{"id":"https://openalex.org/W36911175","doi":"https://doi.org/10.21437/interspeech.2007-178","title":"Exploiting information extraction annotations for document retrieval in distillation tasks","display_name":"Exploiting information extraction annotations for document retrieval in distillation tasks","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W36911175","doi":"https://doi.org/10.21437/interspeech.2007-178","mag":"36911175"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-178","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5015334291","display_name":"Dilek Hakkani-T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dilek Hakkani-T\u00fcr","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011053835","display_name":"Michael Levit","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Levit","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015334291"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.3467,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88993683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"330","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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":0.8552664518356323},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8045581579208374},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.733349084854126},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7010103464126587},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6158491373062134},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.572167694568634},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5442978143692017},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.49436044692993164},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.475885272026062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46982622146606445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2500154674053192},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.24034759402275085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552664518356323},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8045581579208374},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.733349084854126},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7010103464126587},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6158491373062134},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.572167694568634},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5442978143692017},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.49436044692993164},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.475885272026062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46982622146606445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2500154674053192},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24034759402275085},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-178","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W131395912","https://openalex.org/W348133106","https://openalex.org/W1486660648","https://openalex.org/W1509769683","https://openalex.org/W2053463056","https://openalex.org/W2080278171","https://openalex.org/W2082145945","https://openalex.org/W2104049393","https://openalex.org/W2185615741"],"related_works":["https://openalex.org/W2004087619","https://openalex.org/W4321472216","https://openalex.org/W2557094866","https://openalex.org/W2469016277","https://openalex.org/W2362196274","https://openalex.org/W2757101400","https://openalex.org/W1982302668","https://openalex.org/W2240384024","https://openalex.org/W173956503","https://openalex.org/W1531508671"],"abstract_inverted_index":{"Information":[0],"distillation":[1,51],"aims":[2],"to":[3,10,35,76],"extract":[4],"relevant":[5],"pieces":[6],"of":[7,44,49],"information":[8,32,84,102,104,106],"related":[9],"a":[11],"given":[12],"query":[13,98],"from":[14],"massive,":[15],"possibly":[16],"multilingual,":[17],"audio":[18],"and":[19],"textual":[20],"document":[21,37,79,108],"sources.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"present":[27],"our":[28],"approach":[29],"for":[30,39,60,95],"using":[31,72],"extraction":[33],"annotations":[34],"augment":[36],"retrieval":[38,85,109],"distillation.":[40],"We":[41,68],"take":[42],"advantage":[43],"the":[45,50,61,73,78,89],"fact":[46],"that":[47,71],"some":[48],"queries":[52],"can":[53],"be":[54],"associated":[55],"with":[56],"annotation":[57],"elements":[58],"introduced":[59],"NIST":[62],"Automatic":[63],"Content":[64],"Extraction":[65],"(ACE)":[66],"task.":[67],"experimentally":[69],"show":[70],"ACE":[74],"events":[75],"constrain":[77],"set":[80],"returned":[81],"by":[82],"an":[83],"engine":[86],"significantly":[87],"improves":[88],"precision":[90],"at":[91],"various":[92],"recall":[93],"rates":[94],"two":[96],"different":[97],"templates.":[99],"Index":[100],"Terms:":[101],"distillation,":[103],"retrieval,":[105],"extraction,":[107]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}