no code implementations • TACL 2013 • Xian Qian, Yang Liu
Graph based dependency parsing is inefficient when handling non-local features due to high computational complexity of inference.
no code implementations • 9 Apr 2013 • Yan-Lin Tang, Hua-Lei Yin, Xiongfeng Ma, Chi-Hang Fred Fung, Yang Liu, Hai-Lin Yong, Teng-Yun Chen, Cheng-Zhi Peng, Zeng-Bing Chen, Jian-Wei Pan
Specifically, by implementing a linear-optics unambiguous-state-discrimination measurement, we show that the security of a system without phase randomization --- which is a step assumed in conventional security analyses but sometimes neglected in practice --- can be compromised.
Quantum Physics
no code implementations • CVPR 2013 • Yang Liu, Jing Liu, Zechao Li, Jinhui Tang, Hanqing Lu
In this paper, we propose a novel Weakly-Supervised Dual Clustering (WSDC) approach for image semantic segmentation with image-level labels, i. e., collaboratively performing image segmentation and tag alignment with those regions.
no code implementations • 14 Sep 2013 • Yang Liu, Mingyan Liu
We analyze the following group learning problem in the context of opinion diffusion: Consider a network with $M$ users, each facing $N$ options.
no code implementations • TACL 2014 • Xian Qian, Yang Liu
We show that the decoding problem in generalized Higher Order Conditional Random Fields (CRFs) can be decomposed into two parts: one is a tree labeling problem that can be solved in linear time using dynamic programming; the other is a supermodular quadratic pseudo-Boolean maximization problem, which can be solved in cubic time using a minimum cut algorithm.
no code implementations • 9 Jun 2014 • Yang Liu, Xiaoge Zhang, Yong Deng
The user equilibrium in traffic assignment problem is based on the fact that travelers choose the minimum-cost path between every origin-destination pair and on the assumption that such a behavior will lead to an equilibrium of the traffic network.
no code implementations • 13 Aug 2014 • Yang Liu, Bo He, Diya Dong, Yue Shen, Tianhong Yan, Rui Nian, Amaury Lendase
Second, an adaptive selective ensemble framework for online learning is designed to balance the robustness and complexity of the algorithm.
no code implementations • 8 Oct 2014 • Yang Liu, Maosong Sun
However, a major challenge still remains: it is intractable to calculate the expectations of non-local features that are critical for capturing the divergence between natural languages.
no code implementations • 26 Dec 2014 • Sezer Karaoglu, Yang Liu, Theo Gevers
Experiments on the PASCAL VOC07 and VOC10 datasets show that the proposed method significantly outperforms single object detectors, DPM (8. 4%), CN (6. 8%) and EES (17. 0%) on VOC07 and DPM (6. 5%), CN (5. 5%) and EES (16. 2%) on VOC10.
2 code implementations • AAAI 2015 2015 • Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu
Knowledge graph completion aims to perform link prediction between entities.
no code implementations • 4 Apr 2015 • Yang Liu, Mingyan Liu
A natural remedy is a learning framework, which has also been extensively studied in the same context, but a typical learning algorithm in this literature seeks only the best static policy, with performance measured by weak regret, rather than learning a good dynamic channel access policy.
no code implementations • IJCNLP 2015 • Yang Liu, Furu Wei, Sujian Li, Heng Ji, Ming Zhou, Houfeng Wang
Previous research on relation classification has verified the effectiveness of using dependency shortest paths or subtrees.
Ranked #5 on Relation Classification on SemEval 2010 Task 8
no code implementations • 2 Nov 2015 • Chuang Ding, Lei Xie, Jie Yan, Weini Zhang, Yang Liu
Prosody affects the naturalness and intelligibility of speech.
1 code implementation • ACL 2016 • Shiqi Shen, Yong Cheng, Zhongjun He, wei he, Hua Wu, Maosong Sun, Yang Liu
We propose minimum risk training for end-to-end neural machine translation.
1 code implementation • 15 Dec 2015 • Yong Cheng, Shiqi Shen, Zhongjun He, wei he, Hua Wu, Maosong Sun, Yang Liu
The attentional mechanism has proven to be effective in improving end-to-end neural machine translation.
