{"id":"https://openalex.org/W2101446498","doi":"https://doi.org/10.1109/icassp.2008.4518807","title":"Sentence segmentation and punctuation recovery for spoken language translation","display_name":"Sentence segmentation and punctuation recovery for spoken language translation","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2101446498","doi":"https://doi.org/10.1109/icassp.2008.4518807","mag":"2101446498"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518807","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":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002419451","display_name":"Matthias Paulik","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthias Paulik","raw_affiliation_strings":["Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","Interactive Systems Laboratories (interACT), Universit\u00e4t Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Universit\u00e4t Karlsruhe, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110747272","display_name":"Sharath Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharath Rao","raw_affiliation_strings":["Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lane","raw_affiliation_strings":["Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064572063","display_name":"Stephan Vogel","orcid":"https://orcid.org/0000-0003-2630-4881"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Vogel","raw_affiliation_strings":["Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","Interactive Systems Laboratories (interACT), Universit\u00e4t Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Interactive Systems Laboratories (interACT), Universit\u00e4t Karlsruhe, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002419451"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.7109,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89109347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5105","last_page":"5108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T13629","display_name":"Text Readability and Simplification","score":0.9936000108718872,"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/punctuation","display_name":"Punctuation","score":0.880200207233429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998910546302795},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7763923406600952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7343372702598572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6045781373977661},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5859678983688354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44297322630882263},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.436921626329422},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.43336522579193115},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.4309297204017639},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39003539085388184},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3469359874725342}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.880200207233429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998910546302795},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7763923406600952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7343372702598572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6045781373977661},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5859678983688354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44297322630882263},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.436921626329422},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.43336522579193115},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.4309297204017639},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39003539085388184},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3469359874725342},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2008.4518807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518807","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"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000009159","is_oa":false,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000009159","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:bookPart"},{"id":"pmh:doi:10.5445/ir/1000009159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5710","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.ira.uka.de/fileadmin/media/publication_files/PaulikSchultz-ICASSP2008.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:doi:10.5445/ir/1000009159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W83095340","https://openalex.org/W194869192","https://openalex.org/W1484504603","https://openalex.org/W1973923101","https://openalex.org/W2034724441","https://openalex.org/W2063697624","https://openalex.org/W2152311128","https://openalex.org/W6603393933","https://openalex.org/W6628972281"],"related_works":["https://openalex.org/W3089218859","https://openalex.org/W2000013842","https://openalex.org/W4362495644","https://openalex.org/W2134714056","https://openalex.org/W4321065355","https://openalex.org/W2997015083","https://openalex.org/W2404510748","https://openalex.org/W2892009878","https://openalex.org/W4379381477","https://openalex.org/W4293577743"],"abstract_inverted_index":{"Sentence":[0],"segmentation":[1,24],"and":[2,25,37,69],"punctuation":[3,26],"recovery":[4,27],"are":[5],"critical":[6],"components":[7],"for":[8,28,34],"effective":[9],"spoken":[10],"language":[11,31,52,71],"translation":[12,62,94],"(SLT).":[13],"In":[14],"this":[15],"paper":[16],"we":[17,55],"describe":[18],"our":[19],"recent":[20],"work":[21],"on":[22],"sentence":[23],"three":[29],"different":[30,51],"pairs,":[32],"namely":[33],"English-to-Spanish,":[35],"Arabic-to-English":[36],"Chinese-to-English.":[38],"We":[39],"show":[40],"that":[41,65],"the":[42,61],"proposed":[43],"approach":[44],"works":[45],"equally":[46],"well":[47],"in":[48],"these":[49],"very":[50],"pairs.":[53],"Furthermore,":[54],"introduce":[56,88],"two":[57],"features":[58,84],"computed":[59],"from":[60],"beam-search":[63],"lattice":[64],"indicate":[66],"if":[67],"phrasal":[68],"target":[70],"model":[72],"context":[73],"is":[74],"jeopardized":[75],"when":[76],"segmenting":[77],"at":[78],"a":[79],"given":[80],"word":[81],"boundary.":[82],"These":[83],"enable":[85],"us":[86],"to":[87],"short":[89],"intra-sentence":[90],"segments":[91],"without":[92],"degrading":[93],"performance.":[95]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
