JingqingZ/KG4ZeroShotText
Source code of the paper 'Integrating Semantic Knowledge to Tackle Zero-shot Text Classification. NAACL-HLT 2019. '
This project helps classify text documents, especially when you encounter new categories that weren't present in your initial training data. You provide a collection of text documents and the system outputs which category each document belongs to, even for categories it has never seen before. It is designed for data scientists, NLP practitioners, or researchers dealing with evolving text classification needs.
No commits in the last 6 months.
Use this if you need to categorize text documents into classes, some of which are new or 'unseen,' without requiring new training examples for those specific classes.
Not ideal if all your document categories are already well-represented with plenty of existing labeled examples for traditional text classification.
Stars
50
Forks
11
Language
Python
License
—
Category
Last pushed
Mar 18, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/JingqingZ/KG4ZeroShotText"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
airaria/TextBrewer
A PyTorch-based knowledge distillation toolkit for natural language processing
sunyilgdx/NSP-BERT
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original...
kssteven418/LTP
[KDD'22] Learned Token Pruning for Transformers
princeton-nlp/CoFiPruning
[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
georgian-io/Transformers-Domain-Adaptation
:no_entry: [DEPRECATED] Adapt Transformer-based language models to new text domains