{"id":"https://openalex.org/W2250385510","doi":"https://doi.org/10.18653/v1/d15-1067","title":"Online Sentence Novelty Scoring for Topical Document Streams","display_name":"Online Sentence Novelty Scoring for Topical Document Streams","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250385510","doi":"https://doi.org/10.18653/v1/d15-1067","mag":"2250385510"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1067","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1067","pdf_url":"https://www.aclweb.org/anthology/D15-1067.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D15-1067.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100720086","display_name":"Sung\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-9348-8356"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sungjin Lee","raw_affiliation_strings":["Yahoo Labs 229 West 43rd Street, New York, NY 10036, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Labs 229 West 43rd Street, New York, NY 10036, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100720086"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"567","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980000257492065,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.870520830154419},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.8623579740524292},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6324517726898193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6056409478187561},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5968758463859558},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5814774036407471},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5619955062866211},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5214768648147583},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44294804334640503},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4284120500087738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40846478939056396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870520830154419},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8623579740524292},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6324517726898193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6056409478187561},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5968758463859558},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5814774036407471},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5619955062866211},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5214768648147583},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44294804334640503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4284120500087738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40846478939056396},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d15-1067","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1067","pdf_url":"https://www.aclweb.org/anthology/D15-1067.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.697.3267","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.697.3267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1067.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1067","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1067","pdf_url":"https://www.aclweb.org/anthology/D15-1067.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250385510.pdf","grobid_xml":"https://content.openalex.org/works/W2250385510.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W13932556","https://openalex.org/W53209706","https://openalex.org/W63837240","https://openalex.org/W98761997","https://openalex.org/W99754442","https://openalex.org/W116128650","https://openalex.org/W183720700","https://openalex.org/W589664387","https://openalex.org/W1481997832","https://openalex.org/W1538789362","https://openalex.org/W1601068082","https://openalex.org/W1614298861","https://openalex.org/W2012897754","https://openalex.org/W2022827250","https://openalex.org/W2056664748","https://openalex.org/W2081798681","https://openalex.org/W2091362531","https://openalex.org/W2098162425","https://openalex.org/W2102445696","https://openalex.org/W2105083637","https://openalex.org/W2115791615","https://openalex.org/W2117473841","https://openalex.org/W2153256230","https://openalex.org/W2162594512","https://openalex.org/W2218641061","https://openalex.org/W2293159451","https://openalex.org/W2396767181","https://openalex.org/W2963355447","https://openalex.org/W3215982047","https://openalex.org/W4297818512"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2390346111","https://openalex.org/W3011883280","https://openalex.org/W2369082698","https://openalex.org/W2024983515"],"abstract_inverted_index":{"The":[0],"enormous":[1],"amount":[2],"of":[3,12,19,25,57],"information":[4,15],"on":[5],"the":[6,10,17],"Internet":[7],"has":[8],"raised":[9],"challenge":[11],"highlighting":[13],"new":[14],"in":[16],"context":[18],"already":[20],"viewed":[21],"content.":[22],"This":[23],"type":[24],"intelligent":[26],"interface":[27],"can":[28],"save":[29],"users":[30],"time":[31],"and":[32,50,64],"prevent":[33],"frustration.":[34],"Our":[35],"goal":[36],"is":[37],"to":[38,43],"scale":[39],"up":[40],"novelty":[41,62],"detection":[42],"large":[44],"web":[45],"properties":[46],"like":[47],"Google":[48],"News":[49],"Yahoo":[51],"News.":[52],"We":[53],"present":[54],"a":[55],"set":[56],"lightweight":[58],"features":[59],"for":[60],"online":[61],"scoring":[63],"fast":[65],"nonlinear":[66],"feature":[67],"transformation":[68],"methods.":[69]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
