{"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/bilingual-sentiment-embeddings-joint","title":"Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languages","arxiv_id":"1805.09016","date":"2018-05-23","proceeding":"ACL 2018 7","authors":["Jeremy Barnes","Roman Klinger","Sabine Schulte im Walde"],"abstract":"Sentiment analysis in low-resource languages suffers from a lack of annotated\ncorpora to estimate high-performing models. Machine translation and bilingual\nword embeddings provide some relief through cross-lingual sentiment approaches.\nHowever, they either require large amounts of parallel data or do not\nsufficiently capture sentiment information. We introduce Bilingual Sentiment\nEmbeddings (BLSE), which jointly represent sentiment information in a source\nand target language. This model only requires a small bilingual lexicon, a\nsource-language corpus annotated for sentiment, and monolingual word embeddings\nfor each language. We perform experiments on three language combinations\n(Spanish, Catalan, Basque) for sentence-level cross-lingual sentiment\nclassification and find that our model significantly outperforms\nstate-of-the-art methods on four out of six experimental setups, as well as\ncapturing complementary information to machine translation. Our analysis of the\nresulting embedding space provides evidence that it represents sentiment\ninformation in the resource-poor target language without any annotated data in\nthat language.","url_abs":"http://arxiv.org/abs/1805.09016v1","url_pdf":"http://arxiv.org/pdf/1805.09016v1.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":"bilingual-sentiment-embeddings-joint","repo_url":"https://github.com/jbarnesspain/blse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-lingual-sentiment-classification","task_name":"Cross-Lingual Sentiment Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.09016","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}