nutcrtnk/DHGNet
Code for paper "Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph", EMNLP 2021 - findings.
This project helps natural language processing researchers classify text in languages with limited training data by leveraging information from resource-rich languages like English. It takes multilingual text datasets and pre-trained word embeddings as input and outputs a trained text classification model. Researchers and data scientists working on cross-lingual NLP tasks would use this.
No commits in the last 6 months.
Use this if you need to perform text classification on low-resource languages by transferring knowledge from high-resource languages.
Not ideal if your text classification task is solely in a single, well-resourced language, or if you are not an NLP researcher or data scientist.
Stars
13
Forks
4
Language
Python
License
MIT
Category
Last pushed
Dec 14, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/nutcrtnk/DHGNet"
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)