3 code implementations • ACL 2016 • Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, Hang Li
Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate.
no code implementations • 9 Mar 2016 • Yang Liu, Sujian Li, Xiaodong Zhang, Zhifang Sui
Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser.
no code implementations • 17 Apr 2016 • Yang Liu, Yi-Ling Chen
In crowdsourcing when there is a lack of verification for contributed answers, output agreement mechanisms are often used to incentivize participants to provide truthful answers when the correct answer is hold by the majority.
no code implementations • LREC 2016 • Yang Liu, Jiajun Zhang, Cheng-qing Zong, Yating Yang, Xi Zhou
Existing discourse research only focuses on the monolingual languages and the inconsistency between languages limits the power of the discourse theory in multilingual applications such as machine translation.
2 code implementations • 30 May 2016 • Yang Liu, Chengjie Sun, Lei Lin, Xiaolong Wang
In our approach, the encoding of sentence is a two-stage process.
Ranked #73 on Natural Language Inference on SNLI
no code implementations • 31 May 2016 • Yang Liu, Minh Hoai, Mang Shao, Tae-Kyun Kim
LBSVM is based on Structured-Output SVM, but extends it to handle noisy video data and ensure consistency of the output decision throughout time.
no code implementations • CVPR 2016 • Yuanlu Xu, Xiaobai Liu, Yang Liu, Song-Chun Zhu
This paper presents a hierarchical composition approach for multi-view object tracking.
no code implementations • ACL 2016 • Chunyang Liu, Yang Liu, Huanbo Luan, Maosong Sun, Heng Yu
We introduce an agreement-based approach to learning parallel lexicons and phrases from non-parallel corpora.
no code implementations • ACL 2016 • Yong Cheng, Wei Xu, Zhongjun He, wei he, Hua Wu, Maosong Sun, Yang Liu
While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation.
3 code implementations • 29 Jun 2016 • Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu, Santhoshkumar Saminathan
Also, we show that the subgraph vectors could be used for building a deep learning variant of Weisfeiler-Lehman graph kernel.
no code implementations • 3 Aug 2016 • Christian Hadiwinoto, Yang Liu, Hwee Tou Ng
Reordering poses a major challenge in machine translation (MT) between two languages with significant differences in word order.
2 code implementations • TACL 2017 • Zhaopeng Tu, Yang Liu, Zhengdong Lu, Xiaohua Liu, Hang Li
In neural machine translation (NMT), generation of a target word depends on both source and target contexts.
no code implementations • EMNLP 2016 • Yang Liu, Sujian Li
Recognizing implicit discourse relations is a challenging but important task in the field of Natural Language Processing.
no code implementations • 24 Sep 2016 • Shenglan Liu, Jun Wu, Lin Feng, Yang Liu, Hong Qiao, Wenbo Luo Muxin Sun, Wei Wang
Incompatibility of image descriptor and ranking is always neglected in image retrieval.
no code implementations • 24 Sep 2016 • Shenglan Liu, Muxin Sun, Lin Feng, Yang Liu, Jun Wu
Multi-feature fusion ranking can be utilized to improve the ranking list of query.
no code implementations • 25 Sep 2016 • Jinsong Su, Zhixing Tan, Deyi Xiong, Rongrong Ji, Xiaodong Shi, Yang Liu
Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences.
no code implementations • 4 Oct 2016 • Yandi Xia, Yang Liu
A lot of prior work on event extraction has exploited a variety of features to represent events.
1 code implementation • 5 Nov 2016 • Frank S. He, Yang Liu, Alexander G. Schwing, Jian Peng
We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation.
1 code implementation • 7 Nov 2016 • Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, Hang Li
Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy.
no code implementations • 15 Nov 2016 • Peng-Shuai Wang, Yang Liu, Xin Tong
At runtime, our method applies the learned cascaded regression functions to a noisy input mesh and reconstructs the denoised mesh from the output facet normals.
no code implementations • 15 Nov 2016 • Yong Cheng, Yang Liu, Qian Yang, Maosong Sun, Wei Xu
While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs.
no code implementations • 28 Nov 2016 • Zhuoran Liu, Yang Liu
Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years.
no code implementations • NeurIPS 2016 • Yang Liu, Yi-Ling Chen
We propose a Strategic Regression-Upper Confidence Bound (SR-UCB) framework, an UCB-style index combined with a simple payment rule, where the index of a worker approximates the quality of his past contributions and is used by the learner to determine whether the worker receives future work.
