论文标题
学会对少数示例进行分类和插槽标签进行分类
Learning to Classify Intents and Slot Labels Given a Handful of Examples
论文作者
论文摘要
意图分类（IC）和插槽填充（SF）是大多数面向目标的对话系统中的核心组件。当每个课程的训练示例数量很少时，当前的IC/SF模型的性能很差。我们提出了一项新的几次学习任务，几乎没有IC/SF，以研究和改善IC和SF模型在超低资源场景中未见的课程中的IC和SF模型的性能。我们通过为三个公共IC/SF数据集，ATIS，TOP和SNIPS定义几杆拆分，建立了几个IC/SF基准测试。我们表明，两种流行的少量学习算法，模型不可知的元学习（MAML）和典型网络，在此基准测试中优于微调基线。原型网络在ATI和顶部数据集上的IC性能取得了显着增长，而原型网络和MAML在所有三个数据集上均优于基线相对于SF。此外，我们证明了联合培训以及使用预训练的语言模型，在我们的情况下，Elmo和Bert都与这些少量学习方法相辅相成，并带来了进一步的收益。
Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning task, few-shot IC/SF, to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios. We establish a few-shot IC/SF benchmark by defining few-shot splits for three public IC/SF datasets, ATIS, TOP, and Snips. We show that two popular few-shot learning algorithms, model agnostic meta learning (MAML) and prototypical networks, outperform a fine-tuning baseline on this benchmark. Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets. In addition, we demonstrate that joint training as well as the use of pre-trained language models, ELMo and BERT in our case, are complementary to these few-shot learning methods and yield further gains.
