 |
VOOZH | about |
In this project, we implemented a topic detection system on Twitter. This system reads tweets from a data stream and assigns them to one of the existing clusters or a new one. Each cluster acts as an agent, which makes the proposed approach a multi-agent system. There is also a coordinator, who monitors the whole system and coordinates the agent.
Convert LaBSE model from TF Hub to PyTorch.
Modular pipeline and interface for multilingual tag prediction on RKD art exhibition catalogues, built with LaBSE and Streamlit.
English-Sinhala multilingual word embedding alignment resources
Powering Silah's smart features!
Align Parallel Sentence of 104 Languages with the help of mBERT and LaBSE
A comprehensive framework for detecting hate speech in the low-resource Telugu language using multimodal (audio and text) analysis
AI-powered scoring tool for the Emotional and Classic Hayling Test
[ARCHIVED] Utilities for preparing and cleaning English-Russian parallel corpora.
Proyek ini berfokus pada pemecahan "Bahasa Mars" (anagram Bahasa Indonesia) dan pencocokannya dengan dokumen Bahasa Inggris. Metodologi utama meliputi dekripsi anagram, diikuti oleh pencarian informasi lintas-bahasa (CLIR) menggunakan fine-tuning model LaBSE dengan hard negative mining untuk ketahanan terhadap noise.
Low-resource multimodal hate speech detection leveraging acoustic and textual representations for robust moderation in Telugu.
Cross-lingual prompt injection detection using multilingual BERT models (LaBSE, mDeBERTa)
A tool to translate and check the accuracy of Japanese driver's license practice questions into foreign language (Thai, etc...using NLLB & LaBSE). This is a personal project for hobby and self-learning purposes. / 日本の免許試験の模擬問題を日本語からタイ語等へ翻訳・精度チェックするツール（NLLB & LaBSE使用）です。自己学習目的で作成しています
Add a description, image, and links to the labse topic page so that developers can more easily learn about it.
To associate your repository with the labse topic, visit your repo's landing page and select "manage topics."