Jingrui Hou

Jan 3, 2024 | onlinelibrary.wiley.com | Jingrui Hou |Tingting Xu |Bingyan Wang |Haoyuan Yang

Conflict of Interest The authors declare no conflict of interest. Supporting Information Filename Description adfm202312750-sup-0001-SuppMat.pdf3.1 MB Supporting Information adfm202312750-sup-0002-MovieS1.mp41.5 MB Supplemental Movie 1 adfm202312750-sup-0003-MovieS2.mp4372.9 KB Supplemental Movie 2 adfm202312750-sup-0004-MovieS3.mp41.2 MB Supplemental Movie 3 adfm202312750-sup-0005-MovieS4.mp46.1 MB Supplemental Movie 4 References 1a) , , , , , , , Adv. Funct.

Sep 15, 2023 | paperity.org | Jingrui Hou |Ping Wang

PLOS ONE, Jul 2023 As hieroglyphic languages, such as Chinese, differ from alphabetic languages, researchers have always been interested in using internal glyph features to enhance semantic representation. However, the models used in such studies are becoming increasingly computationally expensive, even for simple tasks like text classification. In this paper, we aim to balance model performance and computation cost in glyph-aware Chinese text classification tasks.

Jul 28, 2023 | journals.plos.org | Ping Wang |Jingrui Hou

Sentiment-based text classification experimentNext, we conducted another experiment to analyze the importance of radical features in the sentiment-based Chinese classification task. The results are shown in Table 5. As Table 5 shows, the accuracy rankings of the four base learners are the same as those on the domain-based Chinese text classification task. FastText is better than BI-GRU, and BI-GRU is better than TextCNN and DNN.