{"id":"https://openalex.org/W2148247209","doi":null,"title":"The Ngram Statistics Package (Text::NSP)- A Flexible Tool for Identifying Ngrams, Collocations, and Word Associations","display_name":"The Ngram Statistics Package (Text::NSP)- A Flexible Tool for Identifying Ngrams, Collocations, and Word Associations","publication_year":2012,"publication_date":"2012-01-06","ids":{"openalex":"https://openalex.org/W2148247209","mag":"2148247209"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5062","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/W/W11/W11-0821.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5060188217","display_name":"Ted Pedersen A","orcid":"https://orcid.org/0000-0003-0417-4123","observed_orcids":["https://orcid.org/0000-0003-0417-4123"]},"institutions":[{"id":"https://openalex.org/I4210115145","display_name":"University of Minnesota, Duluth","ror":"https://ror.org/01hy4qx27","country_code":"US","type":"education","lineage":["https://openalex.org/I4210115145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ted Pedersen","raw_affiliation_strings":["UNIVERSITY OF MINNESOTA, Duluth, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNIVERSITY OF MINNESOTA, Duluth, MN","institution_ids":["https://openalex.org/I4210115145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024489911","display_name":"Satanjeev Banerjee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satanjeev Banerjee","raw_affiliation_strings":["Twitter Inc., San Francisco, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Twitter Inc., San Francisco, CA#TAB#","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083901654","display_name":"Bridget  Thomson McInnes","orcid":"https://orcid.org/0000-0003-2297-6672","observed_orcids":["https://orcid.org/0000-0003-2297-6672"]},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bridget T. Mcinnes","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090203039","display_name":"Saiyam Kohli","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saiyam Kohli","raw_affiliation_strings":["SDL Language Weaver, Inc., Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SDL Language Weaver, Inc., Los Angeles, CA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004767808","display_name":"Mahesh Joshi","orcid":"https://orcid.org/0000-0002-4814-9555","observed_orcids":["https://orcid.org/0000-0002-4814-9555","https://orcid.org/0000-0003-1153-932X"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahesh Joshi","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112116986","display_name":"Ying Liu","orcid":"https://orcid.org/0009-0007-9399-8576","observed_orcids":["https://orcid.org/0009-0007-9399-8576"]},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4823,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92867492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9731000065803528,"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":0.9731000065803528,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.011599999852478504,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.006899999920278788,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/collocations","display_name":"collocations","score":0.9240000247955322},{"id":"https://openalex.org/keywords/word-association","display_name":"word association","score":0.9800000190734863},{"id":"https://openalex.org/keywords/perl","display_name":"Perl","score":0.6940000057220459},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.800000011920929},{"id":"https://openalex.org/keywords/measures-of-association","display_name":"association measures","score":0.902999997138977},{"id":"https://openalex.org/keywords/text-analysis","display_name":"text analysis","score":0.4580000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618409395217896},{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.6546787023544312},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6119593381881714},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5986059904098511},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5516685247421265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145365595817566},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49333277344703674},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45687592029571533},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.418554425239563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2075393795967102},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13369396328926086},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09239357709884644},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5062","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/W/W11/W11-0821.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W80619934","https://openalex.org/W126722120","https://openalex.org/W1529075208","https://openalex.org/W1557914122","https://openalex.org/W1593045043","https://openalex.org/W1940278502","https://openalex.org/W1975690018","https://openalex.org/W2116780029","https://openalex.org/W2142321923","https://openalex.org/W2991446475","https://openalex.org/W2997757304"],"related_works":["https://openalex.org/W7099943846","https://openalex.org/W7071161486","https://openalex.org/W7004044267","https://openalex.org/W3134353090","https://openalex.org/W7015133901","https://openalex.org/W7059883264","https://openalex.org/W4243020341","https://openalex.org/W2117961998","https://openalex.org/W1694187411","https://openalex.org/W7143329447"],"abstract_inverted_index":{"The":[0],"Ngram":[1],"Statistics":[2],"Package":[3],"(Text::NSP)":[4],"is":[5,20],"freely":[6],"available":[7],"open-source":[8],"software":[9],"that":[10,53],"identifies":[11],"ngrams,":[12],"collocations":[13],"and":[14,24,35],"word":[15],"associations":[16],"in":[17,22],"text.":[18],"It":[19,44],"implemented":[21],"Perl":[23],"takes":[25],"advantage":[26],"of":[27,41,49,51],"regular":[28],"expressions":[29],"to":[30,36,57],"provide":[31],"very":[32],"flexible":[33],"tokenization":[34],"allow":[37],"for":[38],"the":[39],"identification":[40],"non-adjacent":[42],"ngrams.":[43],"includes":[45],"a":[46],"wide":[47],"range":[48],"measures":[50],"association":[52],"can":[54],"be":[55],"used":[56],"identify":[58],"collocations.":[59],"1":[60]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
