论文标题
CG-BERT：带有BERT的有条件文本生成，用于广义的少数射击意图检测
CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
论文作者
论文摘要
在本文中，我们为自然语言理解中的意图检测任务制定了一个更现实和困难的问题，即概括的意图检测（GFSID）。 GFSID的目的是区分由现有意图组成的关节标签空间，这些意图具有足够的标记数据和新颖的意图，每班只有几个示例。为了解决这个问题，我们提出了一个新型的模型，即用BERT（CG-BERT）的条件文本生成。 CG-BERT有效利用大型的预训练的语言模型来生成以意图标签为条件的文本。通过用变异推断对话语分布进行建模，CG-Bert即使只有几种话语也可以为新颖意图产生多种话语。实验结果表明，CG-BERT在两个现实世界数据集上使用1-Shot和5-Shot设置在GFSID任务上实现最新性能。
In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detection (GFSID). GFSID aims to discriminate a joint label space consisting of both existing intents which have enough labeled data and novel intents which only have a few examples for each class. To approach this problem, we propose a novel model, Conditional Text Generation with BERT (CG-BERT). CG-BERT effectively leverages a large pre-trained language model to generate text conditioned on the intent label. By modeling the utterance distribution with variational inference, CG-BERT can generate diverse utterances for the novel intents even with only a few utterances available. Experimental results show that CG-BERT achieves state-of-the-art performance on the GFSID task with 1-shot and 5-shot settings on two real-world datasets.
