1 code implementation • 26 May 2023 • Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Lluis Marquez
Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn.
no code implementations • 3 Apr 2023 • Yu Chen, Chao Shang, Xiaolin Huang, Xiang Yin
We first formulate the safety synthesis problem as a robust convex program (RCP) based on notion of control barrier function.
no code implementations • CVPR 2023 • Chao Shang, Hongliang Li, Fanman Meng, Qingbo Wu, Heqian Qiu, Lanxiao Wang
Most existing methods are based on convolutional networks and prevent forgetting through knowledge distillation, which (1) need to add additional convolutional layers to predict new classes, and (2) ignore to distinguish different regions corresponding to old and new classes during knowledge distillation and roughly distill all the features, thus limiting the learning of new classes.
Class-Incremental Semantic Segmentation
Knowledge Distillation
no code implementations • 7 Nov 2022 • Kaixiang Zhang, Yang Zheng, Chao Shang, Zhaojian Li
In this letter, we propose a simple yet effective singular value decomposition (SVD) based strategy to reduce the optimization problem dimension in data-enabled predictive control (DeePC).
no code implementations • ACL 2022 • Chao Shang, Guangtao Wang, Peng Qi, Jing Huang
These questions often involve three time-related challenges that previous work fail to adequately address: 1) questions often do not specify exact timestamps of interest (e. g., "Obama" instead of 2000); 2) subtle lexical differences in time relations (e. g., "before" vs "after"); 3) off-the-shelf temporal KG embeddings that previous work builds on ignore the temporal order of timestamps, which is crucial for answering temporal-order related questions.
Ranked #2 on
Question Answering
on CronQuestions
no code implementations • AKBC 2021 • Chao Shang, Peng Qi, Guangtao Wang, Jing Huang, Youzheng Wu, BoWen Zhou
Understanding the temporal relations among events in text is a critical aspect of reading comprehension, which can be evaluated in the form of temporal question answering (TQA).
1 code implementation • Findings (EMNLP) 2021 • Jieren Deng, Yijue Wang, Ji Li, Chao Shang, Cao Qin, Hang Liu, Sanguthevar Rajasekaran, Caiwen Ding
In this paper, as the first attempt, we formulate the gradient attack problem on the Transformer-based language models and propose a gradient attack algorithm, TAG, to reconstruct the local training data.
Federated Learning
Cryptography and Security
1 code implementation • ICLR 2021 • Chao Shang, Jie Chen, Jinbo Bi
Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model.
no code implementations • ACL 2020 • Chao Shang, Sarthak Dash, Md. Faisal Mahbub Chowdhury, N Mihindukulasooriya, ana, Alfio Gliozzo
However, there has been no attempt to exploit GNN to create taxonomies.
no code implementations • 27 Mar 2019 • Chao Shang, Fengqi You
By synthesizing comprehensive information about support constraints and validation tests, improved risk evaluation can be achieved for randomized solutions in comparison with existing a posteriori bounds.
1 code implementation • 11 Nov 2018 • Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, Bo-Wen Zhou
The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure.
Ranked #26 on
Link Prediction
on FB15k-237
no code implementations • 14 Oct 2018 • Chao Shang, Wei-Han Chen, Abraham Duncan Stroock, Fengqi You
For evapotranspiration forecast error, the support vector clustering-based uncertainty set is adopted, which can be conveniently built from historical data.
1 code implementation • 14 Feb 2018 • Chao Shang, Qinqing Liu, Ko-Shin Chen, Jiangwen Sun, Jin Lu, Jin-Feng Yi, Jinbo Bi
The proposed GCN model, which we call edge attention-based multi-relational GCN (EAGCN), jointly learns attention weights and node features in graph convolution.
1 code implementation • 22 Aug 2017 • Chao Shang, Aaron Palmer, Jiangwen Sun, Ko-Shin Chen, Jin Lu, Jinbo Bi
Especially, when certain samples miss an entire view of data, it creates the missing view problem.