AdrianBZG/HyperBERT
[EMNLP 2024] HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs
This project helps researchers and data scientists classify nodes within complex, interconnected datasets like academic papers or movies. It takes text-attributed hypergraphs, such as citations or movie relationships, and uses advanced language models to assign labels to individual items. The end users are primarily researchers working with large textual networks.
No commits in the last 6 months.
Use this if you need to categorize or label individual entities (like papers, authors, or movies) within a dataset where items are connected in complex, group-based relationships and described by text.
Not ideal if your data lacks textual descriptions for its entities or if your relationships are simple, pairwise connections rather than group-based.
Stars
23
Forks
1
Language
Python
License
MIT
Category
Last pushed
Apr 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/AdrianBZG/HyperBERT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DerwenAI/pytextrank
Python implementation of TextRank algorithms ("textgraphs") for phrase extraction
Tiiiger/bert_score
BERT score for text generation
BrikerMan/Kashgari
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for...
asyml/texar
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. ...
yohasebe/wp2txt
A command-line tool to extract plain text from Wikipedia dumps with category and section filtering