Quaternion Convolutional Neural Networks For Theme Identification Of Telephone Conversations.
SLT(2018)
摘要
Quaternion convolutional neural networks (QCNN) are powerful architectures to learn and model external dependencies that exist between neighbor features of an input vector, and internal latent dependencies within the feature. This paper proposes to evaluate the effectiveness of the QCNN on a realistic theme identification task of spoken telephone conversations between agents and customers from the call center of the Paris transportation system (RATP). We show that QCNNs are more suitable than real-valued CNN to process multidimensional data and to code internal dependencies. Indeed, real-valued CNNs deal with both internal and external relations at the same level since components of an entity are processed independently. Experimental evidence is provided that the proposed QCNN architecture always outperforms real-valued equivalent CNN models in the theme identification task of the DECODA corpus. It is also shown that QCNN accuracy results are the best achieved so far on this task, while reducing by a factor of 4 the number of model parameters.
更多查看译文
关键词
Quaternions,Task analysis,Convolution,Telephone sets,Adaptation models,Convolutional neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络