论文标题
构成的自然语言生成几乎没有镜头
Composed Variational Natural Language Generation for Few-shot Intents
论文作者
论文摘要
在本文中，我们专注于在现实的不平衡情况下生成训练示例。为了在现有的许多镜头意图和几乎没有射击意图之间建立连接，我们将意图视为域和动作的组合，并提出了一个组成的变异自然语言生成器（Clang），这是一种基于变压器的条件变异自动编码器。 Clang利用两个潜在变量表示意图中对应于两个不同的独立部分（域和动作）的话语，并且潜在变量组成在一起以生成自然示例。此外，为了改善发电机的学习，我们采用了对比的正规化损失，将室内与室外的话语产生形成鲜明对比。为了评估生成的话语的质量，对广义的少数射击意图任务进行了实验。经验结果表明，我们提出的模型可以在两个现实世界中的检测数据集上实现最先进的性能。
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.
