no code implementations • 21 Mar 2024 • Ming Cai, Hisayuki Hara
However, when the sample size is small relative to the number of variables, the accuracy of estimating causal graphs using existing methods decreases.
1 code implementation • 7 Mar 2024 • Ang Li, Qiangchao Chen, Yiquan Wu, Ming Cai, Xiang Zhou, Fei Wu, Kun Kuang
In this paper, we introduce a novel From Graph to Word Bag (FWGB) approach, which introduces domain knowledge regarding constituent elements to guide the model in making judgments on confusing charges, much like a judge's reasoning process.
1 code implementation • 7 Mar 2024 • Ang Li, Yiquan Wu, Yifei Liu, Fei Wu, Ming Cai, Kun Kuang
Court View Generation (CVG) is a challenging task in the field of Legal Artificial Intelligence (LegalAI), which aims to generate court views based on the plaintiff claims and the fact descriptions.
1 code implementation • 5 Jun 2023 • Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Zhilin Gong, Ming Cai, Tianxiang Wang
We adopt usage-based construction grammar as the basis of our work, which is highly compatible with statistical models such as PLMs.
2 code implementations • 22 Oct 2022 • Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Jiayu Fu, Ming Cai
Grammatical Error Correction (GEC) has been broadly applied in automatic correction and proofreading system recently.
Ranked #1 on Grammatical Error Correction on FCGEC
1 code implementation • 27 Apr 2022 • Lvxiaowei Xu, Xiaoxuan Pang, Jianwang Wu, Ming Cai, Jiawei Peng
Aspect-level sentiment analysis aims to determine the sentiment polarity towards a specific target in a sentence.
Ranked #1 on Aspect-Based Sentiment Analysis (ABSA) on Rest16
no code implementations • 7 Mar 2021 • Huimin Huang, Ming Cai, Lanfen Lin, Jing Zheng, Xiongwei Mao, Xiaohan Qian, Zhiyi Peng, Jianying Zhou, Yutaro Iwamoto, Xian-Hua Han, Yen-Wei Chen, Ruofeng Tong
Our Graph- PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance.
no code implementations • 27 Feb 2021 • Yingying Xu, Ming Cai, Lanfen Lin, Yue Zhang, Hongjie Hu, Zhiyi Peng, Qiaowei Zhang, Qingqing Chen, Xiongwei Mao, Yutaro Iwamoto, Xian-Hua Han, Yen-Wei Chen, Ruofeng Tong
In this paper, we propose a phase attention residual network (PA-ResSeg) to model multi-phase features for accurate liver tumor segmentation, in which a phase attention (PA) is newly proposed to additionally exploit the images of arterial (ART) phase to facilitate the segmentation of portal venous (PV) phase.
no code implementations • CVPR 2020 • Ming Cai, Ian Reid
If a CAD model is not available, it is possible to use multi-view visual reconstruction methods to create a geometric model, and use this in the same manner.
no code implementations • 29 Nov 2018 • Kejie Li, Ravi Garg, Ming Cai, Ian Reid
3D shape reconstruction from a single image is a highly ill-posed problem.
no code implementations • 27 Aug 2018 • Ke Ning, Linchao Zhu, Ming Cai, Yi Yang, Di Xie, Fei Wu
We validate the effectiveness of our ASST on two large-scale datasets.
no code implementations • 28 Feb 2018 • Thanh-Toan Do, Ming Cai, Trung Pham, Ian Reid
Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications.