# The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification

arXiv: https://arxiv.org/abs/2210.06440 · HTML: https://mlsanity.com/paper/2210.06440/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces](https://mlsanity.com/paper/1805.10190/) (2018)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks](https://mlsanity.com/paper/1811.01088/) (2018)
- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (2020)
- [Benchmarking Natural Language Understanding Services for building Conversational Agents](https://mlsanity.com/paper/1903.05566/) (2019)
- [DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue](https://mlsanity.com/paper/2009.13570/) (2020)
- [Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey](https://mlsanity.com/paper/2011.00564/) (2020)
- [Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference](https://mlsanity.com/paper/2010.13009/) (2020)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [Learning to Classify Intents and Slot Labels Given a Handful of Examples](https://mlsanity.com/paper/2004.10793/) (2020)
- [Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog](https://mlsanity.com/paper/2205.10400/) (2022)
- [Example-Driven Intent Prediction with Observers](https://mlsanity.com/paper/2010.08684/) (2020)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [ConvFiT: Conversational Fine-Tuning of Pretrained Language Models](https://mlsanity.com/paper/2109.10126/) (2021)
- [Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization](https://mlsanity.com/paper/2205.07208/) (2022)
- [ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning](https://mlsanity.com/paper/2105.12995/) (2021)
- [Label Semantic Aware Pre-training for Few-shot Text Classification](https://mlsanity.com/paper/2204.07128/) (2022)
- [Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection](https://mlsanity.com/paper/2010.02481/) (2020)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [Pseudo Siamese Network for Few-shot Intent Generation](https://mlsanity.com/paper/2105.00896/) (2021)
- [Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/1903.08268/) (2019)

## Built on by (most cited first, 2 of 2)

- [IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery](https://mlsanity.com/paper/2310.16761/) (2023)
- [Pingala: Prosody-Aware Decoding for Sanskrit Poetry Generation](https://mlsanity.com/paper/2603.24413/) (2026)

## Abstract (arXiv)

Few-shot Intent Classification (FSIC) is one of the key challenges in modular task-oriented dialog systems. While advanced FSIC methods are similar in using pretrained language models to encode texts and nearest neighbour-based inference for classification, these methods differ in details. They start from different pretrained text encoders, use different encoding architectures with varying similarity functions, and adopt different training regimes. Coupling these mostly independent design decisions and the lack of accompanying ablation studies are big obstacle to identify the factors that drive the reported FSIC performance. We study these details across three key dimensions: (1) Encoding architectures: Cross-Encoder vs Bi-Encoders; (2) Similarity function: Parameterized (i.e., trainable) functions vs non-parameterized function; (3) Training regimes: Episodic meta-learning vs the straightforward (i.e., non-episodic) training. Our experimental results on seven FSIC benchmarks reveal three important findings. First, the unexplored combination of the cross-encoder architecture (with parameterized similarity scoring function) and episodic meta-learning consistently yields the best FSIC performance. Second, Episodic training yields a more robust FSIC classifier than non-episodic one. Third, in meta-learning methods, splitting an episode to support and query sets is not a must. Our findings paves the way for conducting state-of-the-art research in FSIC and more importantly raise the community's attention to details of FSIC methods. We release our code and data publicly.