no code implementations • COLING 2016 • Meng Zhang, Yang Liu, Huanbo Luan, Yiqun Liu, Maosong Sun
Being able to induce word translations from non-parallel data is often a prerequisite for cross-lingual processing in resource-scarce languages and domains.
no code implementations • COLING 2016 • Chen Li, Zhongyu Wei, Yang Liu, Yang Jin, Fei Huang
A news article summary usually consists of 2-3 key sentences that reflect the gist of that news article.
no code implementations • 6 Jan 2017 • Yongwang Zhao, David Sanan, Fuyuan Zhang, Yang Liu
In accordance with the analytical framework, a comprehensive analysis and discussion of related work are presented.
Software Engineering
no code implementations • 19 Jan 2017 • Zhongyu Wei, Chen Li, Yang Liu
For argumentation mining, there are several sub-tasks such as argumentation component type classification, relation classification.
no code implementations • 6 Apr 2017 • Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu
Most of the existing malware detection approaches use only one (or a selected few) of the aforementioned feature sets which prevent them from detecting a vast majority of attacks.
no code implementations • 7 Apr 2017 • Yang Liu, Prajit Ramachandran, Qiang Liu, Jian Peng
Policy gradient methods have been successfully applied to many complex reinforcement learning problems.
no code implementations • 19 Apr 2017 • Xin Liu, Qingcai Chen, Xiang-Ping Wu, Yan Liu, Yang Liu
Music emotion recognition (MER) is usually regarded as a multi-label tagging task, and each segment of music can inspire specific emotion tags.
no code implementations • 25 Apr 2017 • Liner Yang, Meishan Zhang, Yang Liu, Nan Yu, Maosong Sun, Guohong Fu
While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems.
no code implementations • ACL 2017 • Yun Chen, Yang Liu, Yong Cheng, Victor O. K. Li
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains.
3 code implementations • TACL 2018 • Yang Liu, Mirella Lapata
In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations.
no code implementations • 31 May 2017 • Christos Dimitrakakis, Yang Liu, David Parkes, Goran Radanovic
We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty.
no code implementations • 3 Jun 2017 • Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu
Contrary to this fact, most of the prior works on Machine Learning based Android malware detection have assumed that the distribution of the observed malware characteristics (i. e., features) does not change over time.
6 code implementations • 20 Jun 2017 • Jiacheng Zhang, Yanzhuo Ding, Shiqi Shen, Yong Cheng, Maosong Sun, Huanbo Luan, Yang Liu
This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University.
no code implementations • ACL 2017 • Meng Zhang, Yang Liu, Huanbo Luan, Maosong Sun
In this work, we show that such cross-lingual connection can actually be established without any form of supervision.
no code implementations • ACL 2017 • Yanzhuo Ding, Yang Liu, Huanbo Luan, Maosong Sun
While neural machine translation (NMT) has made remarkable progress in recent years, it is hard to interpret its internal workings due to the continuous representations and non-linearity of neural networks.
no code implementations • 6 Jul 2017 • Yang Liu, Goran Radanovic, Christos Dimitrakakis, Debmalya Mandal, David C. Parkes
In addition, we define the {\em fairness regret}, which corresponds to the degree to which an algorithm is not calibrated, where perfect calibration requires that the probability of selecting an arm is equal to the probability with which the arm has the best quality realization.
6 code implementations • 17 Jul 2017 • Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan, Lihui Chen, Yang Liu, Shantanu Jaiswal
Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs.
Ranked #1 on Malware Detection on Android Malware Dataset
no code implementations • CONLL 2017 • Xian Qian, Yang Liu
For this year{'}s multilingual dependency parsing shared task, we developed a pipeline system, which uses a variety of features for each of its components.
no code implementations • CONLL 2017 • Wanxiang Che, Jiang Guo, Yuxuan Wang, Bo Zheng, Huaipeng Zhao, Yang Liu, Dechuan Teng, Ting Liu
Our system includes three pipelined components: \textit{tokenization}, \textit{Part-of-Speech} (POS) \textit{tagging} and \textit{dependency parsing}.
