Few-Shot Text Classification
42 papers with code • 8 benchmarks • 4 datasets
Few-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances 1
Benchmarks
These leaderboards are used to track progress in Few-Shot Text Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Few-Shot Text Classification models and implementations
SST
SST-5
RAFT
Events classification - Biotech news
Most implemented papers
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
timoschick/pet
•
•
Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e. g., Radford et al., 2019).
Induction Networks for Few-Shot Text Classification
zhongyuchen/few-shot-text-classification
•
•
IJCNLP 2019
Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
Diverse Few-Shot Text Classification with Multiple Metrics
Gorov/DiverseFewShot_Amazon
•
•
NAACL 2018
We study few-shot learning in natural language domains.
Few-shot Text Classification with Distributional Signatures
YujiaBao/Distributional-Signatures
•
•
ICLR 2020
In this paper, we explore meta-learning for few-shot text classification.
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification
timoschick/pet
•
•
COLING 2020
A recent approach for few-shot text classification is to convert textual inputs to cloze questions that contain some form of task description, process them with a pretrained language model and map the predicted words to labels.
Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
thunlp/knowledgeableprompttuning
•
•
ACL 2022
Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification.
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
r-three/t-few
•
•
ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
zjunlp/promptkg
•
•
Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.
Few-Shot Text Classification with Pre-Trained Word Embeddings and a Human in the Loop
Our work aims to make it possible to classify an entire corpus of unlabeled documents using a human-in-the-loop approach, where the content owner manually classifies just one or two documents per category and the rest can be automatically classified.
A Neural Few-Shot Text Classification Reality Check
tdopierre/FewShotText
•
•
EACL 2021
Additionally, some models used in Computer Vision are yet to be tested in NLP applications.
