GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → laohur → Learning-To-Compare-For-Text

laohur / Learning-To-Compare-For-Text

Licence: other
Learning To Compare For Text , Few shot learning in text classification

Programming Languages

python
139335 projects - #7 most used programming language

Labels

nlppytorchpretrained-modelsmeta-learningfew-shot-learning

Projects that are alternatives of or similar to Learning-To-Compare-For-Text

sib meta learn
Code of Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
Stars: ✭ 56 (+47.37%)
Mutual labels:  meta-learning, few-shot-learning
awesome-few-shot-meta-learning
awesome few shot / meta learning papers
Stars: ✭ 44 (+15.79%)
Mutual labels:  meta-learning, few-shot-learning
LearningToCompare-Tensorflow
Tensorflow implementation for paper: Learning to Compare: Relation Network for Few-Shot Learning.
Stars: ✭ 17 (-55.26%)
Mutual labels:  meta-learning, few-shot-learning
Awesome-Few-shot
Awesome Few-shot learning
Stars: ✭ 50 (+31.58%)
Mutual labels:  meta-learning, few-shot-learning
Transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Stars: ✭ 8,481 (+22218.42%)
Mutual labels:  meta-learning, few-shot-learning
FUSION
PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"
Stars: ✭ 18 (-52.63%)
Mutual labels:  meta-learning, few-shot-learning
Meta-TTS
Official repository of https://arxiv.org/abs/2111.04040v1
Stars: ✭ 69 (+81.58%)
Mutual labels:  meta-learning, few-shot-learning
simple-cnaps
Source codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)
Stars: ✭ 88 (+131.58%)
Mutual labels:  meta-learning, few-shot-learning
LibFewShot
LibFewShot: A Comprehensive Library for Few-shot Learning.
Stars: ✭ 629 (+1555.26%)
Mutual labels:  meta-learning, few-shot-learning
CDFSL-ATA
[IJCAI 2021] Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
Stars: ✭ 21 (-44.74%)
Mutual labels:  meta-learning, few-shot-learning
FSL-Mate
FSL-Mate: A collection of resources for few-shot learning (FSL).
Stars: ✭ 1,346 (+3442.11%)
Mutual labels:  meta-learning, few-shot-learning
WARP
Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification. https://aclanthology.org/2021.acl-long.381/
Stars: ✭ 66 (+73.68%)
Mutual labels:  pretrained-models, few-shot-learning
MeTAL
Official PyTorch implementation of "Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning" (ICCV2021 Oral)
Stars: ✭ 24 (-36.84%)
Mutual labels:  meta-learning, few-shot-learning
Meta Learning Papers
Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning
Stars: ✭ 2,420 (+6268.42%)
Mutual labels:  meta-learning, few-shot-learning
finetuner
Finetuning any DNN for better embedding on neural search tasks
Stars: ✭ 442 (+1063.16%)
Mutual labels:  pretrained-models, few-shot-learning
CheXpert-Challenge
Code for CheXpert Challenge 2019 Top 1 && Top 2 solution
Stars: ✭ 30 (-21.05%)
Mutual labels:  pretrained-models
AiSpace
AiSpace: Better practices for deep learning model development and deployment For Tensorflow 2.0
Stars: ✭ 28 (-26.32%)
Mutual labels:  pretrained-models
SCL
📄 Spatial Contrastive Learning for Few-Shot Classification (ECML/PKDD 2021).
Stars: ✭ 42 (+10.53%)
Mutual labels:  few-shot-learning
P-tuning
A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
Stars: ✭ 593 (+1460.53%)
Mutual labels:  few-shot-learning
pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem
Stars: ✭ 381 (+902.63%)
Mutual labels:  meta-learning
View All Similar Projects ➔

LearnToCompareText

implement "StructuredSelfAttention" + "RelationNetwork" for few shot learning of text

step

python Util.py python fewshot_main.py

how

more data via manual annotation or data augmentation
more features via transfer learning
more train via meta learning
less parameters and other robust

performance

30seq 10000step 300dim minum100shot
embeeding +cosine  0.54   
embedding+ [bi]GRU + cosine 0.59/0.61
embedding+ [bi]LSTM + cosine 0.63/0.61
embedding+ attn BiGRU + cosine 0.77
embedding+ attn BiLSTM + cosine 0.76
embedding+ attn BiGRU + cosine + data arguementation 0.79
embedding+ attn BiLSTM + concat not converge
bert... tokenize in task_generator

data augmentation √
seqquence length √
pretrain √
less parameters √
c-way-k-shot √

Reference：

  1. Few-Shot Text Classification with Induction Network https://arxiv.org/abs/1902.10482
  2. Learning to Compare: Relation Network for Few-Shot Learning https://arxiv.org/abs/1711.06025 https://github.com/floodsung/LearningToCompare_FSL
  3. A Structured Self-attentive Sentence Embedding https://arxiv.org/abs/1703.03130 https://github.com/kaushalshetty/Structured-Self-Attention
  4. corpus https://github.com/fate233/toutiao-multilevel-text-classfication-dataset
  5. char_vector https://github.com/Embedding/Chinese-Word-Vectors
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].