no code implementations • WMT (EMNLP) 2020 • Minghan Wang, Hao Yang, Hengchao Shang, Daimeng Wei, Jiaxin Guo, Lizhi Lei, Ying Qin, Shimin Tao, Shiliang Sun, Yimeng Chen, Liangyou Li
This paper presents our work in the WMT 2020 Word and Sentence-Level Post-Editing Quality Estimation (QE) Shared Task.
1 code implementation • ICML 2020 • Dejun Chu, Chang-Shui Zhang, Shiliang Sun, Qing Tao
Structured sparsity-inducing $\ell_{1, \infty}$-norm, as a generalization of the classical $\ell_1$-norm, plays an important role in jointly sparse models which select or remove simultaneously all the variables forming a group.
no code implementations • WMT (EMNLP) 2020 • Hao Yang, Minghan Wang, Daimeng Wei, Hengchao Shang, Jiaxin Guo, Zongyao Li, Lizhi Lei, Ying Qin, Shimin Tao, Shiliang Sun, Yimeng Chen
The paper presents the submission by HW-TSC in the WMT 2020 Automatic Post Editing Shared Task.
no code implementations • WMT (EMNLP) 2020 • Daimeng Wei, Hengchao Shang, Zhanglin Wu, Zhengzhe Yu, Liangyou Li, Jiaxin Guo, Minghan Wang, Hao Yang, Lizhi Lei, Ying Qin, Shiliang Sun
We also conduct experiment with similar language augmentation, which lead to positive results, although not used in our submission.
no code implementations • EAMT 2020 • Minghan Wang, Hao Yang, Ying Qin, Shiliang Sun, Yao Deng
We propose a unified multilingual model for humor detection which can be trained under a transfer learning framework.
no code implementations • 17 Oct 2023 • Chaoyue Ding, Shiliang Sun, Jing Zhao
Multimodal time series (MTS) anomaly detection is crucial for maintaining the safety and stability of working devices (e. g., water treatment system and spacecraft), whose data are characterized by multivariate time series with diverse modalities.
no code implementations • 10 Dec 2020 • Daoming Zong, Shiliang Sun
Extreme multi-label text classification (XMTC) aims to tag a text instance with the most relevant subset of labels from an extremely large label set.
no code implementations • 23 Nov 2020 • Yang Zhou, Shiliang Sun
We propose a novel algorithm for supervised dimensionality reduction named Manifold Partition Discriminant Analysis (MPDA).
no code implementations • 19 Jun 2020 • Xuli Sun, Shiliang Sun
With the mild assumption that the single-view model on which the target multi-view model is based is known, we first propose the TSA strategy.
no code implementations • 25 Nov 2019 • Ziang Dong, Liang Mao, Shiliang Sun
We propose a generative model for adversarial attack.
no code implementations • ACL 2019 • Changzhi Sun, Yeyun Gong, Yuanbin Wu, Ming Gong, Daxin Jiang, Man Lan, Shiliang Sun, Nan Duan
We develop a new paradigm for the task of joint entity relation extraction.
Ranked #1 on Relation Extraction on ACE 2005 (Sentence Encoder metric)
no code implementations • 17 Jun 2019 • Shiliang Sun, Zehui Cao, Han Zhu, Jing Zhao
Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields.
no code implementations • 9 Jun 2019 • Jing Zhao, Jingjing Fei, Shiliang Sun
In order to better model high-dimensional sequential data, we propose a collaborative multi-output Gaussian process dynamical system (CGPDS), which is a novel variant of GPDSs.
no code implementations • 1 Jun 2019 • Minghao Gu, Shiliang Sun
The Hamiltonian Monte Carlo (HMC) sampling algorithm exploits Hamiltonian dynamics to construct efficient Markov Chain Monte Carlo (MCMC), which has become increasingly popular in machine learning and statistics.
no code implementations • 14 May 2019 • Jingjing Fei, Shiliang Sun
Moreover, the SGP-Q makes use of few abnormal data in the training data by its strategy of updating training data, resulting in more accurate sparse Gaussian process regression models and better anomaly detection results.
no code implementations • EMNLP 2018 • Changzhi Sun, Yuanbin Wu, Man Lan, Shiliang Sun, Wenting Wang, Kuang-Chih Lee, Kewen Wu
We investigate the task of joint entity relation extraction.
Ranked #1 on Relation Extraction on ACE 2005 (Sentence Encoder metric)
no code implementations • NeurIPS 2018 • Omar Rivasplata, Emilio Parrado-Hernandez, John Shawe-Taylor, Shiliang Sun, Csaba Szepesvari
Our main result estimates the risk of the randomized algorithm in terms of the hypothesis stability coefficients.
no code implementations • 25 Dec 2017 • Rongqing Huang, Shiliang Sun
Generally, the function value for a test input is estimated by a weighted average of the surrounding training examples.
no code implementations • 25 Dec 2017 • Shiliang Sun, Rongqing Huang, Ya Gao
In this paper, we apply GPR to traffic flow forecasting and show its potential.
no code implementations • 24 Dec 2017 • Shiliang Sun, Chang-Shui Zhang, Yi Zhang
A novel predictor for traffic flow forecasting, namely spatio-temporal Bayesian network predictor, is proposed.
no code implementations • 24 Dec 2017 • Qingjiu Zhang, Shiliang Sun
Artificial neural network (ANN) is a very useful tool in solving learning problems.
no code implementations • 24 Dec 2017 • Feng Jin, Shiliang Sun
Traditional neural network approaches for traffic flow forecasting are usually single task learning (STL) models, which do not take advantage of the information provided by related tasks.
no code implementations • 18 Dec 2017 • Guoqing Chao, Shiliang Sun, Jinbo Bi
With advances in information acquisition technologies, multi-view data become ubiquitous.
no code implementations • NeurIPS 2017 • Yuanbin Wu, Man Lan, Shiliang Sun, Qi Zhang, Xuanjing Huang
In this work, we try to understand the differences between exact and approximate inference algorithms in structured prediction.
no code implementations • 2 Jul 2017 • Shiliang Sun, John Paisley, Qiuyang Liu
Dirichlet processes (DP) are widely applied in Bayesian nonparametric modeling.
no code implementations • EACL 2017 • Changzhi Sun, Yuanbin Wu, Man Lan, Shiliang Sun, Qi Zhang
We investigate the task of open domain opinion relation extraction.
no code implementations • 17 Jan 2017 • Qiuyang Liu, Shiliang Sun
Moreover, we give a general point selection scheme for multi-view learning and improve the proposed model by this criterion.
no code implementations • 21 Jun 2014 • Shiliang Sun, John Shawe-Taylor, Liang Mao
This paper presents eight PAC-Bayes bounds to analyze the generalization performance of multi-view classifiers.
no code implementations • 26 Jul 2013 • Shiliang Sun
This paper presents a new model called infinite mixtures of multivariate Gaussian processes, which can be used to learn vector-valued functions and applied to multitask learning.
no code implementations • 26 Jul 2013 • Shiliang Sun
It integrates manifold regularization and multi-view regularization into the usual formulation of SVMs and is a natural extension of SVMs from supervised learning to multi-view semi-supervised learning.