{"id":"https://openalex.org/W2108483185","doi":"https://doi.org/10.1109/asru.2007.4430192","title":"Integrating several annotation layers for statistical information distillation","display_name":"Integrating several annotation layers for statistical information distillation","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2108483185","doi":"https://doi.org/10.1109/asru.2007.4430192","mag":"2108483185"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5011053835","display_name":"Michael Levit","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Levit","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Int. Comput. Sci. Inst., Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Int. Comput. Sci. Inst., Berkeley","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-Tur","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Int. Comput. Sci. Inst., Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Int. Comput. Sci. Inst., Berkeley","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":"https://orcid.org/0009-0008-7740-2557"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","Sri International, Menlo Park, CA 94025, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Sri International, Menlo Park, CA 94025, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110778504","display_name":"Daniel Gillick","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gillick","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","International Computer Science Institute, Berkeley, CA 94704, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.998199999332428,"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":0.8521616458892822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6854148507118225},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6687827110290527},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5746145844459534},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5551761984825134},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.552920937538147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269477963447571},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5033764243125916},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49267131090164185},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4404173195362091},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0880204439163208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521616458892822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6854148507118225},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6687827110290527},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5746145844459534},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5551761984825134},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.552920937538147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269477963447571},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5033764243125916},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49267131090164185},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4404173195362091},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0880204439163208},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2007.4430192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.6468","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.6468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/asru2007-distillation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.6765","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.6765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/~levit/papers/ASRU07_IntegSevAnnot.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W36911175","https://openalex.org/W121805954","https://openalex.org/W131395912","https://openalex.org/W131863957","https://openalex.org/W148137852","https://openalex.org/W1486660648","https://openalex.org/W1508977358","https://openalex.org/W1592696684","https://openalex.org/W2000654059","https://openalex.org/W2037595448","https://openalex.org/W2104049393","https://openalex.org/W2185615741","https://openalex.org/W2793236179","https://openalex.org/W2885050925","https://openalex.org/W6605373601","https://openalex.org/W6605932610","https://openalex.org/W6628944848","https://openalex.org/W6635388633","https://openalex.org/W6686545002","https://openalex.org/W6753815910"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2358755282","https://openalex.org/W2352448290","https://openalex.org/W2380820513"],"abstract_inverted_index":{"We":[0,109,158],"present":[1],"a":[2,9,13,144],"sentence":[3,31],"extraction":[4],"algorithm":[5],"for":[6,12,107],"Information":[7,131],"Distillation,":[8],"task":[10],"where":[11],"given":[14],"templated":[15],"query,":[16,60],"relevant":[17,34],"passages":[18],"must":[19],"be":[20,40],"extracted":[21],"from":[22,42,113,118],"massive":[23],"audio":[24],"and":[25,76,86,127,130,174],"textual":[26],"document":[27],"sources.":[28],"For":[29],"each":[30],"of":[32,55,64,73,81,96,104,116,156],"the":[33,43,53,59,70,74,97,102,161],"documents":[35],"(that":[36],"are":[37,66,92],"assumed":[38],"to":[39,51,58],"known":[41],"upstream":[44],"stages)":[45],"we":[46,137],"employ":[47],"statistical":[48],"classification":[49],"methods":[50],"estimate":[52],"extent":[54],"its":[56,77,169],"relevance":[57,65],"whereby":[61],"two":[62],"aspects":[63],"taken":[67],"into":[68],"account:":[69],"template":[71],"(type)":[72],"query":[75],"slots":[78],"(free-text":[79],"descriptions":[80],"names,":[82],"organizations,":[83],"topic,":[84],"events":[85],"so":[87],"on,":[88],"around":[89],"which":[90],"templates":[91],"centered).":[93],"The":[94],"idiosyncrasy":[95],"presented":[98],"method":[99],"is":[100],"in":[101,154],"choice":[103],"features":[105,112],"used":[106],"classification.":[108],"extract":[110],"our":[111,135],"charts,":[114],"compilations":[115],"elements":[117],"various":[119],"annotation":[120],"levels,":[121],"such":[122],"as":[123,149,151],"word":[124],"transcriptions,":[125],"syntactic":[126],"semantic":[128],"parses,":[129],"Extraction":[132],"annotations.":[133],"In":[134],"experiments":[136],"show":[138],"that":[139],"this":[140],"integrated":[141],"approach":[142],"outperforms":[143],"purely":[145],"lexical":[146],"baseline":[147],"by":[148,167],"much":[150],"30%":[152],"relative":[153],"terms":[155],"F-measure.":[157],"also":[159],"investigate":[160],"algorithm's":[162],"behavior":[163],"under":[164],"noisy":[165],"conditions,":[166],"comparing":[168],"performance":[170],"on":[171,175],"ASR":[172],"output":[173],"corresponding":[176],"manual":[177],"transcriptions.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}