Hierarchical text classification (HTC) is essential for various real applications. However, HTC models are challenging to develop because they often require processing a large volume of documents and labels with hierarchical taxonomy. Recent HTC models based on deep learning have attempted to incorporate hierarchy information into a model structure. Consequently, these models are challenging to implement when the model parameters increase for a large-scale hierarchy because the model structure depends on the hierarchy size. To solve this problem, we formulate HTC as a sub-hierarchy sequence generation to incorporate hierarchy information into a target label sequence instead of the model structure. Subsequently, we propose the Hierarchy DECoder (HiDEC), which decodes a text sequence into a sub-hierarchy sequence using recursive hierarchy decoding, classifying all parents at the same level into children at once. In addition, HiDEC is trained to use hierarchical path information from a root to each leaf in a sub-hierarchy composed of the labels of a target document via an attention mechanism and hierarchy-aware masking. HiDEC achieved state-of-the-art performance with significantly fewer model parameters than existing models on benchmark datasets, such as RCV1-v2, NYT, and EURLEX57K.

No abstract

This study aims to extract the most relevant set consisted of affective variables to the level of user satisfaction on engine sounds using classification algorithm. The affective variables for engine sounds were defined by three axes, and two classification algorithms were used to determine the prediction accuracy for those affective axes. The study was consisted of three phases: 1) extracting sets of affective variables and the level of satisfaction on engine sounds, 2) preprocessing of engine sounds and experiment design, and 3) analysis of the most relevant sets of affective variables to user satisfaction. As a result, PA (PowerfulAffective) variable set showed the highest prediction accuracy of user satisfaction compared to other sets. Predicting the level of satisfaction based on classification algorithm could help to generalize the relationship between user satisfaction and affective variables more easily, beyond the limitation with a small size of subjects.

No abstract