no code implementations • EMNLP 2017 • Yang Liu, Kun Han, Zhao Tan, Yun Lei
Previous work on dialog act (DA) classification has investigated different methods, such as hidden Markov models, maximum entropy, conditional random fields, graphical models, and support vector machines.
no code implementations • EMNLP 2017 • Yang Liu, Mirella Lapata
Experimental results show that our parser obtains state-of-the art performance on benchmark datasets, while being efficient (with time complexity linear in the number of sentences in the document) and requiring minimal feature engineering.
no code implementations • EMNLP 2017 • Meng Zhang, Yang Liu, Huanbo Luan, Maosong Sun
By viewing word embedding spaces as distributions, we propose to minimize their earth mover{'}s distance, a measure of divergence between distributions.
no code implementations • 22 Sep 2017 • Xuefeng Liang, Lixin Fan, Yuen Peng Loh, Yang Liu, Song Tong
In psychology, theory-driven researches are usually conducted with extensive laboratory experiments, yet rarely tested or disproved with big data.
no code implementations • ICCV 2017 • Yang Liu, Ping Wei, Song-Chun Zhu
Given an egocentric video, a beam search algorithm is applied to jointly recognizing the object fluents in each frame, and the task of the entire video.
1 code implementation • ICCV 2017 • Lei Huang, Xianglong Liu, Yang Liu, Bo Lang, DaCheng Tao
Training deep neural networks is difficult for the pathological curvature problem.
no code implementations • 10 Oct 2017 • Jiaqi Guan, Yang Liu, Qiang Liu, Jian Peng
Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing.
no code implementations • 27 Oct 2017 • Chen Chen, Xiaowei Zhao, Yang Liu
In this paper, we present a solution to Large-Scale Video Classification Challenge (LSVC2017) [1] that ranked the 1st place.
no code implementations • 14 Nov 2017 • Gongze Cao, Yezhou Yang, Jie Lei, Cheng Jin, Yang Liu, Mingli Song
As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts.
1 code implementation • TACL 2018 • Zhaopeng Tu, Yang Liu, Shuming Shi, Tong Zhang
Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information.
1 code implementation • 29 Nov 2017 • Qiong Wu, Fan Zhang, Hao Wang, Jun Lin, Yang Liu
The Alternating Direction Method of Multipliers (ADMM) decoding of Low Density Parity Check (LDPC) codes has received many attentions due to its excellent performance at the error floor region.
Information Theory Information Theory
1 code implementation • 5 Dec 2017 • Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis.
Ranked #3 on 3D Object Classification on ModelNet40
no code implementations • 10 Dec 2017 • Bo Wu, Yang Liu, Bo Lang, Lei Huang
Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs.
Ranked #1 on Graph Classification on AIDS
no code implementations • 25 Dec 2017 • Yang Liu, Jinshan Pan, Zhixun Su
However, directly using exist- ing residual learning algorithms in image restoration does not well solve this problem as little information is available in the corrupted regions.
no code implementations • ICLR 2018 • Yang Liu, Matt Gardner
Using a structured attention mechanism, our model matches possible spans in the first sentence to possible spans in the second sentence, simultaneously discovering the tree structure of each sentence and performing a comparison, in a model that is fully differentiable and is trained only on the comparison objective.
no code implementations • ICLR 2018 • Keyi Yu, Yang Liu, Alexander G. Schwing, Jian Peng
Recent advances in recurrent neural nets (RNNs) have shown much promise in many applications in natural language processing.
2 code implementations • 16 Jan 2018 • Xiangwen Zhang, Jinsong Su, Yue Qin, Yang Liu, Rongrong Ji, Hongji Wang
The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation.
no code implementations • 9 Feb 2018 • Yun Chen, Yang Liu, Victor O. K. Li
While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem for low-resource language pairs and domains.
1 code implementation • ECCV 2018 • Yongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, DaCheng Tao, Mingli Song
In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.
no code implementations • 26 Feb 2018 • Yang Liu, Juntao Wang, Yi-Ling Chen
We show that, with a single bit of information about the prior distribution of the random variables, SSR in a multi-task setting recover SPSR in expectation, as if having access to the ground truth.
no code implementations • 20 Mar 2018 • Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data.
no code implementations • 27 Mar 2018 • Elizaveta Rebrova, Gustavo Chavez, Yang Liu, Pieter Ghysels, Xiaoye Sherry Li
We present memory-efficient and scalable algorithms for kernel methods used in machine learning.
no code implementations • CVPR 2018 • Jie Song, Chengchao Shen, Yezhou Yang, Yang Liu, Mingli Song
Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes.
