{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/portuguese-word-embeddings-evaluating-on-word","title":"Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks","arxiv_id":"1708.06025","date":"2017-08-20","proceeding":"WS 2017 10","authors":["Nathan Hartmann","Erick Fonseca","Christopher Shulby","Marcos Treviso","Jessica Rodrigues","Sandra Aluisio"],"abstract":"Word embeddings have been found to provide meaningful representations for\nwords in an efficient way; therefore, they have become common in Natural\nLanguage Processing sys- tems. In this paper, we evaluated different word\nembedding models trained on a large Portuguese corpus, including both Brazilian\nand European variants. We trained 31 word embedding models using FastText,\nGloVe, Wang2Vec and Word2Vec. We evaluated them intrinsically on syntactic and\nsemantic analogies and extrinsically on POS tagging and sentence semantic\nsimilarity tasks. The obtained results suggest that word analogies are not\nappropriate for word embedding evaluation; task-specific evaluations appear to\nbe a better option.","url_abs":"http://arxiv.org/abs/1708.06025v1","url_pdf":"http://arxiv.org/pdf/1708.06025v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"portuguese-word-embeddings-evaluating-on-word","repo_url":"https://github.com/guilhermevarela/deep_srl-br","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"portuguese-word-embeddings-evaluating-on-word","repo_url":"https://github.com/guilhermevarela/deep_srlbr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"portuguese-word-embeddings-evaluating-on-word","repo_url":"https://github.com/nathanshartmann/portuguese_word_embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.06025","atlas_url":"https://app.syntology.ai/?focus=1708.06025","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}