Composed Variational Natural Language Generation for Few-shot Intents
arXiv:2009.10056
Abstract
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.
arXiv comment10 pages, accepted to Findings of EMNLP 2020
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Prototypical Networks for Few-shot Learning
- Unified Language Model Pre-training for Natural Language Understanding and Generation
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
- EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Toward Controlled Generation of Text
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation
- Zero-Shot Learning -- The Good, the Bad and the Ugly
- Meta-learning for Few-shot Natural Language Processing: A Survey
- Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
- CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
- Zero-shot User Intent Detection via Capsule Neural Networks