.png){kind=icon}
返回
A Contrastive learning-based Task Adaptation model for few-shot intent recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2021.102863.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Few-shot intent recognition aims to identify user's intent from the utterance with limited training data. A considerable number of existing methods mainly rely on the generic knowledge acquired on the base classes to identify the novel classes. Such methods typically ignore the characteristics of each meta task itself, resulting in the inability to make full use of limited given samples when classifying unseen classes. To deal with such issues, we propose a Contrastive learning-based Task Adaptation model (CTA) for few-shot intent recognition. In detail, we leverage contrastive learning to help achieve task adaptation and make full use of the limited samples of novel classes. First, a self-attention layer is employed in the task adaptation module, which aims to establish interactions between samples of different categories so that new representations are task-specific rather than relying entirely on the base classes. Then, the contrastive-based loss functions and the semantics of the label name are respectively used for reducing the similarity between sample representations in different categories while increasing it in the same categories. Experimental results on a public dataset OOS verify the effectiveness of our proposal by beating the competitive baselines in terms of accuracy. Besides, we conduct the cross-domain experiments on three datasets, i.e., OOS, SNIPS as well as ATIS. We find that CTA gains obvious improvements in terms of accuracy in all cross-domain experiments, indicating that it has a better generalization ability than other competitive baselines in both cross-domain and single-domain settings.
Keyword:
Intent recognition
Few-shot learning
Contrastive learning
期刊
I
IF:
6.9
论文数:
5.2K
被引数:
1.4W
机构
引用论文
Pre-train, Interact, Fine-tune: a novel interaction representation for text classification预训练，交互，微调: 一种新颖的文本分类交互表示
OAAI
OAAI分享收藏分享收藏
Subduction-related hybridization of the lithospheric mantle revealed by trace element and Sr-Nd-Pb isotopic data in composite xenoliths from Tallante (Betic Cordillera, Spain)塔兰特 (西班牙Betic Cordillera) 复合异种岩中的微量元素和sr-nd-pb同位素数据揭示了岩石圈地幔的俯冲相关杂交.png)
LithosOAAI
LithosIF0
OAAI分享收藏
查看更多内容