2 code implementations • CVPR 2017 • Zhi-Qi Cheng, Xiao Wu, Yang Liu, Xian-Sheng Hua
For the video side, deep visual features are extracted from detected object regions in each frame, and further fed into a Long Short-Term Memory (LSTM) framework for sequence modeling, which captures the temporal dynamics in videos.
17 code implementations • 20 Apr 2018 • Sheng Chen, Yang Liu, Xiang Gao, Zhen Han
Face Analysis Project on MXNet
Ranked #5 on Lightweight Face Recognition on AgeDB-30
no code implementations • 23 Apr 2018 • Yang Liu, Qiang Qu, Chao GAO
Finally, we replicate this new block into n copies and concatenate them as the input to the FC layer.
no code implementations • 3 May 2018 • Yang Liu
To address modeling problems of brain-inspired intelligence, this thesis is focused on researching in the semantic-oriented framework design for multimedia and multimodal information.
no code implementations • 5 May 2018 • YanTong Wu, Yang Liu
The monocular depth recovery is often studied as an independent part, and a better depth estimation is used to solve the pose.
no code implementations • 10 May 2018 • Cohen Daniel, Yang Liu, Croft W. Bruce
With the rise in mobile and voice search, answer passage retrieval acts as a critical component of an effective information retrieval system for open domain question answering.
no code implementations • CVPR 2018 • Jinshan Pan, Sifei Liu, Deqing Sun, Jiawei Zhang, Yang Liu, Jimmy Ren, Zechao Li, Jinhui Tang, Huchuan Lu, Yu-Wing Tai, Ming-Hsuan Yang
These problems usually involve the estimation of two components of the target signals: structures and details.
4 code implementations • 14 May 2018 • Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i. e., training data and training programs).
Software Engineering
no code implementations • ACL 2018 • Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, Yang Liu
Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models.
no code implementations • 19 May 2018 • Xiang Ao, Yang Liu, Zhen Huang, Luo Zuo, Qing He
An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently.
no code implementations • 28 May 2018 • Jose Dolz, Xiaopan Xu, Jerome Rony, Jing Yuan, Yang Liu, Eric Granger, Christian Desrosiers, Xi Zhang, Ismail Ben Ayed, Hongbing Lu
Precise segmentation of bladder walls and tumor regions is an essential step towards non-invasive identification of tumor stage and grade, which is critical for treatment decision and prognosis of patients with bladder cancer (BC).
no code implementations • CVPR 2018 • Qingchao Chen, Yang Liu, Zhaowen Wang, Ian Wassell, Kevin Chetty
In this paper, we propose the Re-weighted Adversarial Adaptation Network (RAAN) to reduce the feature distribution divergence and adapt the classifier when domain discrepancies are disparate.
Open-Ended Question Answering Unsupervised Domain Adaptation
no code implementations • CVPR 2018 • Yang Liu, Zhaowen Wang, Hailin Jin, Ian Wassell
The encoder and the discriminators are trained cooperatively on factors of interest, but in an adversarial way on factors of distraction.
1 code implementation • CVPR 2018 • Peisong Wang, Qinghao Hu, Yifan Zhang, Chunjie Zhang, Yang Liu, Jian Cheng
In this paper, we propose a simple yet effective Two-Step Quantization (TSQ) framework, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes.
no code implementations • CVPR 2018 • Ping Wei, Yang Liu, Tianmin Shu, Nanning Zheng, Song-Chun Zhu
We built a new video dataset of tasks, intentions, and attention.
no code implementations • NeurIPS 2018 • Zehong Hu, Yitao Liang, Yang Liu, Jie Zhang
Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels.
no code implementations • 15 Jun 2018 • Jakub Breier, Xiaolu Hou, Dirmanto Jap, Lei Ma, Shivam Bhasin, Yang Liu
As deep learning systems are widely adopted in safety- and security-critical applications, such as autonomous vehicles, banking systems, etc., malicious faults and attacks become a tremendous concern, which potentially could lead to catastrophic consequences.
