{"id":"https://openalex.org/W2756675017","doi":"https://doi.org/10.18653/v1/w17-4607","title":"Spoken Term Discovery for Language Documentation using Translations","display_name":"Spoken Term Discovery for Language Documentation using Translations","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2756675017","doi":"https://doi.org/10.18653/v1/w17-4607","mag":"2756675017"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4607","pdf_url":"https://www.aclweb.org/anthology/W17-4607.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Speech-Centric Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4607.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228","https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076282184","display_name":"Sameer Bansal","orcid":"https://orcid.org/0000-0001-5607-1914"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sameer Bansal","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228","https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036026526","display_name":"David Chiang","orcid":"https://orcid.org/0000-0002-0435-4864"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"David Chiang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228","https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228","https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109031255","display_name":"Adam Lopez","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Adam Lopez","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame  School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame \u2666 School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I107639228","https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"58"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.852672815322876},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.7336838841438293},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7101976871490479},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7058970928192139},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5986706018447876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5905144810676575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5431929230690002},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4700813591480255},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4538007378578186},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.42022499442100525},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41550785303115845},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.37612196803092957},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3688427209854126},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05530080199241638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852672815322876},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7336838841438293},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7101976871490479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7058970928192139},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5986706018447876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5905144810676575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5431929230690002},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4700813591480255},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4538007378578186},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.42022499442100525},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41550785303115845},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.37612196803092957},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3688427209854126},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05530080199241638},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w17-4607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4607","pdf_url":"https://www.aclweb.org/anthology/W17-4607.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Speech-Centric Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/c22311da-c2bb-49c8-85f2-8e8dce954745","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c22311da-c2bb-49c8-85f2-8e8dce954745","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Anastasopoulos, A, Bansal, S, Goldwater, S, Lopez, A & Chiang, D 2017, Spoken Term Discovery for Language Documentation using Translations. in Proceedings of the First Workshop on Speech-Centric Natural Language Processing. pp. 53-58, First Workshop on Speech-Centric Natural Language Processing, Copenhagen, Denmark, 7/09/17. https://doi.org/10.18653/v1/W17-4607","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c22311da-c2bb-49c8-85f2-8e8dce954745","is_oa":true,"landing_page_url":"https://www.aclweb.org/anthology/W17-4607/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4607","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4607","pdf_url":"https://www.aclweb.org/anthology/W17-4607.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Speech-Centric Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8786586098","display_name":"RI: Small: Language Induction meets Language Documentation: Leveraging bilingual aligned audio for learning and preserving languages","funder_award_id":"1464553","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306183","display_name":"James S. McDonnell Foundation","ror":"https://ror.org/03dy4aq19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2756675017.pdf","grobid_xml":"https://content.openalex.org/works/W2756675017.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W116902681","https://openalex.org/W141348503","https://openalex.org/W2006969979","https://openalex.org/W2084616221","https://openalex.org/W2114347655","https://openalex.org/W2252212004","https://openalex.org/W2345799635","https://openalex.org/W2347145335","https://openalex.org/W2466918907","https://openalex.org/W2563850823","https://openalex.org/W2574132677","https://openalex.org/W2593011301","https://openalex.org/W2949328740","https://openalex.org/W2950613790","https://openalex.org/W2963999449","https://openalex.org/W2964102148","https://openalex.org/W3012492057","https://openalex.org/W4317473142"],"related_works":["https://openalex.org/W2404510748","https://openalex.org/W3089218859","https://openalex.org/W4385571610","https://openalex.org/W1540615732","https://openalex.org/W4200068392","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W2772686614","https://openalex.org/W1489621819","https://openalex.org/W39235475"],"abstract_inverted_index":{"Vast":[0],"amounts":[1],"of":[2,20,84],"speech":[3,21,35,51,77],"data":[4],"collected":[5],"for":[6,31],"language":[7],"documentation":[8],"and":[9,13,48,80,88,93],"research":[10],"remain":[11],"untranscribed":[12],"unsearchable,":[14],"but":[15],"often":[16],"a":[17,29,75],"small":[18],"amount":[19],"may":[22],"have":[23],"text":[24],"translations":[25,37],"available.":[26],"We":[27,41,70],"present":[28],"method":[30,73],"partially":[32],"labeling":[33],"additional":[34],"with":[36],"in":[38,60,66,95],"this":[39],"scenario.":[40,99],"modify":[42],"an":[43,96],"unsupervised":[44],"speech-totranslation":[45],"alignment":[46],"model":[47],"obtain":[49],"prototype":[50],"segments":[52],"that":[53],"match":[54],"the":[55,67],"translation":[56,78],"words,":[57],"which":[58],"are":[59],"turn":[61],"used":[62],"to":[63],"discover":[64],"terms":[65],"unlabelled":[68],"data.":[69],"evaluate":[71],"our":[72],"on":[74,81],"Spanish-English":[76],"corpus":[79],"two":[82],"corpora":[83],"endangered":[85],"languages,":[86],"Arapaho":[87],"Ainu,":[89],"demonstrating":[90],"its":[91],"appropriateness":[92],"applicability":[94],"actual":[97],"very-low-resource":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}