{"id":"https://openalex.org/W2120502101","doi":"https://doi.org/10.1145/1148170.1148303","title":"Swordfish","display_name":"Swordfish","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2120502101","doi":"https://doi.org/10.1145/1148170.1148303","mag":"2120502101"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5113448679","display_name":"Chris Jordan","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Chris Jordan","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020714471","display_name":"John Healy","orcid":"https://orcid.org/0000-0002-8996-4054"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"John Healy","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035485219","display_name":"Vlado Ke\u0161elj","orcid":"https://orcid.org/0000-0001-8760-3223"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vlado Keselj","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113448679"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":0.4518,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74284709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"657","last_page":"658"},"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/T11269","display_name":"Algorithms and Data Compression","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/T10028","display_name":"Topic Modeling","score":0.9955000281333923,"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/morpheme","display_name":"Morpheme","score":0.8331196308135986},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.7912800908088684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7336373329162598},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5463096499443054},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5427520275115967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535049557685852},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.4630259573459625},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4437200129032135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2132365107536316}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.8331196308135986},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.7912800908088684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336373329162598},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5463096499443054},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5427520275115967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535049557685852},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.4630259573459625},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4437200129032135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2132365107536316},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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:10.1145/1148170.1148303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1660390307","https://openalex.org/W2008434289","https://openalex.org/W2101711363","https://openalex.org/W3183153947"],"related_works":["https://openalex.org/W4237628466","https://openalex.org/W2735979742","https://openalex.org/W3112474074","https://openalex.org/W2362025288","https://openalex.org/W4384447452","https://openalex.org/W2971923188","https://openalex.org/W4388740574","https://openalex.org/W2889906500","https://openalex.org/W3137191661","https://openalex.org/W2035645574"],"abstract_inverted_index":{"Extracting":[0],"morphemes":[1,97],"from":[2],"words":[3],"is":[4,144],"a":[5,29,65],"nontrivial":[6],"task.":[7],"Rule":[8],"based":[9,46,86,120],"stemming":[10],"approaches":[11,47],"such":[12],"as":[13],"Porter's":[14],"algorithm":[15],"have":[16],"encountered":[17],"some":[18,75],"success,":[19],"however":[20],"they":[21],"are":[22,35,98],"restricted":[23],"by":[24],"their":[25],"ability":[26],"to":[27,53,134],"identify":[28],"limited":[30],"number":[31],"of":[32,71],"affixes":[33],"and":[34,73,117,148],"language":[36],"dependent.":[37],"When":[38],"dealing":[39],"with":[40,42,55],"languages":[41],"many":[43,50],"affixes,":[44],"rule":[45],"generally":[48],"require":[49],"more":[51],"rules":[52,63],"deal":[54],"all":[56],"the":[57,69,94,118,130,140],"possible":[58,96,104],"word":[59],"forms.":[60],"Deriving":[61],"these":[62],"requires":[64],"larger":[66],"effort":[67],"on":[68,121],"part":[70],"linguists":[72],"in":[74,93],"instances":[76],"can":[77],"be":[78,135],"simply":[79],"impractical.":[80],"We":[81,100],"propose":[82],"an":[83],"unsupervised":[84],"ngram":[85,91],"approach,":[87],"named":[88],"Swordfish.":[89],"Using":[90],"probabilities":[92,113],"corpus,":[95],"identified.":[99],"look":[101],"at":[102],"two":[103,115],"methods":[105],"for":[106,137,146],"identifying":[107],"candidate":[108],"morphemes,":[109],"one":[110],"using":[111],"joint":[112,131],"between":[114,124],"ngrams,":[116],"second":[119],"log":[122],"odds":[123],"prefix":[125,141],"probabilities.":[126],"Initial":[127],"results":[128],"indicate":[129],"probability":[132],"approach":[133,143],"better":[136,145],"English":[138],"while":[139],"ratio":[142],"Finnish":[147],"Turkish.":[149]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
