# A Neural Few-Shot Text Classification Reality Check

arXiv: https://arxiv.org/abs/2101.12073 · HTML: https://mlsanity.com/paper/2101.12073/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 28 Jan 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Benchmarking Natural Language Understanding Services for building Conversational Agents](https://mlsanity.com/paper/1903.05566/) (2019)
- [Induction Networks for Few-Shot Text Classification](https://mlsanity.com/paper/1902.10482/) (2019)
- [Diverse Few-Shot Text Classification with Multiple Metrics](https://mlsanity.com/paper/1805.07513/) (2018)
- [Learning Only from Relevant Keywords and Unlabeled Documents](https://mlsanity.com/paper/1910.04385/) (2019)

## Built on by (most cited first, 6 of 6)

- [ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning](https://mlsanity.com/paper/2105.12995/) (2021)
- [Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation](https://mlsanity.com/paper/2203.11670/) (2022)
- [Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification](https://mlsanity.com/paper/2305.14827/) (2023)
- [ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection](https://mlsanity.com/paper/2108.12229/) (2021)
- [Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification](https://mlsanity.com/paper/2212.10391/) (2022)
- [ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation](https://mlsanity.com/paper/2211.09855/) (2022)

## Abstract (arXiv)

Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision and Natural Language Processing. In the latter, such models used to rely on fixed word embeddings before the advent of transformers. Additionally, some models used in Computer Vision are yet to be tested in NLP applications. In this paper, we compare all these models, first adapting those made in the field of image processing to NLP, and second providing them access to transformers. We then test these models equipped with the same transformer-based encoder on the intent detection task, known for having a large number of classes. Our results reveal that while methods perform almost equally on the ARSC dataset, this is not the case for the Intent Detection task, where the most recent and supposedly best competitors perform worse than older and simpler ones (while all are given access to transformers). We also show that a simple baseline is surprisingly strong. All the new developed models, as well as the evaluation framework, are made publicly available.