Few-shot Text Classification with Distributional Signatures

Yujia Bao, Menghua Wu, Shiyu Chang, Regina Barzilay
8/16/2019
cs.CLcs.LG

Official code: YujiaBao/Distributional-Signatures (259 stars, MIT, last commit 2020-12-17).

Abstract

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this approach to text is challenging--lexical features highly informative for one task may be insignificant for another. Thus, rather than learning solely from words, our model also leverages their distributional signatures, which encode pertinent word occurrence patterns. Our model is trained within a meta-learning framework to map these signatures into attention scores, which are then used to weight the lexical representations of words. We demonstrate that our model consistently outperforms prototypical networks learned on lexical knowledge (Snell et al., 2017) in both few-shot text classification and relation classification by a significant margin across six benchmark datasets (20.0% on average in 1-shot classification).

View on arXivView PDF

Code Implementations(1)

YujiaBao/Distributional-SignaturesOfficial100%
MIT

"Few-shot Text Classification with Distributional Signatures" ICLR 2020

25954Shell, PythonAug 15, 20195 years agoMIT
few-shot-learningiclr2020machine-learningtext-classification

Similar Papers

Multimodal CLIP Inference for Meta-Few-Shot Image Classification

89% match2024

ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification

88% match1 repo252023

Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning

88% match1 repo612023

Meta-Learning Siamese Network for Few-Shot Text Classification

87% match1 repo112023

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

87% match1 repo582023

Label-template based Few-Shot Text Classification with Contrastive Learning

87% match2024

Cite this paper

@article{bao2019fewshot,
  title  = {Few-shot Text Classification with Distributional Signatures},
  author = {Yujia Bao and Menghua Wu and Shiyu Chang and Regina Barzilay},
  year   = {2019},
  eprint = {1908.06039},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1908.06039}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1908.06039.svg)](https://codeofpaper.com/paper/1908.06039)

Discussion