no code implementations • 20 Jun 2018 • Lei Ma, Fuyuan Zhang, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) has achieved remarkable progress over the past decade and been widely applied to many safety-critical applications.
no code implementations • 22 Jun 2018 • Pang Guofei, Yang Liu, Karniadakis George Em
Neural-net-induced Gaussian process (NNGP) regression inherits both the high expressivity of deep neural networks (deep NNs) as well as the uncertainty quantification property of Gaussian processes (GPs).
no code implementations • 2 Jul 2018 • Zhu Kaili, Chuan Wang, Ruobing Li, Yang Liu, Tianlei Hu, Hui Lin
We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices.
no code implementations • 16 Jul 2018 • Shufei Zhang, Kai-Zhu Huang, Jianke Zhu, Yang Liu
All the existing adversarial training methods consider only how the worst perturbed examples (i. e., adversarial examples) could affect the model output.
3 code implementations • 20 Jul 2018 • Yang Liu, Xin Yuan, Jinli Suo, David J. Brady, Qionghai Dai
We further investigate the special structure of the sampling process in SCI to tackle the computational workload and memory issues in SCI reconstruction.
no code implementations • COLING 2018 • Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang
Visual Question Generation (VQG) aims to ask natural questions about an image automatically.
1 code implementation • COLING 2018 • Lu Ji, Zhongyu Wei, Xiangkun Hu, Yang Liu, Qi Zhang, Xuanjing Huang
In this paper, we investigate the issue of persuasiveness evaluation for argumentative comments.
no code implementations • 1 Aug 2018 • Sheng Chen, Jia Guo, Yang Liu, Xiang Gao, Zhen Han
In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global average pooling layer.
no code implementations • 2 Aug 2018 • Jinshan Pan, Jiangxin Dong, Yang Liu, Jiawei Zhang, Jimmy Ren, Jinhui Tang, Yu-Wing Tai, Ming-Hsuan Yang
We present an algorithm to directly solve numerous image restoration problems (e. g., image deblurring, image dehazing, image deraining, etc.).
1 code implementation • CVPR 2020 • Yu-Qi Yang, Shilin Liu, Hao Pan, Yang Liu, Xin Tong
Surface meshes are widely used shape representations and capture finer geometry data than point clouds or volumetric grids, but are challenging to apply CNNs directly due to their non-Euclidean structure.
Ranked #27 on Semantic Segmentation on ScanNet
2 code implementations • 22 Aug 2018 • Yang Liu, Lixin Ji, Ruiyang Huang, Tuosiyu Ming, Chao GAO, Jianpeng Zhang
The classification of sentences is very challenging, since sentences contain the limited contextual information.
no code implementations • Frontiers in Physiology 2018 • Runnan He, Kuanquan Wang, Na Zhao, Yang Liu, Yongfeng Yuan, Qince Li, Henggui Zhang
The proposed method analyzed the time-frequency features of the electrocardiogram (ECG), thus being different to conventional AF detecting methods that implement isolating atrial or ventricular activities.
Ranked #2 on Atrial Fibrillation Detection on MIT-BIH AF
no code implementations • ECCV 2018 • Yang Liu, Zhaowen Wang, Hailin Jin, Ian Wassell
We propose to leverage the parameters that lead to the output images to improve image feature learning.
no code implementations • 3 Sep 2018 • Yang Liu, Zhaoyang Lu, Jing Li, Tao Yang
In order to make the feature representations of videos across views transferable, we then learn a transferable dictionary pair simultaneously from pairs of videos taken at different views to encourage each action video across views to have the same sparse representation.
no code implementations • 4 Sep 2018 • Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Hongxu Chen, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical scenarios such as autonomous driving.
no code implementations • 7 Sep 2018 • Alvin Chan, Lei Ma, Felix Juefei-Xu, Xiaofei Xie, Yang Liu, Yew Soon Ong
Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks.
1 code implementation • 7 Sep 2018 • Yucheng Fu, Yang Liu
The tool could be used to provide benchmarking and training data for existing image processing algorithms and to guide the future development of bubble detecting algorithms.
no code implementations • 11 Sep 2018 • Yiling Chen, Yang Liu, Juntao Wang
We show that a broad family of randomized wagering mechanisms satisfy all desirable theoretical properties.
no code implementations • 15 Sep 2018 • Annamalai Narayanan, Charlie Soh, Lihui Chen, Yang Liu, Lipo Wang
Building behavior profiles of Android applications (apps) with holistic, rich and multi-view information (e. g., incorporating several semantic views of an app such as API sequences, system calls, etc.)
