no code implementations • EMNLP 2021 • Zhiyuan Ma, Jianjun Li, Zezheng Zhang, GuoHui Li, Yongjing Cheng
Based on such a mechanism, we further propose an intention reasoning network (IR-Net), which consists of joint and multi-hop reasoning, to obtain intention-aware representations of conceptual tokens that can be used to capture the concept shifts involved in task-oriented conversations, so as to effectively identify user’s intention and generate more accurate responses.
no code implementations • ACL 2022 • Zhiyuan Ma, Jianjun Li, GuoHui Li, Yongjing Cheng
Specifically, we first embed the multimodal features into a unified Transformer semantic space to prompt inter-modal interactions, and then devise a feature alignment and intention reasoning (FAIR) layer to perform cross-modal entity alignment and fine-grained key-value reasoning, so as to effectively identify user’s intention for generating more accurate responses.
no code implementations • COLING 2022 • Zhiyuan Ma, Jianjun Li, GuoHui Li, Yongjing Cheng
Accurate fact verification depends on performing fine-grained reasoning over crucial entities by capturing their latent logical relations hidden in multiple evidence clues, which is generally lacking in existing fact verification models.
1 code implementation • 26 Mar 2024 • Yabin Zhang, Wenjie Zhu, Hui Tang, Zhiyuan Ma, Kaiyang Zhou, Lei Zhang
In this paper, we introduce a versatile adaptation approach that can effectively work under all three settings.
1 code implementation • 8 Feb 2024 • Zhiyuan Ma, Xiangyu Zhu, GuoJun Qi, Chen Qian, Zhaoxiang Zhang, Zhen Lei
We suspect this is due to a shortage of paired audio-4D data, which is crucial for the Transformer to effectively perform as a denoiser within the Diffusion framework.
no code implementations • 2 Feb 2024 • Guanwen Feng, Haoran Cheng, Yunan Li, Zhiyuan Ma, Chaoneng Li, Zhihao Qian, Qiguang Miao, Chi-Man Pun
Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix.
no code implementations • 16 Jan 2024 • Xinwei Long, Jiali Zeng, Fandong Meng, Zhiyuan Ma, Kaiyan Zhang, BoWen Zhou, Jie zhou
Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications.
1 code implementation • 13 Dec 2023 • Zhiyuan Ma, zhihuan yu, Jianjun Li, BoWen Zhou
Then, we combine the advantages of MAEs and DPMs to design a progressive masking diffusion model, which gradually increases the masking proportion by three different schedulers and reconstructs the latent features from simple to difficult, without sequentially performing denoising diffusion as in DPMs or using fixed high masking ratio as in MAEs, so as to alleviate the high training time-consumption predicament.
1 code implementation • 13 Dec 2023 • Zhiyuan Ma, Guoli Jia, BoWen Zhou
With the great success of text-conditioned diffusion models in creative text-to-image generation, various text-driven image editing approaches have attracted the attentions of many researchers.
no code implementations • 5 Jun 2023 • Yongqi Dong, KeJia Chen, Zhiyuan Ma
This study systematically compares semi-supervised learning methods applied for anomaly detection in hydraulic condition monitoring systems.
1 code implementation • CVPR 2023 • Zhiyuan Ma, Xiangyu Zhu, GuoJun Qi, Zhen Lei, Lei Zhang
In this paper, we propose One-shot Talking face Avatar (OTAvatar), which constructs face avatars by a generalized controllable tri-plane rendering solution so that each personalized avatar can be constructed from only one portrait as the reference.
no code implementations • 21 Jul 2022 • Yongqi Dong, KeJia Chen, Yinxuan Peng, Zhiyuan Ma
To enhance the security of in-vehicle networks and promote the research in this area, based upon a large scale of CAN network traffic data with the extracted valuable features, this study comprehensively compared fully-supervised machine learning with semi-supervised machine learning methods for CAN message anomaly detection.
1 code implementation • 27 Jul 2021 • Song Tang, Yan Yang, Zhiyuan Ma, Norman Hendrich, Fanyu Zeng, Shuzhi Sam Ge, ChangShui Zhang, Jianwei Zhang
To reach this goal, we construct the nearest neighborhood for every target data and take it as the fundamental clustering unit by building our objective on the geometry.
no code implementations • 2 Sep 2019 • Jiaying Zhang, Zhixing Zhang, Huanhuan Zhang, Zhiyuan Ma, Yangming Zhou, Ping He
Afterwards, both semantic and structure embeddings are combined to measure the relevancy between the terminology and the entity.
no code implementations • 22 Aug 2019 • Tingting Cai, Zhiyuan Ma, Hong Zheng, Yangming Zhou
Meanwhile, to minimize the computational cost of learning, we propose a joint model including a word segmenter and a loss prediction model.
1 code implementation • 21 Aug 2019 • Kui Xue, Yangming Zhou, Zhiyuan Ma, Tong Ruan, Huanhuan Zhang, Ping He
Entity and relation extraction is the necessary step in structuring medical text.
no code implementations • 20 Aug 2019 • Liang Zhao, Zhiyuan Ma, Yangming Zhou, Kai Wang, Shengping Liu, Ju Gao
Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which could lead to severe damages to both patients and hospital services.
no code implementations • 19 Aug 2019 • Jiahui Qiu, Yangming Zhou, Zhiyuan Ma, Tong Ruan, Jinlin Liu, Jing Sun
Clinical text structuring is a critical and fundamental task for clinical research.
no code implementations • 10 Sep 2018 • Zhiyuan Ma, Ping Wang, Zehui Gao, Ruobing Wang, Koroush Khalighi
Here, we present novel algorithms using stacked generalization frameworks to estimate the warfarin dose, within which different types of machine learning algorithms function together through a meta-machine learning model to maximize the prediction accuracy.