• Corpus ID: 67856277

Few-Shot Text Classification with Induction Network

@article{Geng2019FewShotTC,
  title={Few-Shot Text Classification with Induction Network},
  author={Ruiying Geng and Binhua Li and Yongbin Li and Yuxiao Ye and Ping Jian and Jian Sun},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.10482}
}
Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies often use meta learning to simulate the few-shot task, in which new queries are compared to a small support set on a sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and… 
Improving Few-shot Text Classification via Pretrained Language Representations
TLDR
It is suggested that pretraining could be a promising solution for few shot learning of many other NLP tasks and produces state-of-the-art performance on a well-studied sentiment classification dataset.
When Low Resource NLP Meets Unsupervised Language Model: Meta-Pretraining then Meta-Learning for Few-Shot Text Classification (Student Abstract)
TLDR
This paper addresses text classification problems using meta-learning and unsupervised language models using pretraining and shows that this approach is not only simple but also produces a state-of-the-art performance on a well-studied sentiment classification dataset.
Few-shot Text Classification with Distributional Signatures
TLDR
This paper demonstrates that this model consistently outperforms prototypical networks learned on lexical knowledge in both few-shot text classification and relation classification by a significant margin across six benchmark datasets.
Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
TLDR
A novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different undefined classes from the other class to improve few-shot NER and improve the discriminative ability of NER classifier.
Learning to Classify Intents and Slot Labels Given a Handful of Examples
TLDR
A new few-shot learning task is proposed to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios, and it is demonstrated that joint training as well as the use of pre-trained language models are complementary to these few- shot learning methods and yield further gains.
Integrating Bi-Dynamic Routing Capsule Network with Label-Constraint for Text classification
TLDR
A Bi-dynamic routing Capsule Network with Label-constraint (BCNL) model for text classification, which moves beyond the limitations of previous methods by automatically learning the task-relevant and label-relevant words of text.
Reconstructing Capsule Networks for Zero-shot Intent Classification
TLDR
This work proposes to reconstruct capsule networks for zero-shot intent classification by introducing a dimensional attention mechanism to fight against polysemy and reconstruct the transformation matrices for unseen intents by utilizing abundant latent information of the labeled utterances, which significantly improves the model generalization ability.
ConvProtoNet: Deep Prototype Induction towards Better Class Representation for Few-Shot Malware Classification
TLDR
This paper designs a convolutional induction module to replace the insufficient prototype reduction in most few-shot models and generates more appropriate class-level malware prototypes for classification and adopts meta-learning scheme to make classifier robust enough to adapt unseen malware classes without fine-tuning.
Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models
TLDR
This work studies the problem of information extraction from visually rich documents (VRDs) and presents a model that combines the power of large pre-trained language models and graph neural networks to efficiently encode both textual and visual information in business documents.
Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation
  • Peipeng Wang, Xiuguo Zhang, Zhiying Cao
  • Applied Sciences
  • 2021
The task of charge prediction is to predict the charge based on the fact description. Existing methods have a good effect on the prediction of high-frequency charges, but the prediction of
...
1
2
...

References

SHOWING 1-10 OF 25 REFERENCES
Diverse Few-Shot Text Classification with Multiple Metrics
TLDR
This work proposes an adaptive metric learning approach that automatically determines the best weighted combination from a set of metrics obtained from meta-training tasks for a newly seen few-shot task.
Learning to Compare: Relation Network for Few-Shot Learning
TLDR
A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
Prototypical Networks for Few-shot Learning
TLDR
This work proposes Prototypical Networks for few-shot classification, and provides an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning.
Matching Networks for One Shot Learning
TLDR
This work employs ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories to learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types.
A Simple Neural Attentive Meta-Learner
TLDR
This work proposes a class of simple and generic meta-learner architectures that use a novel combination of temporal convolutions and soft attention; the former to aggregate information from past experience and the latter to pinpoint specific pieces of information.
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
TLDR
This work extends to sentiment classification the recently-proposed structural correspondence learning (SCL) algorithm, reducing the relative error due to adaptation between domains by an average of 30% over the original SCL algorithm and 46% over a supervised baseline.
Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces
TLDR
This paper develops few- and zero-shot methods for multi-label text classification when there is a known structure over the label space, and evaluates them on two publicly available medical text datasets: MIMIC II and MIMic III.
Unsupervised Domain Adaptation with Residual Transfer Networks
TLDR
Empirical evidence shows that the new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeledData in the target domain outperforms state of the art methods on standard domain adaptation benchmarks.
Zero-shot User Intent Detection via Capsule Neural Networks
TLDR
Two capsule-based architectures are proposed: IntentC CapsNet that extracts semantic features from utterances and aggregates them to discriminate existing intents, and IntentCapsNet-ZSL which gives IntentCpsNet the zero-shot learning ability to discriminate emerging intents via knowledge transfer from existing intent.
...
1
2
3
...