no code implementations • NAACL 2022 • Minghao Zhu, Junli Wang, Chungang Yan
Variational Autoencoder (VAE) is an effective framework to model the interdependency for non-autoregressive neural machine translation (NAT).
no code implementations • 17 Apr 2024 • Bin Zhang, Junli Wang
To address these problems, we propose a novel framework based on associated and hierarchical code description distillation (AHDD) for better code representation learning and avoidance of improper code assignment. we utilize the code description and the hierarchical structure inherent to the ICD codes.
no code implementations • 10 Jul 2023 • Mingze Yuan, Yingda Xia, Xin Chen, Jiawen Yao, Junli Wang, Mingyan Qiu, Hexin Dong, Jingren Zhou, Bin Dong, Le Lu, Li Zhang, Zaiyi Liu, Ling Zhang
In our experiments, the proposed method achieves a sensitivity of 85. 0% and specificity of 92. 6% for detecting gastric tumors on a hold-out test set consisting of 100 patients with cancer and 148 normal.
1 code implementation • 23 Nov 2022 • ZiHao Wang, Junli Wang, Changjun Jiang
Prior work performs the standard likelihood training for answer generation on the positive instances (involving correct answers).
no code implementations • 13 Oct 2021 • ZiHao Wang, Ming Jiang, Junli Wang
Differing from prior work that solely relies on the content of conversation history to generate a response, we argue that capturing relative social relations among utterances (i. e., generated by either the same speaker or different persons) benefits the machine capturing fine-grained context information from a conversation history to improve context coherence in the generated response.
no code implementations • 6 Sep 2021 • Kun Zhai, Qiang Ren, Junli Wang, Chungang Yan
Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands.