Composed Variational Natural Language Generation for Few-shot Intents
By Congying Xia, Caiming Xiong, Philip S. Yu, Richard Socher. 2020
31 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System (2021, neutral): “Recently, few-shot text classification (Yu et al., 2018; Geng et al., 2019; Xia et al., 2020a) has attracted increasing attention from the NLP community since it is unlikely to have large-scale labeled data for new classes in the real world.”
- GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation (2021, background): “Some other researchers have taken the direction of perturbing the latent spaces, optionally by introducing variational inference in the architecture (Xia et al., 2020b,a; Hou et al., 2018; Yoo et al., 2019).”