{"id":"https://openalex.org/W2029587734","doi":"https://doi.org/10.1145/1277741.1277867","title":"Story segmentation of broadcast news in Arabic, Chinese and English using multi-window features","display_name":"Story segmentation of broadcast news in Arabic, Chinese and English using multi-window features","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2029587734","doi":"https://doi.org/10.1145/1277741.1277867","mag":"2029587734"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5071900309","display_name":"Martin Franz","orcid":"https://orcid.org/0000-0001-6697-3022"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Martin Franz","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101678958","display_name":"Jianming Xu","orcid":"https://orcid.org/0000-0002-4915-8891"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian-Ming Xu","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071900309"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.5917,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8844945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"703","last_page":"704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/arabic","display_name":"Arabic","score":0.7999117970466614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7571024894714355},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6477716565132141},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.6218044757843018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5618764758110046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5266247391700745},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.45310255885124207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43634408712387085},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4120030701160431},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15827038884162903},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12017816305160522}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7999117970466614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571024894714355},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6477716565132141},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.6218044757843018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618764758110046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5266247391700745},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.45310255885124207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43634408712387085},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4120030701160431},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15827038884162903},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12017816305160522},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1145/1277741.1277867","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W2096175520","https://openalex.org/W2097341304","https://openalex.org/W2098162425","https://openalex.org/W2143720614","https://openalex.org/W6628905179"],"related_works":["https://openalex.org/W2109115373","https://openalex.org/W2390901981","https://openalex.org/W4249048193","https://openalex.org/W4230691760","https://openalex.org/W3000360420","https://openalex.org/W1931440630","https://openalex.org/W4391923333","https://openalex.org/W3041490575","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"The":[0],"paper":[1],"describes":[2],"a":[3,34],"maximum":[4],"entropy":[5],"based":[6],"story":[7],"segmentation":[8],"system":[9],"for":[10,42],"Arabic,":[11],"Chinese":[12],"and":[13,24],"English.":[14],"In":[15],"experiments":[16],"with":[17],"broadcast":[18],"news":[19],"data":[20],"from":[21],"TDT-3,":[22],"TDT-4,":[23],"corpora":[25],"collected":[26],"in":[27],"the":[28],"DARPA":[29],"GALE":[30],"project":[31],"we":[32],"obtain":[33],"substantial":[35],"performance":[36],"gain":[37],"using":[38],"multiple":[39],"overlapping":[40],"windows":[41],"text-based":[43],"features.":[44]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}