{"id":"https://openalex.org/W2095880437","doi":"https://doi.org/10.1145/2396761.2398410","title":"Segmenting web-domains and hashtags using length specific models","display_name":"Segmenting web-domains and hashtags using length specific models","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2095880437","doi":"https://doi.org/10.1145/2396761.2398410","mag":"2095880437"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398410","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","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/A5101516752","display_name":"Sriram Srinivasan","orcid":"https://orcid.org/0009-0000-7487-3638"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sriram Srinivasan","raw_affiliation_strings":["Yahoo! SDC, Bangalore, India","Yahoo! SDC, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! SDC, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo! SDC, Bangalore, India#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046910575","display_name":"Sourangshu Bhattacharya","orcid":"https://orcid.org/0000-0001-5220-1881"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sourangshu Bhattacharya","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025100345","display_name":"Rudrasis Chakraborty","orcid":"https://orcid.org/0000-0002-0448-911X"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rudrasis Chakraborty","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101516752"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7125,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.86594172,"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":"1113","last_page":"1122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965999722480774,"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":0.7986901998519897},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7446032166481018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6467127799987793},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5185461640357971},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5022938251495361},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.5012242794036865},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4806979298591614},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.4548223614692688},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4319503605365753},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4148159623146057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39559149742126465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3315748870372772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986901998519897},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7446032166481018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6467127799987793},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5185461640357971},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5022938251495361},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.5012242794036865},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4806979298591614},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4548223614692688},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4319503605365753},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4148159623146057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39559149742126465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3315748870372772},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2396761.2398410","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1970810070","https://openalex.org/W2016856586","https://openalex.org/W2029189646","https://openalex.org/W2036516910","https://openalex.org/W2097927681","https://openalex.org/W2105008421","https://openalex.org/W2105644991","https://openalex.org/W2122228338","https://openalex.org/W2147880316","https://openalex.org/W2158188757","https://openalex.org/W2158551114","https://openalex.org/W2161952424","https://openalex.org/W2163353449","https://openalex.org/W2429914308","https://openalex.org/W2950186769","https://openalex.org/W3021371423","https://openalex.org/W6675760969","https://openalex.org/W6954717305"],"related_works":["https://openalex.org/W4298831272","https://openalex.org/W2962916388","https://openalex.org/W2086694237","https://openalex.org/W2095614499","https://openalex.org/W2489956408","https://openalex.org/W349256592","https://openalex.org/W2250330186","https://openalex.org/W3042328374","https://openalex.org/W2118909941","https://openalex.org/W2122892337"],"abstract_inverted_index":{"Segmentation":[0,238],"of":[1,4,11,37,48,132,239],"a":[2,9,45,110],"string":[3],"English":[5],"language":[6,65],"characters":[7],"into":[8,145],"sequence":[10],"words":[12],"has":[13],"many":[14],"applications.":[15],"Here,":[16],"we":[17,41,91,128],"study":[18,44],"two":[19,183],"applications":[20],"in":[21,109,242,245],"the":[22,28,74,85,107,171,216],"internet":[23],"domain.":[24],"First":[25],"application":[26,47],"is":[27,33,134],"web":[29,185],"domain":[30],"segmentation":[31,51,62,121,154],"which":[32],"crucial":[34],"for":[35,52,60,138,249],"monetization":[36],"broken":[38],"URLs.":[39],"Secondly,":[40],"propose":[42,92,104],"and":[43,141,188,210,227],"novel":[46],"twitter":[49,56,250],"hashtag":[50],"increasing":[53],"recall":[54,246],"on":[55,179,224,232,247],"searches.":[57],"Existing":[58],"methods":[59,178],"word":[61,139],"use":[63],"unsupervised":[64,207],"models.":[66,126,159,213],"We":[67,103,175],"find":[68],"that":[69,130,219],"when":[70],"using":[71,113,170],"multiple":[72,79],"corpora,":[73],"joint":[75,94,124,211],"probability":[76,95,118,125,158,212,221],"model":[77],"from":[78,184,190,194],"corpora":[80],"performs":[81],"significantly":[82],"better":[83],"than":[84],"individual":[86],"corpora.":[87],"Motivated":[88],"by":[89],"this,":[90],"weighted":[93],"model,":[96],"with":[97],"weights":[98,108,144],"specific":[99,150,201,229],"to":[100,105],"each":[101],"corpus.":[102],"train":[106],"supervised":[111,117,157,199,220],"manner":[112],"max-margin":[114],"methods.":[115],"The":[116,148,198],"models":[119,151,162,202,222,230],"improve":[120,153],"accuracy":[122,155],"over":[123,156,206],"Finally,":[127],"observe":[129],"length":[131,149,200,228],"segments":[133],"an":[135,195],"important":[136],"parameter":[137],"segmentation,":[140],"incorporate":[142],"length-specific":[143],"our":[146,177],"model.":[147],"further":[152],"For":[160],"all":[161,225],"proposed":[163],"here,":[164],"inference":[165],"problem":[166],"can":[167],"be":[168],"solved":[169],"dynamic":[172],"programming":[173],"algorithm.":[174],"test":[176],"five":[180],"different":[181],"datasets,":[182,226],"domains":[186],"data,":[187,235],"three":[189],"news":[191,233],"headlines":[192,234],"data":[193],"LDC":[196],"dataset.":[197],"show":[203],"significant":[204,243],"improvements":[205],"single":[208],"corpus":[209],"Cross-testing":[214],"between":[215],"datasets":[217],"confirm":[218],"trained":[223,231],"generalize":[236],"well.":[237],"hashtags":[240],"result":[241],"improvement":[244],"searches":[248],"trends.":[251]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}