{"id":"https://openalex.org/W2895713185","doi":"https://doi.org/10.21437/sltu.2018-13","title":"Mining Training Data for Language Modeling Across the World's Languages","display_name":"Mining Training Data for Language Modeling Across the World's Languages","publication_year":2018,"publication_date":"2018-08-29","ids":{"openalex":"https://openalex.org/W2895713185","doi":"https://doi.org/10.21437/sltu.2018-13","mag":"2895713185"},"language":"en","primary_location":{"id":"doi:10.21437/sltu.2018-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/sltu.2018-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2018)","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/A5113960780","display_name":"Manasa Prasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Manasa Prasad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063381559","display_name":"Theresa Breiner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Theresa Breiner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113902201","display_name":"Daan van Esch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daan van Esch","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113960780"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1402,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83964242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9445000290870667,"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":0.9404000043869019,"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":0.7765762805938721},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5781644582748413},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.564077615737915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283212065696716},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4673123061656952},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4658281207084656},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1078624427318573},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06266245245933533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765762805938721},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5781644582748413},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.564077615737915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283212065696716},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4673123061656952},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4658281207084656},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1078624427318573},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06266245245933533},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/sltu.2018-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/sltu.2018-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2018)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3204019825","https://openalex.org/W4394050964","https://openalex.org/W2551249631","https://openalex.org/W4285322112","https://openalex.org/W4292794239"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
