{"id":"https://openalex.org/W2117995488","doi":"https://doi.org/10.3115/v1/w14-0404","title":"Some Issues on the Normalization of a Corpus of Products Reviews in Portuguese","display_name":"Some Issues on the Normalization of a Corpus of Products Reviews in Portuguese","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2117995488","doi":"https://doi.org/10.3115/v1/w14-0404","mag":"2117995488"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-0404","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0404","pdf_url":"https://aclanthology.org/W14-0404.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 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-0404.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032431924","display_name":"Magali Sanches Duran","orcid":"https://orcid.org/0000-0002-3843-4600"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Magali Sanches Duran","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071517439","display_name":"Lucas Avan\u00e7o","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Avan\u00e7o","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059202822","display_name":"Sandra Maria Alu\u00edsio","orcid":"https://orcid.org/0000-0001-5108-2630"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sandra Alu\u00edsio","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036475121","display_name":"Thiago Alexandre Salgueiro Pardo","orcid":"https://orcid.org/0000-0003-2111-1319"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Pardo","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043307073","display_name":"Maria da Gra\u00e7a Volpe Nunes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria da Gra\u00e7a Volpe Nunes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.688,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92166694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T12353","display_name":"Lexicography and Language Studies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.8230006694793701},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.8015797138214111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7752208113670349},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.7417178750038147},{"id":"https://openalex.org/keywords/slang","display_name":"Slang","score":0.7274860143661499},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6888033747673035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6385619640350342},{"id":"https://openalex.org/keywords/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.523257851600647},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.517347514629364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5130692720413208},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5126070380210876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4376679062843323},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3319273293018341},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3238449990749359},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2204066812992096},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10118210315704346}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8230006694793701},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8015797138214111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752208113670349},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7417178750038147},{"id":"https://openalex.org/C2779901982","wikidata":"https://www.wikidata.org/wiki/Q8102","display_name":"Slang","level":2,"score":0.7274860143661499},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6888033747673035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6385619640350342},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.523257851600647},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.517347514629364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5130692720413208},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5126070380210876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4376679062843323},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3319273293018341},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3238449990749359},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2204066812992096},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10118210315704346},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-0404","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0404","pdf_url":"https://aclanthology.org/W14-0404.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 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.2684","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.2684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-0404.pdf","raw_type":"text"},{"id":"pmh:oai:www.producao.usp.br:BDPI/45286","is_oa":true,"landing_page_url":"http://www.producao.usp.br/handle/BDPI/45286","pdf_url":null,"source":{"id":"https://openalex.org/S4306401373","display_name":"Scientific Electronic Library Online (S\u00e3o Paulo Research Foundation, Latin American and Caribbean Center on Health Sciences Information, Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2982035970","host_organization_name":"Costa Rican Department of Social Security","host_organization_lineage":["https://openalex.org/I2982035970"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-0404","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0404","pdf_url":"https://aclanthology.org/W14-0404.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 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2117995488.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W63056884","https://openalex.org/W1032169362","https://openalex.org/W1507805082","https://openalex.org/W1532325895","https://openalex.org/W1874835824","https://openalex.org/W2057169877","https://openalex.org/W2116533968","https://openalex.org/W2153804780","https://openalex.org/W2252107166","https://openalex.org/W2616272086","https://openalex.org/W2737716763","https://openalex.org/W2884262036"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2890155603","https://openalex.org/W4292714663","https://openalex.org/W4362595941"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,24,30,39,45],"analysis":[4],"of":[5,8,13,26,33,41],"different":[6],"kinds":[7,32],"noises":[9,43],"in":[10,16],"a":[11],"corpus":[12],"products":[14],"reviews":[15],"Brazilian":[17],"Portuguese.":[18],"Case":[19],"folding,":[20],"punctuation,":[21],"spelling":[22],"and":[23],"use":[25],"internet":[27],"slang":[28],"are":[29],"major":[31],"noise":[34],"we":[35,49],"face.":[36],"After":[37],"noting":[38],"effect":[40],"these":[42],"on":[44],"POS":[46],"tagging":[47],"task,":[48],"propose":[50],"some":[51],"procedures":[52],"to":[53],"minimize":[54],"them.":[55],"1.":[56]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
