sunyilgdx/NSP-BERT
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"
This project helps you instantly categorize text, understand relationships between sentences, or fill in missing information without needing extensive training data. You provide a piece of text and a set of possible categories or relationships, and it tells you the most likely fit. Marketers, researchers, or anyone dealing with large volumes of text can use this to quickly make sense of unstructured data.
230 stars. No commits in the last 6 months.
Use this if you need to classify or understand text data, like news articles, product reviews, or customer feedback, and want to avoid the time and resources typically required for training a custom AI model.
Not ideal if you require highly specialized domain understanding beyond what a general language model can infer, or if you need to build complex, multi-step natural language processing pipelines.
Stars
230
Forks
38
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/sunyilgdx/NSP-BERT"
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
princeton-nlp/CoFiPruning
[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
kssteven418/LTP
[KDD'22] Learned Token Pruning for Transformers
georgian-io/Transformers-Domain-Adaptation
:no_entry: [DEPRECATED] Adapt Transformer-based language models to new text domains
qiangsiwei/bert_distill
BERT distillation（基于BERT的蒸馏实验 ）