You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Jugalbandi (JB) Manager is a full AI-powered conversational chatbot platform. It's platform agnostic and can serve multiple channels such as WhatsApp or custom web interfaces. It can handle conversations in both text and voice across any language. It comes with Bhashini Speech models out of the box and can failover to Azure.
Self-Augmented In-Context Learning for Unsupervised Word Translation (ACL 2024). Keywords: Bilingual Lexicon Induction, Word Translation, Large Language Models, LLMs.
On Bilingual Lexicon Induction with Large Language Models (EMNLP 2023). Keywords: Bilingual Lexicon Induction, Word Translation, Large Language Models, LLMs.
This Project is based on multilingual Translation by using the Transformer with an encoder-decoder architecture along with the multi-head self-attention layers with the positional encoding and embedding for better result and accuracy. Overall, this model converts the English to French language using various Techniques of NLP and DL.
This repository contains a Python script that uses a pre-trained NBART (Neural Bidirectional AutoRegressive Transformer) model to perform multi-lingual translation tasks between several languages. The model was trained on multiple language pairs using data parallelism, allowing it to learn representations across all languages simultaneously.
This repository offers an evaluation of machine translation models for healthcare, focusing on languages like Telugu, Hindi, Arabic, and Swahili. It emphasizes accuracy and medical terminology, aiming to enhance medical communication across diverse languages. The dataset used in evaluation is provided.
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).
A multi-lingual named entity classifier to perform named entity recognition (NER) on two datasets, International: CoNLL 2003, Chinese: Weibo. We used the current state-of-the-art model to test on CoNLL++ dataset, achieved a F1-score of 94.3% with pooled-embeddings.