{"id":"https://openalex.org/W4200356532","doi":"https://doi.org/10.5753/stil.2021.17791","title":"Measuring Brazilian Portuguese Product Titles Similarity using Embeddings","display_name":"Measuring Brazilian Portuguese Product Titles Similarity using Embeddings","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W4200356532","doi":"https://doi.org/10.5753/stil.2021.17791"},"language":"en","primary_location":{"id":"doi:10.5753/stil.2021.17791","is_oa":true,"landing_page_url":"https://doi.org/10.5753/stil.2021.17791","pdf_url":"https://sol.sbc.org.br/index.php/stil/article/download/17791/17625","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIII Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana (STIL 2021)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://sol.sbc.org.br/index.php/stil/article/download/17791/17625","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042077565","display_name":"Alan da Silva Romualdo","orcid":null},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Alan da Silva Romualdo","raw_affiliation_strings":["UFSCar"],"affiliations":[{"raw_affiliation_string":"UFSCar","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063881434","display_name":"Livy Real","orcid":"https://orcid.org/0000-0002-4763-3898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Livy Real","raw_affiliation_strings":["Americanas S. A"],"affiliations":[{"raw_affiliation_string":"Americanas S. A","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087505547","display_name":"Helena de Medeiros Caseli","orcid":"https://orcid.org/0000-0003-3996-8599"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Helena de Medeiros Caseli","raw_affiliation_strings":["UFSCar"],"affiliations":[{"raw_affiliation_string":"UFSCar","institution_ids":["https://openalex.org/I177909021"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042077565"],"corresponding_institution_ids":["https://openalex.org/I177909021"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70050828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9901000261306763,"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/T13629","display_name":"Text Readability and Simplification","score":0.982699990272522,"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/word2vec","display_name":"Word2vec","score":0.7911025285720825},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7815477252006531},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.685263454914093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6820986866950989},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.679513156414032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.661055862903595},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.652579665184021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6256552338600159},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.6241244077682495},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6136067509651184},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5056216716766357},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.49042460322380066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26891425251960754},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.25053030252456665},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.22367864847183228},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21515214443206787}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.7911025285720825},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7815477252006531},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.685263454914093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6820986866950989},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.679513156414032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661055862903595},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.652579665184021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6256552338600159},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.6241244077682495},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6136067509651184},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5056216716766357},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.49042460322380066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26891425251960754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25053030252456665},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.22367864847183228},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21515214443206787},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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:10.5753/stil.2021.17791","is_oa":true,"landing_page_url":"https://doi.org/10.5753/stil.2021.17791","pdf_url":"https://sol.sbc.org.br/index.php/stil/article/download/17791/17625","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIII Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana (STIL 2021)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5753/stil.2021.17791","is_oa":true,"landing_page_url":"https://doi.org/10.5753/stil.2021.17791","pdf_url":"https://sol.sbc.org.br/index.php/stil/article/download/17791/17625","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIII Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana (STIL 2021)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200356532.pdf","grobid_xml":"https://content.openalex.org/works/W4200356532.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2747424680","https://openalex.org/W2760738985","https://openalex.org/W2896457183","https://openalex.org/W2929779715","https://openalex.org/W2936695845","https://openalex.org/W2968304944","https://openalex.org/W3009234749","https://openalex.org/W3096266342","https://openalex.org/W4213338820","https://openalex.org/W4294170691","https://openalex.org/W4298857951","https://openalex.org/W6691431627","https://openalex.org/W6742927404","https://openalex.org/W6761205521","https://openalex.org/W6766411995","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W1560851690","https://openalex.org/W3092047717","https://openalex.org/W3110772647","https://openalex.org/W2770162183","https://openalex.org/W4390881630","https://openalex.org/W3107848922","https://openalex.org/W2135511601","https://openalex.org/W3210334372","https://openalex.org/W4287385180"],"abstract_inverted_index":{"Textual":[0],"similarity":[1,33,64],"deals":[2],"with":[3,51],"determining":[4],"how":[5],"similar":[6,78],"two":[7],"pieces":[8],"of":[9],"texts":[10],"are,":[11],"considering":[12],"the":[13,62,67,83,91],"lexical":[14],"(surface":[15],"forms)":[16],"or":[17],"semantic":[18],"(meaning)":[19],"closeness.":[20],"In":[21],"this":[22],"paper":[23],"we":[24],"applied":[25],"word":[26,41,69],"embeddings":[27,42,55,70],"for":[28],"measuring":[29],"e-commerce":[30],"product":[31],"title":[32],"in":[34],"Brazilian":[35],"Portuguese.":[36],"We":[37,59],"generated":[38],"some":[39],"domainspecific":[40],"(using":[43],"Word2Vec,":[44],"FastText":[45],"and":[46,48,56,79],"GloVe)":[47],"compared":[49],"them":[50],"general-domain":[52],"models":[53],"(word":[54],"BERT":[57,85],"models).":[58],"concluded":[60],"that":[61],"cosine":[63],"calculated":[65],"using":[66],"domain-specific":[68],"was":[71],"a":[72],"good":[73],"approach":[74],"to":[75,89],"distinguish":[76],"between":[77],"nonsimilar":[80],"products,":[81],"but":[82],"multilingual":[84],"pre-trained":[86],"model":[87],"proved":[88],"be":[90],"best":[92],"one.":[93]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}