ishan00/meta-learning-for-multi-task-multilingual
Official Repository for the paper titled "Meta-Learning for Effective Multi-task and Multilingual Modelling" accepted at EACL 2021
This project helps natural language processing (NLP) practitioners build more robust models by combining knowledge from various NLP tasks (like question answering or named entity recognition) and multiple languages (such as English, Spanish, or Hindi). It takes in existing datasets for different NLP tasks across multiple languages and outputs a model that performs better on these tasks, even for languages it hasn't explicitly seen. NLP researchers, data scientists, and engineers working on multilingual applications would find this useful.
No commits in the last 6 months.
Use this if you are developing AI models for natural language processing and need to improve performance across diverse tasks and multiple languages, especially in low-resource language settings.
Not ideal if you are working with a single language and a single task, or if you do not have access to multilingual datasets.
Stars
9
Forks
2
Language
Python
License
—
Category
Last pushed
Jul 27, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ishan00/meta-learning-for-multi-task-multilingual"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LoicGrobol/zeldarose
Train transformer-based models.
CPJKU/wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of...
yuanzhoulvpi2017/zero_nlp
中文nlp解决方案(大模型、数据、模型、训练、推理)
minggnim/nlp-models
A repository for training transformer based models
IntelLabs/nlp-architect
A model library for exploring state-of-the-art deep learning topologies and techniques for...