# Composed Variational Natural Language Generation for Few-shot Intents

arXiv: https://arxiv.org/abs/2009.10056 · HTML: https://mlsanity.com/paper/2009.10056/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 19 of 19)

- [GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://mlsanity.com/paper/2104.08826/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Federated Social Recommendation with Graph Neural Network](https://mlsanity.com/paper/2111.10778/) (2021)
- [Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning](https://mlsanity.com/paper/2109.06349/) (2021)
- [Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer](https://mlsanity.com/paper/2105.00522/) (2021)
- [Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System](https://mlsanity.com/paper/2104.11882/) (2021)
- [Effectiveness of Pre-training for Few-shot Intent Classification](https://mlsanity.com/paper/2109.05782/) (2021)
- [Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization](https://mlsanity.com/paper/2205.07208/) (2022)
- [Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System](https://mlsanity.com/paper/2205.04006/) (2022)
- [Pseudo Siamese Network for Few-shot Intent Generation](https://mlsanity.com/paper/2105.00896/) (2021)
- [A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection](https://mlsanity.com/paper/2109.01267/) (2021)
- [Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots](https://mlsanity.com/paper/2203.00732/) (2022)
- [Template-based Approach to Zero-shot Intent Recognition](https://mlsanity.com/paper/2206.10914/) (2022)
- [Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training](https://mlsanity.com/paper/2306.05278/) (2023)
- [Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation](https://mlsanity.com/paper/2308.01080/) (2023)
- [A Unified Causal View of Instruction Tuning](https://mlsanity.com/paper/2402.06220/) (2024)
- [Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detection](https://mlsanity.com/paper/2112.07434/) (2021)
- [Inducing Causal Structure for Abstractive Text Summarization](https://mlsanity.com/paper/2308.12888/) (2023)
- [Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents](https://mlsanity.com/paper/2403.15765/) (2024)

## Abstract (arXiv)

In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-shot intents, we consider an intent as a combination of a domain and an action, and propose a composed variational natural language generator (CLANG), a transformer-based conditional variational autoencoder. CLANG utilizes two latent variables to represent the utterances corresponding to two different independent parts (domain and action) in the intent, and the latent variables are composed together to generate natural examples. Additionally, to improve the generator learning, we adopt the contrastive regularization loss that contrasts the in-class with the out-of-class utterance generation given the intent. To evaluate the quality of the generated utterances, experiments are conducted on the generalized few-shot intent detection task. Empirical results show that our proposed model achieves state-of-the-art performances on two real-world intent detection datasets.