no code implementations • 14 Jun 2023 • Weidong Ji, Shijie Zan, Guohui Zhou, Xu Wang
To address the issue of poor generalization ability in end-to-end speech recognition models within deep learning, this study proposes a new Conformer-based speech recognition model called "Conformer-R" that incorporates the R-drop structure.
no code implementations • 14 Jun 2023 • Weidong Ji, Yousheng Zhang, Guohui Zhou, Xu Wang
To enhance the generalization ability of the model and improve the effectiveness of the transformer for named entity recognition tasks, the XLNet-Transformer-R model is proposed in this paper.
no code implementations • 4 Feb 2023 • Weidong Ji, Zengxiang Yin, Guohui Zhou, Yuqi Yue, Xinru Zhang, Chenghong Sun
Translation models tend to ignore the rich semantic information in triads in the process of knowledge graph complementation.
no code implementations • 4 Feb 2023 • Chenghong Sun, Weidong Ji, Guohui Zhou, Hui Guo, Zengxiang Yin, Yuqi Yue
We propose the hypothesis that the key semantic information inside the sentence plays a key role in entity relationship extraction.
no code implementations • 4 Feb 2023 • Yuqi Yue, Xiaoqing Sun, Weidong Ji, Zengxiang Yin, Chenghong Sun
Knowledge tracing aims to model students' past answer sequences to track the change in their knowledge acquisition during exercise activities and to predict their future learning performance.