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
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category.
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference
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).
Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System
congyingxia/IncrementalFSTC
•
•
NAACL 2021
Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes.
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
hccngu/MLADA
•
•
Findings (ACL) 2021
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance.
Distinct Label Representations for Few-Shot Text Classification
21335732529sky/difference_extractor
•
•
ACL 2021
Few-shot text classification aims to classify inputs whose label has only a few examples.
Noisy Channel Language Model Prompting for Few-Shot Text Classification
shmsw25/Channel-LM-Prompting
•
•
ACL 2022
We introduce a noisy channel approach for language model prompting in few-shot text classification.
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
inimah/protoinfomax
•
•
Findings (EMNLP) 2021
The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications.
RAFT: A Real-World Few-Shot Text Classification Benchmark
Will models soon solve classification tasks that have so far been reserved for human research assistants?
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
We also find that good demonstration can save many labeled examples and consistency in demonstration contributes to better performance.
Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
jixuan-wang/grad2task
•
•
NeurIPS 2021
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks.