3 code implementations • 18 Sep 2018 • Berk Ustun, Alexander Spangher, Yang Liu
We present integer programming tools to ensure recourse in linear classification problems without interfering in model development.
1 code implementation • 21 Sep 2018 • Peng-Shuai Wang, Chun-Yu Sun, Yang Liu, Xin Tong
The Adaptive O-CNN encoder takes the planar patch normal and displacement as input and performs 3D convolutions only at the octants at each level, while the Adaptive O-CNN decoder infers the shape occupancy and subdivision status of octants at each level and estimates the best plane normal and displacement for each leaf octant.
no code implementations • 30 Sep 2018 • Fred Roosta, Yang Liu, Peng Xu, Michael W. Mahoney
We consider a variant of inexact Newton Method, called Newton-MR, in which the least-squares sub-problems are solved approximately using Minimum Residual method.
1 code implementation • EMNLP 2018 • Jiali Zeng, Jinsong Su, Huating Wen, Yang Liu, Jun Xie, Yongjing Yin, Jianqiang Zhao
Based on this intuition, in this paper, we devote to distinguishing and exploiting word-level domain contexts for multi-domain NMT.
1 code implementation • CONLL 2018 • Lishuang Li, Yang Liu, AnQiao Zhou
Aspect-level sentiment analysis aims to identify the sentiment of a specific target in its context.
Aspect-Based Sentiment Analysis (ABSA) Feature Engineering +2
no code implementations • EMNLP 2018 • Yang Liu, Matt Gardner, Mirella Lapata
We evaluate this model on two tasks, natural entailment detection and answer sentence selection, and find that modeling latent tree structures results in superior performance.
1 code implementation • ICLR 2019 • Jingkang Wang, Yang Liu, Bo Li
For instance, the state-of-the-art PPO algorithm is able to obtain 84. 6% and 80. 8% improvements on average score for five Atari games, with error rates as 10% and 30% respectively.
3 code implementations • EMNLP 2018 • Jiacheng Zhang, Huanbo Luan, Maosong Sun, FeiFei Zhai, Jingfang Xu, Min Zhang, Yang Liu
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge.
no code implementations • 10 Oct 2018 • Lei Ma, Felix Juefei-Xu, Minhui Xue, Qiang Hu, Sen Chen, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processing, speech processing, and medical diagnostics.
1 code implementation • 12 Oct 2018 • Fu Sun, Linyang Li, Xipeng Qiu, Yang Liu
A key subtask is to reliably predict whether the question is unanswerable.
Ranked #12 on Question Answering on SQuAD2.0 dev
no code implementations • 25 Oct 2018 • Shenglan Liu, Xiang Liu, Yang Liu, Lin Feng, Hong Qiao, Jian Zhou, Yang Wang
Supervised learning methods are widely used in machine learning.
1 code implementation • 31 Oct 2018 • Yan Yin, Ramon Prieto, Bin Wang, Jianwei Zhou, Yiwei Gu, Yang Liu, Hui Lin
Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks.
no code implementations • WS 2018 • Yunfan Gu, Zhongyu Wei, Maoran Xu, Hao Fu, Yang Liu, Xuanjing Huang
In this paper, we propose to incorporate topic aspects information for online comments convincingness evaluation.
no code implementations • 2 Nov 2018 • Xiang Li, Haiyang Xue, Wei Chen, Yang Liu, Yang Feng, Qun Liu
Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
1 code implementation • ACL 2017 • Jiacheng Zhang, Yang Liu, Huanbo Luan, Jingfang Xu, Maosong Sun
Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge.
no code implementations • 8 Nov 2018 • Nripsuta Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David Parkes, Yang Liu
What is the best way to define algorithmic fairness?
no code implementations • 13 Nov 2018 • Qianyu Guo, Xiaofei Xie, Lei Ma, Qiang Hu, Ruitao Feng, Li Li, Yang Liu, Jianjun Zhao, Xiaohong Li
Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process.
no code implementations • 14 Nov 2018 • Bowen Li, Jianpeng Cheng, Yang Liu, Frank Keller
Transition-based models enable faster inference with $O(n)$ time complexity, but their performance still lags behind.
