引水渠
发表于 2025-3-28 16:06:11
http://reply.papertrans.cn/88/8741/874053/874053_41.png
健谈的人
发表于 2025-3-28 21:23:52
Lightweight Language Agnostic Data Sanitization Pipeline for Dealing with Homoglyphs in Code-Mixed Lomoglyphed sentences. We also introduce HEMNIST, an extended version of EMNIST that includes images of homoglyphs. We achieve a cosine similarity of 0.922, 0.845, 0.671, 0.508 and 0.231 between original and retrieved text at 5%, 10%, 20%, 30% and 50% masking respectively.
政府
发表于 2025-3-29 01:58:42
http://reply.papertrans.cn/88/8741/874053/874053_43.png
Enliven
发表于 2025-3-29 04:45:40
1865-0929 w-Resource Languages, SPELLL 2023, held in Perundurai, Erode, India, during December 6–8, 2023...The 27 full papers and 6 short papers presented in this book were carefully reviewed and selected from 94 submissions. The papers are divided into the following topical sections: language resources; lang
HEAVY
发表于 2025-3-29 10:54:55
Conference proceedings 2024re carefully reviewed and selected from 94 submissions. The papers are divided into the following topical sections: language resources; language technologies; speech technologies; and workshops - regional fake, MMLOW, LC4..
aviator
发表于 2025-3-29 13:06:37
http://reply.papertrans.cn/88/8741/874053/874053_46.png
Wernickes-area
发表于 2025-3-29 17:46:15
PolitiKweli: A Swahili-English Code-Switched Twitter Political Misinformation Classification Datasete these platforms’ set policies against misinformation, there is an alarming rise in misleading news dissemination. On political matters, misinformation online can result in defamation and in extreme cases, violence offline. Misinformation classification involves classifying text as fake or fact. Mo
Bmd955
发表于 2025-3-29 23:09:18
Telugu Meme Dataset and Baseline System for Automatic Identification of Domain, and Troll in Memes or be helpful or educational for them. Memes are one type of media that is disseminated in this way through direct messages, videos, or photographs. A meme is an image or video that captures the opinions and sentiments of a particular group of people. Memes can be trolling or not, and they include
枫树
发表于 2025-3-30 00:14:24
SamPar: A Marathi Hate Speech Dataset for Homophobia, Transphobia regarding the LGBTQ+ community on social media. Leveraging a meticulously curated dataset extracted from prominent social media platforms, YouTube and Facebook, the study unveils the social, cultural, and moral perspectives palpable across both urban and rural domains. The data, derived via a rigor
极力证明
发表于 2025-3-30 05:28:55
http://reply.papertrans.cn/88/8741/874053/874053_50.png