Context-Aware Word Representations","publication_year":2018,"publication_date":"2018-03-05","ids":{"openalex":"https://openalex.org/W2792389670","doi":"https://doi.org/10.1145/3172944.3173011","mag":"2792389670"},"language":"en","primary_location":{"id":"doi:10.1145/3172944.3173011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3172944.3173011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"23rd International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013422880","display_name":"Micha\u0142 Derezi\u0144ski","orcid":"https://orcid.org/0009-0001-7274-539X"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michal Derezinski","raw_affiliation_strings":["University of California, Santa Cruz, Santa Cruz, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037673735","display_name":"Khashayar Rohanimanesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khashayar Rohanimanesh","raw_affiliation_strings":["eBay Research Labs, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"eBay Research Labs, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063451006","display_name":"Aamer Hydrie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aamer Hydrie","raw_affiliation_strings":["eBay Research Labs, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"eBay Research Labs, San Jose, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013422880"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55897719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/surprise","display_name":"Surprise","score":0.8650593161582947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8523195385932922},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6489672660827637},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6226235628128052},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.615985631942749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6078134179115295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5823991894721985},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48938220739364624},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47160252928733826},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4132618308067322},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07208195328712463}],"concepts":[{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.8650593161582947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523195385932922},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6489672660827637},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6226235628128052},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.615985631942749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6078134179115295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823991894721985},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48938220739364624},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47160252928733826},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4132618308067322},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07208195328712463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3172944.3173011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3172944.3173011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"23rd International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2028602070"],"related_works":["https://openalex.org/W4236382845","https://openalex.org/W4388712630","https://openalex.org/W2481168998","https://openalex.org/W2476994687","https://openalex.org/W642988558","https://openalex.org/W2324507472","https://openalex.org/W2511141457","https://openalex.org/W1999899047","https://openalex.org/W2173353921","https://openalex.org/W1561721581"],"abstract_inverted_index":{"User":[0],"experiences":[1],"can":[2,92],"be":[3,93],"made":[4],"more":[5],"engaging":[6],"by":[7],"incorporating":[8],"surprise.":[9],"For":[10],"example,":[11],"online":[12],"shoppers":[13],"may":[14],"like":[15],"to":[16,95],"view":[17],"unique":[18],"products.":[19],"In":[20],"this":[21],"paper":[22],"we":[23],"propose":[24],"an":[25,61,70],"approach":[26,63,74],"for":[27,48,64,124],"detecting":[28],"surprising":[29,67],"documents,":[30],"such":[31,58],"as":[32],"product":[33],"titles.":[34],"As":[35,104],"the":[36,50,96,101,105,114,117],"concept":[37],"of":[38,53,81,86,107,116,153,161],"surprise":[39],"is":[40,43,75,120],"subjective,":[41],"there":[42],"currently":[44],"no":[45],"principled":[46],"method":[47],"measuring":[49],"surprisingness":[51,169],"score":[52,170],"a":[54,59,78,84,129,151,159],"document.":[55],"We":[56,132],"present":[57],"method;":[60],"unsupervised":[62,140],"automatically":[65],"discovering":[66],"documents":[68,127],"in":[69,99,137],"unlabeled":[71],"corpus.":[72],"Our":[73],"based":[76],"on":[77,146],"probabilistic":[79],"model":[80,109,135],"surprise,":[82],"and":[83,139,158],"construction":[85],"effective":[87],"distributional":[88],"word":[89,102],"embeddings,":[90],"which":[91,100],"adapted":[94],"semantic":[97],"context":[98],"appears.":[103],"performance":[106,145],"our":[108,134,168],"does":[110],"not":[111],"degrade":[112],"with":[113,174],"length":[115],"document,":[118],"it":[119],"particularly":[121],"well":[122],"suited":[123],"very":[125],"short":[126],"(even":[128],"single":[130],"sentence).":[131],"evaluate":[133],"both":[136],"supervised":[138],"settings,":[141],"demonstrating":[142],"its":[143],"state-of-the-art":[144],"two":[147],"real-world":[148],"data":[149],"sets:":[150],"collection":[152],"e-commerce":[154],"products":[155],"from":[156],"eBay,":[157],"corpus":[160],"NSF":[162],"proposals.":[163],"These":[164],"experiments":[165],"show":[166],"that":[167],"exhibits":[171],"high":[172],"correlation":[173],"human":[175],"annotated":[176],"labels.":[177]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}