TencentGameMate/gnn_cross_lingual
Implementation of ACL-2021 paper: Cross-lingual Text Classification with Heterogeneous Graph Neural Network.
This project helps data scientists, machine learning engineers, and NLP researchers classify text documents in one language, even if they only have labeled training examples in a different language. You provide text datasets in various languages and domains, along with machine-translated versions. The system then outputs accurate classifications for new, unseen texts, bridging the language gap in text analysis.
No commits in the last 6 months.
Use this if you need to classify text data in multiple languages but only have labeled training data for one or a few of them.
Not ideal if you only work with single-language text classification or if you require an out-of-the-box solution without significant setup.
Stars
30
Forks
4
Language
Python
License
MIT
Category
Last pushed
May 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/TencentGameMate/gnn_cross_lingual"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kyzhouhzau/NLPGNN
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and...
IndexFziQ/GNN4NLP-Papers
A list of recent papers about Graph Neural Network methods applied in NLP areas.
qipeng/gcn-over-pruned-trees
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (authors' PyTorch...
kenqgu/Text-GCN
A PyTorch implementation of "Graph Convolutional Networks for Text Classification." (AAAI 2019)
daiquocnguyen/Graph-Transformer
Universal Graph Transformer Self-Attention Networks (TheWebConf WWW 2022) (Pytorch and Tensorflow)