{"id":"https://openalex.org/W46933426","doi":null,"title":"Learning to identify new information","display_name":"Learning to identify new information","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W46933426","mag":"46933426"},"language":"en","primary_location":{"id":"mag:46933426","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1124046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5043650862","display_name":"Barry Schiffman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barry Schiffman","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109565051","display_name":"Kathleen R. McKeown","orcid":"https://orcid.org/0000-0003-4455-2715","observed_orcids":["https://orcid.org/0000-0003-4455-2715"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen McKeown","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":1.3365,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81601502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.47189998626708984,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.47189998626708984,"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":0.31349998712539673,"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/T10028","display_name":"Topic Modeling","score":0.18979999423027039,"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/novelty-detection","display_name":"novelty detection","score":0.7269999980926514},{"id":"https://openalex.org/keywords/syntactic-analysis","display_name":"syntactic analysis","score":0.6370000243186951},{"id":"https://openalex.org/keywords/rule-learning","display_name":"rule induction","score":0.7070000171661377},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"multi-document summarization","score":0.9330000281333923},{"id":"https://openalex.org/keywords/semantic-units","display_name":"semantic units","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7527543306350708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023535966873169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6397169232368469},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6344696283340454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6288512945175171},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5839167237281799},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5665663480758667},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.5506739020347595},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5453613996505737},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5340216755867004},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46867141127586365},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3281517028808594},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08938851952552795},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:46933426","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=1124046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W61761030","https://openalex.org/W73274768","https://openalex.org/W73694622","https://openalex.org/W137524765","https://openalex.org/W139994555","https://openalex.org/W172711807","https://openalex.org/W179179905","https://openalex.org/W312261247","https://openalex.org/W1555460178","https://openalex.org/W1568339100","https://openalex.org/W1576423642","https://openalex.org/W1606211590","https://openalex.org/W1659833910","https://openalex.org/W1679846099","https://openalex.org/W1912123407","https://openalex.org/W1924689489","https://openalex.org/W1977747299","https://openalex.org/W1980813323","https://openalex.org/W2026302857","https://openalex.org/W2029858480","https://openalex.org/W2035534443","https://openalex.org/W2052417512","https://openalex.org/W2055294489","https://openalex.org/W2059975159","https://openalex.org/W2068580143","https://openalex.org/W2070534370","https://openalex.org/W2072284402","https://openalex.org/W2083305840","https://openalex.org/W2085116970","https://openalex.org/W2107130271","https://openalex.org/W2112076978","https://openalex.org/W2115792525","https://openalex.org/W2127314673","https://openalex.org/W2137970221","https://openalex.org/W2139212933","https://openalex.org/W2147169507","https://openalex.org/W2151170651","https://openalex.org/W2151554678","https://openalex.org/W2154652894","https://openalex.org/W2156909104","https://openalex.org/W2159882563","https://openalex.org/W2171064373","https://openalex.org/W2492584954","https://openalex.org/W3089162859"],"related_works":["https://openalex.org/W7098076433","https://openalex.org/W1909233731","https://openalex.org/W2092464680","https://openalex.org/W2074467802","https://openalex.org/W7198788745","https://openalex.org/W2081173909","https://openalex.org/W7095374320","https://openalex.org/W245572922","https://openalex.org/W4213175497","https://openalex.org/W1988107199"],"abstract_inverted_index":{"This":[0],"thesis":[1],"is":[2,16,39,50,77,101,145,209,301],"an":[3,236],"investigation":[4],"into":[5,197],"a":[6,17,25,54,102,126,150,167,172,180,198,214,244,279,285,297],"new":[7,84],"problem":[8],"in":[9,213,235],"natural":[10],"language":[11],"processing:":[12],"new-information":[13,37,48,250],"detection.":[14],"It":[15],"similar":[18],"task":[19,76,110],"to":[20,56,59,152,192,211,257],"first-story":[21],"detection,":[22],"but":[23,287],"with":[24],"very":[26],"large":[27],"difference.":[28],"First-story":[29],"detection":[30,38,49],"operates":[31],"on":[32,40,229],"the":[33,41,51,69,75,80,99,122,131,138,162,194,202,230,233,241,254,258,270,305],"document":[34],"level,":[35],"while":[36],"statement":[42,85],"level.":[43],"In":[44],"its":[45],"fundamental":[46],"guise,":[47],"ability":[52],"for":[53,108,157,201,222,266,269],"machine":[55,189],"be":[57,87],"able":[58],"compare":[60],"two":[61],"textual":[62],"statements":[63,256],"and":[64,147,178],"decide":[65],"whether":[66],"they":[67],"say":[68],"same":[70,139],"thing":[71],"or":[72,118],"not.":[73],"But":[74],"complicated":[78],"by":[79],"fact":[81],"that":[82,98,143,238,282,300],"each":[83],"must":[86,124],"tested":[88],"against":[89],"all":[90,253],"previous":[91],"statements.":[92],"\r\nIn":[93],"this":[94,109],"thesis,":[95],"I":[96,141,148,164,187,262,292],"show":[97],"sentence":[100,135,155,185],"poor":[103],"choice":[104],"of":[105,116,130,159,169,232,246,273],"syntactic":[106,128],"unit":[107,281],"since":[111],"sentences":[112],"are":[113],"arbitrarily":[114],"composed":[115],"one":[117],"more":[119],"structures.":[120],"Thus,":[121,161],"system":[123,163,208,251,276,295],"do":[125],"deeper":[127],"analysis":[129],"inputs":[132],"than":[133],"recognizing":[134],"boundaries.":[136,186],"At":[137],"time,":[140],"found":[142],"context":[144],"important,":[146],"developed":[149,165],"mechanism":[151],"look":[153],"beyond":[154,184],"boundaries":[156],"evidence":[158],"novelty.":[160],"considers":[166],"mixture":[168],"features,":[170],"from":[171,179,304],"micro":[173],"perspective,":[174,182],"looking":[175,183],"within":[176],"sentences,":[177],"macro":[181],"apply":[188],"learning":[190],"techniques":[191],"combine":[193],"features":[195],"coherently":[196],"unified":[199],"hypothesis":[200],"problem,":[203],"using":[204],"rule":[205],"induction.":[206],"The":[207,249,294],"designed":[210],"function":[212],"multi-document":[215],"summarization":[216],"system,":[217],"like":[218],"Columbia's":[219],"NEWSB":[220],"LASTER,":[221],"which":[223,261],"it":[224],"produces":[225],"update":[226],"summaries":[227],"focusing":[228],"developments":[231],"day":[234],"event":[237],"has":[239],"interested":[240],"public":[242],"over":[243],"period":[245],"several":[247],"days.":[248],"provides":[252],"novel":[255],"DEMS":[259],"summarizer,":[260],"had":[263],"previously":[264],"built":[265],"NEWS":[267],"BLASTER,":[268],"final":[271],"selection":[272],"material.":[274],"\r\nThe":[275],"also":[277],"includes":[278],"semantic":[280],"improves":[283],"performance":[284],"bit,":[286],"not":[288],"as":[289,291],"much":[290],"hoped.":[293],"uses":[296],"plugin":[298],"lexicon":[299],"largely":[302],"taken":[303],"WordNet":[306],"data":[307],"at":[308],"present.":[309]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2016-06-24T00:00:00"}