Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
复制标题
DOI：
10.18653/v1/2021.emnlp-main.144
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Jianguo Zhang;Trung Bui;Seunghyun Yoon;Xiang Chen;Zhiwei Liu;Congying Xia;Quan Hung Tran;Walter Chang;P. Yu
中科院分区：
文献类型：
--
作者：
Jianguo Zhang;Trung Bui;Seunghyun Yoon;Xiang Chen;Zhiwei Liu;Congying Xia;Quan Hung Tran;Walter Chang;P. Yu
在这项工作中，我们专注于一个更具挑战性的少数镜头意图检测的情况下，许多意图是细粒度和语义相似。我们通过对比预训练和微调提出了一个简单而有效的少量意图检测方案。具体来说，我们首先对收集到的意图数据集进行自我监督的对比预训练，隐式学习在不使用任何标签的情况下区分语义相似的话语。然后，我们执行少数镜头意图检测与监督对比学习，这明确地拉从相同的意图更接近的话语，并推动不同的意图更远的话语。实验结果表明，我们提出的方法在5次和10次设置下在三个具有挑战性的意图检测数据集上实现了最先进的性能。
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tuning. Specifically, we first conduct self-supervised contrastive pre-training on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot settings.