Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification.

CoRR(2023)

引用 0|浏览61
暂无评分
摘要
Intent classification (IC) plays an important role in task-oriented dialogue systems as it identifies user intents from given utterances. However, models trained on limited annotations for IC often suffer from a lack of generalization to unseen intent classes. We propose a novel pre-training method for text encoders that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks. By applying this pre-training strategy, we also introduce the pre-trained intent-aware encoder (PIE). Specifically, we first train a tagger to identify key phrases within utterances that are crucial for interpreting intents. We then use these extracted phrases to create examples for pre-training a text encoder in a contrastive manner. As a result, our PIE model achieves up to 5.4% and 4.0% higher accuracy than the previous state-of-the-art pre-trained sentence encoder for the N-way zero- and one-shot settings on four IC datasets.
更多
查看译文
关键词
classification,pre-training,intent-aware,few-shot
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要