# Few-shot Text Classification with Distributional Signatures

arXiv: https://arxiv.org/abs/1908.06039 · HTML: https://mlsanity.com/paper/1908.06039/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 30 of 58)

- [AugGPT: Leveraging ChatGPT for Text Data Augmentation](https://mlsanity.com/paper/2302.13007/) (2023)
- [Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2108.13161/) (2021)
- [FLEX: Unifying Evaluation for Few-Shot NLP](https://mlsanity.com/paper/2107.07170/) (2021)
- [CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning](https://mlsanity.com/paper/2109.07589/) (2021)
- [Few-shot Conformal Prediction with Auxiliary Tasks](https://mlsanity.com/paper/2102.08898/) (2021)
- [Meta-Learning with Fewer Tasks through Task Interpolation](https://mlsanity.com/paper/2106.02695/) (2021)
- [A Survey on Data Augmentation in Large Model Era](https://mlsanity.com/paper/2401.15422/) (2024)
- [Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes](https://mlsanity.com/paper/2104.08481/) (2021)
- [Revisiting Self-Training for Few-Shot Learning of Language Model](https://mlsanity.com/paper/2110.01256/) (2021)
- [Label Semantics for Few Shot Named Entity Recognition](https://mlsanity.com/paper/2203.08985/) (2022)
- [Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning](https://mlsanity.com/paper/2311.03748/) (2023)
- [MetaPrompting: Learning to Learn Better Prompts](https://mlsanity.com/paper/2209.11486/) (2022)
- [Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification](https://mlsanity.com/paper/2107.12262/) (2021)
- [Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes](https://mlsanity.com/paper/2208.08023/) (2022)
- [ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification](https://mlsanity.com/paper/2305.09269/) (2023)
- [Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning](https://mlsanity.com/paper/2110.09446/) (2021)
- [Effective Structured Prompting by Meta-Learning and Representative Verbalizer](https://mlsanity.com/paper/2306.00618/) (2023)
- [Semantic-aligned Fusion Transformer for One-shot Object Detection](https://mlsanity.com/paper/2203.09093/) (2022)
- [Facilitating Knowledge Sharing from Domain Experts to Data Scientists for Building NLP Models](https://mlsanity.com/paper/2102.00036/) (2021)
- [Prompt-Based Metric Learning for Few-Shot NER](https://mlsanity.com/paper/2211.04337/) (2022)
- [TAPE: Assessing Few-shot Russian Language Understanding](https://mlsanity.com/paper/2210.12813/) (2022)
- [Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection](https://mlsanity.com/paper/2303.02513/) (2023)
- [Knowledge-Aware Meta-learning for Low-Resource Text Classification](https://mlsanity.com/paper/2109.04707/) (2021)
- [Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks](https://mlsanity.com/paper/2109.09366/) (2021)
- [An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling](https://mlsanity.com/paper/2110.13691/) (2021)
- [Provable Generalization of Overparameterized Meta-learning Trained with SGD](https://mlsanity.com/paper/2206.09136/) (2022)
- [ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback](https://mlsanity.com/paper/2107.14035/) (2021)
- [Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation](https://mlsanity.com/paper/2201.11576/) (2022)
- [Label Anchored Contrastive Learning for Language Understanding](https://mlsanity.com/paper/2205.10227/) (2022)
- [Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection](https://mlsanity.com/paper/2206.13980/) (2022)

## Abstract (arXiv)

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).