Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks

@inproceedings{Bansal2020LearningTF,
  title={Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks},
  author={Trapit Bansal and Rishi Jha and Andrew McCallum},
  booktitle={COLING},
  year={2020}
}
Pre-trained transformer models have shown enormous success in improving performance on several downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labeled data to achieve good performance. We consider this problem of learning to generalize to new tasks, with a few examples, as a meta-learning problem. While meta-learning has shown tremendous progress in recent years, its application is still limited to simulated problems or problems with limited… Expand
Meta-learning for Few-shot Natural Language Processing: A Survey
TLDR
This paper tries to provide clearer definitions, progress summary and some common datasets of applying meta-learning to few-shot NLP domain, especially few- shot applications. Expand
Adaptive Self-training for Few-shot Neural Sequence Labeling
TLDR
Self-training and meta-learning techniques for few-shot training of neural sequence taggers, namely MetaST are developed that help in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels. Expand
Zero-shot Text Classification With Generative Language Models
TLDR
This work investigates the use of natural language to enable zero-shot model adaptation to new tasks, using text and metadata from social commenting platforms as a source for a simple pretraining task and shows that natural language can serve as simple and powerful descriptors for task adaptation. Expand
Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
TLDR
This paper proposes an algorithm that can customize a unique dialogue model for each task in the few-shot setting and shows that this method outperforms all the baselines in terms of task consistency, response quality, and diversity. Expand
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
TLDR
This work demonstrates that this framework enables a pretrained entailment model to work well on new entailment domains in a few-shot setting, and shows its effectiveness as a unified solver for several downstream NLP tasks such as question answering and coreference resolution when the end-task annotations are limited. Expand
Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling
TLDR
This work augments a deep neural network with a layer-specific fast-weight memory, generated sparsely at each time step and accumulated incrementally through time providing a useful inductive bias for online continual adaptation. Expand
Contextual Lensing of Universal Sentence Representations
TLDR
This work breaks the construction of universal sentence vectors into a core, variable length, sentence matrix representation equipped with an adaptable `lens' from which fixed-length vectors can be induced as a function of the lens context to demonstrate the ability to encode translation similarity of sentences across several languages into a single weight matrix. Expand
Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
TLDR
A novel meta-learning latent variable approach, called MetaBridge, is proposed, which can learn transferable knowledge from a subset of categories with limited labeled data and capture the uncertainty of never-seen categories with unlabeled data and integrate meta learning and latent variable in a unified model to effectively capture the Uncertainty of various categories. Expand
Meta-learning with few-shot models Analysis Final Project
This project focuses on understanding the various elements of Meta-learning and few-shot models and the effectiveness of the different detailed implementation approaches. Using the default RobustQAExpand
DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference
TLDR
DReCA (Decomposing datasets into Reasoning Categories), a simple method for discovering and using latent reasoning categories in a dataset, to form additional high quality tasks to improve the accuracy of meta-learners. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 82 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. Expand
Induction Networks for Few-Shot Text Classification
TLDR
This paper proposes a novel Induction Network to learn a generalized class-wise representation of each class in the support set, by innovatively leveraging the dynamic routing algorithm in meta-learning and finds the model is able to induce and generalize better. Expand
Language Models are Unsupervised Multitask Learners
TLDR
It is demonstrated that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText, suggesting a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations. Expand
Multi-Task Deep Neural Networks for Natural Language Understanding
TLDR
A Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks that allows domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations. Expand
Universal Language Model Fine-tuning for Text Classification
TLDR
This work proposes Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduces techniques that are key for fine- Tuning a language model. Expand
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
TLDR
This work proposes Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks, and proposes a new set of baselines for quantifying the benefit of meta-learning in Meta- Dataset. Expand
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. Expand
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
TLDR
Empirical results show that even the most competitive few- shot learning models struggle on this task, especially as compared with humans, and indicate that few-shot relation classification remains an open problem and still requires further research. Expand
Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks
TLDR
The benefits of supplementary training with further training on data-rich supervised tasks, such as natural language inference, obtain additional performance improvements on the GLUE benchmark, as well as observing reduced variance across random restarts in this setting. Expand
...
1
2
3
4
5
...