{"id":"https://openalex.org/W2566811487","doi":"https://doi.org/10.18653/v1/w16-5615","title":"Bag of What? Simple Noun Phrase Extraction for Text Analysis","display_name":"Bag of What? Simple Noun Phrase Extraction for Text Analysis","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2566811487","doi":"https://doi.org/10.18653/v1/w16-5615","mag":"2566811487"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-5615","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-5615","pdf_url":"https://www.aclweb.org/anthology/W16-5615.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on NLP and Computational Social Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-5615.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026207393","display_name":"Abram Handler","orcid":"https://orcid.org/0000-0002-8663-2628"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I4210139463","display_name":"The White House","ror":"https://ror.org/04ars5103","country_code":"US","type":"government","lineage":["https://openalex.org/I4210139463"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Abram Handler","raw_affiliation_strings":["Microsoft Research","NPFST united states, united nations, white house, health care","UMass Amherst","Penn State","united states, united nations, white house, health care, prime minister"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"NPFST united states, united nations, white house, health care","institution_ids":["https://openalex.org/I4210139463"]},{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Penn State","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"united states, united nations, white house, health care, prime minister","institution_ids":["https://openalex.org/I4210139463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109348534","display_name":"Matthew J. Denny","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I4210139463","display_name":"The White House","ror":"https://ror.org/04ars5103","country_code":"US","type":"government","lineage":["https://openalex.org/I4210139463"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Matthew Denny","raw_affiliation_strings":["Penn State","united states, united nations, white house, health care, prime minister","NPFST united states, united nations, white house, health care","UMass Amherst","Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Penn State","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"united states, united nations, white house, health care, prime minister","institution_ids":["https://openalex.org/I4210139463"]},{"raw_affiliation_string":"NPFST united states, united nations, white house, health care","institution_ids":["https://openalex.org/I4210139463"]},{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046348432","display_name":"Hanna Wallach","orcid":"https://orcid.org/0000-0003-3395-7186"},"institutions":[{"id":"https://openalex.org/I4210139463","display_name":"The White House","ror":"https://ror.org/04ars5103","country_code":"US","type":"government","lineage":["https://openalex.org/I4210139463"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Hanna Wallach","raw_affiliation_strings":["UMass Amherst","Penn State","NPFST united states, united nations, white house, health care","Microsoft Research","united states, united nations, white house, health care, prime minister"],"affiliations":[{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Penn State","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"NPFST united states, united nations, white house, health care","institution_ids":["https://openalex.org/I4210139463"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"united states, united nations, white house, health care, prime minister","institution_ids":["https://openalex.org/I4210139463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023365550","display_name":"Brendan O\u2019Connor","orcid":"https://orcid.org/0000-0002-6857-1614"},"institutions":[{"id":"https://openalex.org/I4210139463","display_name":"The White House","ror":"https://ror.org/04ars5103","country_code":"US","type":"government","lineage":["https://openalex.org/I4210139463"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Brendan O'Connor","raw_affiliation_strings":["NPFST united states, united nations, white house, health care","Microsoft Research","Penn State","UMass Amherst","united states, united nations, white house, health care, prime minister"],"affiliations":[{"raw_affiliation_string":"NPFST united states, united nations, white house, health care","institution_ids":["https://openalex.org/I4210139463"]},{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Penn State","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"UMass Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"united states, united nations, white house, health care, prime minister","institution_ids":["https://openalex.org/I4210139463"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026207393"],"corresponding_institution_ids":["https://openalex.org/I130769515","https://openalex.org/I24603500","https://openalex.org/I4210139463","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":8.3927,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97646353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9976000189781189,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.803592324256897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7729758024215698},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7171600461006165},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7008984088897705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6715298891067505},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.6592920422554016},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47730883955955505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45607760548591614},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.43644681572914124},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.43109646439552307},{"id":"https://openalex.org/keywords/exploratory-analysis","display_name":"Exploratory analysis","score":0.4212121069431305},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41936811804771423},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.36840924620628357},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14886868000030518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803592324256897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7729758024215698},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7171600461006165},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7008984088897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6715298891067505},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.6592920422554016},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47730883955955505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45607760548591614},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43644681572914124},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.43109646439552307},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.4212121069431305},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41936811804771423},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.36840924620628357},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14886868000030518},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","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:10.18653/v1/w16-5615","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-5615","pdf_url":"https://www.aclweb.org/anthology/W16-5615.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on NLP and Computational Social Science","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-5615","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-5615","pdf_url":"https://www.aclweb.org/anthology/W16-5615.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on NLP and Computational Social Science","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1714056256","display_name":null,"funder_award_id":"DGE-1144860","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2566811487.pdf","grobid_xml":"https://content.openalex.org/works/W2566811487.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W76749362","https://openalex.org/W371426616","https://openalex.org/W1499641710","https://openalex.org/W1513302538","https://openalex.org/W1574901103","https://openalex.org/W1582482241","https://openalex.org/W1632114991","https://openalex.org/W1974991592","https://openalex.org/W1996430422","https://openalex.org/W2009659525","https://openalex.org/W2038411619","https://openalex.org/W2044070623","https://openalex.org/W2049107599","https://openalex.org/W2070118803","https://openalex.org/W2078244995","https://openalex.org/W2093476618","https://openalex.org/W2095655043","https://openalex.org/W2116780029","https://openalex.org/W2123442489","https://openalex.org/W2143995218","https://openalex.org/W2144874182","https://openalex.org/W2153383412","https://openalex.org/W2156754333","https://openalex.org/W2157765050","https://openalex.org/W2171479377","https://openalex.org/W2185115617","https://openalex.org/W2188631158","https://openalex.org/W2250729567","https://openalex.org/W2962996334","https://openalex.org/W2963266575","https://openalex.org/W3158986179","https://openalex.org/W3179072117","https://openalex.org/W4213367174","https://openalex.org/W4233787372"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W1611246314","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2157830631"],"abstract_inverted_index":{"Social":[0],"scientists":[1],"who":[2],"do":[3],"not":[4],"have":[5],"specialized":[6],"natural":[7],"language":[8],"processing":[9],"training":[10],"often":[11],"use":[12,76],"a":[13,24,31,36,40,52,96,103],"unigram":[14,32,53],"bag-of-words":[15],"(BOW)":[16],"representation":[17],"when":[18],"analyzing":[19],"text":[20],"corpora.":[21],"We":[22,55,71],"offer":[23],"new":[25,104],"phrase-based":[26],"method,":[27],"NPFST,":[28],"for":[29,78],"enriching":[30],"BOW.":[33,54],"NPFST":[34,57,77,100],"uses":[35],"partof-speech":[37],"tagger":[38],"and":[39,61,69],"finite":[41],"state":[42],"transducer":[43],"to":[44,48,51,58,75,101],"extract":[45],"multiword":[46],"phrases":[47],"be":[49],"added":[50],"compare":[56],"both":[59],"ngram":[60],"parsing":[62],"methods":[63],"in":[64],"terms":[65],"of":[66,90,106],"yield,":[67],"recall,":[68],"efficiency.":[70],"then":[72],"demonstrate":[73],"how":[74],"exploratory":[79],"analyses;":[80],"it":[81],"performs":[82],"well,":[83],"without":[84],"configuration,":[85],"on":[86],"many":[87],"different":[88],"kinds":[89],"English":[91],"text.":[92],"Finally,":[93],"we":[94],"present":[95],"case":[97],"study":[98],"using":[99],"analyze":[102],"corpus":[105],"U.S.":[107],"congressional":[108],"bills.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}