no code implementations • 19 Nov 2018 • Kaiqing Zhang, Yang Liu, Ji Liu, Mingyan Liu, Tamer Başar
This paper addresses the problem of distributed learning of average belief with sequential observations, in which a network of $n>1$ agents aim to reach a consensus on the average value of their beliefs, by exchanging information only with their neighbors.
no code implementations • 26 Nov 2018 • Zi Lin, Yang Liu
Previously, researchers paid no attention to the creation of unambiguous morpheme embeddings independent from the corpus, while such information plays an important role in expressing the exact meanings of words for parataxis languages like Chinese.
1 code implementation • 2 Dec 2018 • Sijia Xu, Hongyu Kuang, Zhi Zhuang, Renjie Hu, Yang Liu, Huyang Sun
These rules are not scalable and efficient enough to cope with the enormous yet partially observed state space in the game.
no code implementations • 6 Dec 2018 • YIlun Zhu, Yang Liu, Siyao Peng, Austin Blodgett, Yushi Zhao, Nathan Schneider
This study adapts Semantic Network of Adposition and Case Supersenses (SNACS) annotation to Mandarin Chinese and demonstrates that the same supersense categories are appropriate for Chinese adposition semantics.
no code implementations • 7 Dec 2018 • Partha Das, Anil S. Baslamisli, Yang Liu, Sezer Karaoglu, Theo Gevers
In this paper, we formulate the color constancy task as an image-to-image translation problem using GANs.
no code implementations • 8 Dec 2018 • Yang Liu, Yan Kang, Chaoping Xing, Tianjian Chen, Qiang Yang
A secure transfer cross validation approach is also proposed to guard the FTL performance under the federation.
no code implementations • 13 Dec 2018 • Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Jianjun Zhao, Yang Liu
Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.
no code implementations • 29 Dec 2018 • Yang Liu, Ajay Kumar
Contactless and online palmprint identfication offers improved user convenience, hygiene, user-security and is highly desirable in a range of applications.
no code implementations • 22 Jan 2019 • Rong Kang, Jieqi Shi, Xueming Li, Yang Liu, Xiao Liu
As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days.
1 code implementation • 25 Jan 2019 • Kewei Cheng, Tao Fan, Yilun Jin, Yang Liu, Tianjian Chen, Dimitrios Papadopoulos, Qiang Yang
This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set.
no code implementations • journal 2019 • Zhuo Ma, Haoran Ge, Yang Liu, Meng Zhao, Jianfeng Ma
In this paper, we present a combination method for Android malware detection based on the machine learning algorithm.
no code implementations • 31 Jan 2019 • Xiaoning Du, Bihuan Chen, Yuekang Li, Jianmin Guo, Yaqin Zhou, Yang Liu, Yu Jiang
The latter needs the prior knowledge of known vulnerabilities and can only identify similar but not new types of vulnerabilities.
Software Engineering
1 code implementation • 13 Feb 2019 • Qiang Yang, Yang Liu, Tianjian Chen, Yongxin Tong
We propose a possible solution to these challenges: secure federated learning.
no code implementations • 11 Mar 2019 • Richard Galvez, David F. Fouhey, Meng Jin, Alexandre Szenicer, Andrés Muñoz-Jaramillo, Mark C. M. Cheung, Paul J. Wright, Monica G. Bobra, Yang Liu, James Mason, Rajat Thomas
In this paper we present a curated dataset from the NASA Solar Dynamics Observatory (SDO) mission in a format suitable for machine learning research.
12 code implementations • arXiv 2019 • Yang Liu
BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks.
Extractive Document Summarization Extractive Summarization +1
no code implementations • 28 Mar 2019 • Yang Liu
The intelligent Processing technique is more and more attractive to researchers due to its ability to deal with key problems in Vehicular Ad hoc networks.
no code implementations • 11 Apr 2019 • Sara Beery, Yang Liu, Dan Morris, Jim Piavis, Ashish Kapoor, Markus Meister, Neel Joshi, Pietro Perona
The ability to detect and classify rare occurrences in images has important applications - for example, counting rare and endangered species when studying biodiversity, or detecting infrequent traffic scenarios that pose a danger to self-driving cars.