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
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.
A model-based cleaner using Laser sentence embeddings to exploit embeddings to filter misaligned segment pairs. Product scaled by asynchronously building the Task Queues, dispatching the tasks in a Round Robin method and adding multiple workers on the RabbitMQ server for consumption.
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.
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.
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 repo contains the annotations and other artifacts of the paper titled: In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages
Codes for master's thesis investigating approaches for building a multilingual, knowledge-grounded dialogue system via cross-task and cross-lingual transfer learning.
Self-Augmented In-Context Learning for Unsupervised Word Translation (ACL 2024). Keywords: Bilingual Lexicon Induction, Word Translation, Large Language Models, LLMs.