{"id":"https://openalex.org/W2396045889","doi":"https://doi.org/10.21437/interspeech.2013-627","title":"Web data harvesting for speech understanding grammar induction","display_name":"Web data harvesting for speech understanding grammar induction","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2396045889","doi":"https://doi.org/10.21437/interspeech.2013-627","mag":"2396045889"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-627","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5027552565","display_name":"Ioannis Klasinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ioannis Klasinas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084949286","display_name":"Alexandros Potamianos","orcid":"https://orcid.org/0009-0007-1532-5288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandros Potamianos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108068056","display_name":"Elias Iosif","orcid":"https://orcid.org/0000-0002-4694-8556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elias Iosif","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614817","display_name":"Spiros Georgiladakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spiros Georgiladakis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090854584","display_name":"Gianluca Mameli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gianluca Mameli","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027552565"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3281,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94561691,"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":"2733","last_page":"2737"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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":0.9993000030517578,"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":0.8712719082832336},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7369424700737},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6459628343582153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6421359777450562},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6014666557312012},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5966658592224121},{"id":"https://openalex.org/keywords/grammar-induction","display_name":"Grammar induction","score":0.5451291799545288},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.46719691157341003},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.415406197309494},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3261236548423767},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.21480512619018555},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07981187105178833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8712719082832336},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7369424700737},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6459628343582153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6421359777450562},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6014666557312012},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5966658592224121},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.5451291799545288},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.46719691157341003},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.415406197309494},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3261236548423767},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.21480512619018555},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07981187105178833},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-627","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W143796527","https://openalex.org/W149934508","https://openalex.org/W1549285799","https://openalex.org/W1974967573","https://openalex.org/W2015517729","https://openalex.org/W2030996999","https://openalex.org/W2091466535","https://openalex.org/W2095935433","https://openalex.org/W2101105183","https://openalex.org/W2105830342","https://openalex.org/W2110622404","https://openalex.org/W2125987301","https://openalex.org/W2144363854","https://openalex.org/W2151687588","https://openalex.org/W2158289077","https://openalex.org/W2882319491","https://openalex.org/W2917033454","https://openalex.org/W3117634090"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"The":[0,86],"development":[1,23],"of":[2,24,66,75],"a":[3,6,16,26,29],"grammar":[4],"for":[5,39],"spoken":[7],"dialogue":[8],"system":[9],"can":[10,81,98],"be":[11],"greatly":[12],"accelerated":[13],"by":[14,55,71],"using":[15,90],"corpus":[17,27],"describing":[18],"the":[19,22,44,48,63,67,73,76,83],"application.":[20],"However":[21],"such":[25],"is":[28],"slow":[30],"and":[31,46,93],"expensive":[32],"process.":[33],"This":[34],"paper":[35],"proposes":[36],"unsupervised":[37,92],"methods":[38,96],"finding":[40],"relevant":[41],"corpora":[42,101],"in":[43],"Web":[45],"mining":[47],"most":[49],"informative":[50],"parts.":[51],"We":[52],"show":[53,88],"that":[54,89],"utilizing":[56,72],"perplexity":[57],"we":[58,80,97],"are":[59],"able":[60],"to":[61],"increase":[62,82],"in-domainess":[64],"(precision)":[65],"mined":[68],"corpora,":[69],"while":[70],"rank":[74],"web":[77],"search":[78],"engine":[79],"generalizability":[84],"(recall).":[85],"results":[87],"only":[91],"language":[94],"independent":[95],"compete":[99],"with":[100,104],"created":[102],"manually":[103],"expert":[105],"knowledge.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}