{"id":"https://openalex.org/W2153895584","doi":"https://doi.org/10.1109/icassp.2008.4518784","title":"Punctuating speech for information extraction","display_name":"Punctuating speech for information extraction","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2153895584","doi":"https://doi.org/10.1109/icassp.2008.4518784","mag":"2153895584"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518784","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5071505335","display_name":"Beno\u00eet Favre","orcid":"https://orcid.org/0000-0002-9777-4613"},"institutions":[{"id":"https://openalex.org/I4210166347","display_name":"S.P.E.C.I.E.S.","ror":"https://ror.org/05tgamw04","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210166347"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benoit Favre","raw_affiliation_strings":["I. C. S. I., Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"I. C. S. I., Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210166347"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004580149","display_name":"Ralph Grishman","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ralph Grishman","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091255196","display_name":"Dustin Hillard","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dustin Hillard","raw_affiliation_strings":["SSLI Laboratory, EE Department, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"SSLI Laboratory, EE Department, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210138199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103178893","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-7954-7994"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166347","display_name":"S.P.E.C.I.E.S.","ror":"https://ror.org/05tgamw04","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210166347"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-Tur","raw_affiliation_strings":["I. C. S. I., Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"I. C. S. I., Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210166347"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["SSLI Laboratory, EE Department, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"SSLI Laboratory, EE Department, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210138199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071505335"],"corresponding_institution_ids":["https://openalex.org/I4210166347"],"apc_list":null,"apc_paid":null,"fwci":4.9541,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96101695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5013","last_page":"5016"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.7798404693603516},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.7322542667388916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7151961922645569},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.699089765548706},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.631410539150238},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5938126444816589},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5735869407653809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5702394843101501},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5501785278320312},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5480362772941589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49959564208984375},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.46124333143234253},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.45770952105522156},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15322086215019226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798404693603516},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.7322542667388916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7151961922645569},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.699089765548706},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.631410539150238},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5938126444816589},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5735869407653809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702394843101501},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5501785278320312},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5480362772941589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49959564208984375},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.46124333143234253},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.45770952105522156},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15322086215019226}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518784","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W40475138","https://openalex.org/W121805954","https://openalex.org/W2027257218","https://openalex.org/W2108251622","https://openalex.org/W2108483185","https://openalex.org/W2135799088","https://openalex.org/W2185615741","https://openalex.org/W2426479676","https://openalex.org/W2463682495","https://openalex.org/W6686545002","https://openalex.org/W6719468595"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3163320880","https://openalex.org/W2365703075"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,24,55,60,101],"effect":[4],"of":[5,32,103],"automatic":[6],"sentence":[7],"boundary":[8],"detection":[9],"and":[10,15,34,44,59,78,99],"comma":[11,35,45],"prediction":[12],"on":[13],"entity":[14,56],"relation":[16,61],"extraction":[17,102],"in":[18,38,51],"speech.":[19],"We":[20],"show":[21],"that":[22,70,90],"punctuating":[23],"machine":[25],"generated":[26],"transcript":[27],"according":[28],"to":[29,53,96],"maximum":[30],"F-measure":[31],"period":[33,43],"annotation":[36],"results":[37],"suboptimal":[39],"information":[40],"extraction.":[41],"Precisely,":[42],"decision":[46],"thresholds":[47],"can":[48,81],"be":[49,82],"chosen":[50],"order":[52],"improve":[54],"value":[57,62],"score":[58,63],"by":[64,74],"4%":[65],"relative.":[66],"Error":[67],"analysis":[68],"shows":[69],"preventing":[71],"noun-phrase":[72],"splitting":[73],"generating":[75],"longer":[76],"sentences":[77],"fewer":[79],"commas":[80],"harmful":[83],"for":[84],"IE":[85],"performance.":[86],"Indeed,":[87],"it":[88],"seems":[89],"missed":[91],"punctuation":[92],"allows":[93],"syntactic":[94],"parsers":[95],"merge":[97],"noun-phrases":[98],"prevent":[100],"correct":[104],"information.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
