Search Results for author: Rui Wang

Found 223 papers, 48 papers with code

Estimating Q(s,s') with Deterministic Dynamics Gradients

no code implementations ICML 2020 Ashley Edwards, Himanshu Sahni, Rosanne Liu, Jane Hung, Ankit Jain, Rui Wang, Adrien Ecoffet, Thomas Miconi, Charles Isbell, Jason Yosinski

In this paper, we introduce a novel form of a value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.

Transfer Learning

MixNorm: Test-Time Adaptation Through Online Normalization Estimation

no code implementations21 Oct 2021 Xuefeng Hu, Gokhan Uzunbas, Sirius Chen, Rui Wang, Ashish Shah, Ram Nevatia, Ser-Nam Lim

We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples.

Unsupervised Domain Adaptation Zero-Shot Learning

A Geometry-Based Stochastic Model for Truck Communication Channels in Freeway Scenarios

no code implementations20 Oct 2021 Chen Huang, Rui Wang, Cheng-Xiang Wang, Pan Tang, Andreas F. Molisch

We validate this model by contrasting the root-mean-square delay spread and the angular spreads of departure/arrival derived from the channel model with the outcomes directly derived from the measurements.

Entity Relation Extraction as Dependency Parsing in Visually Rich Documents

no code implementations19 Oct 2021 Yue Zhang, Bo Zhang, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao

Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i. e., semantic entity), while the relations in-between are largely unexplored.

Dependency Parsing Key Information Extraction +1

Tackling the Imbalance for GNNs

no code implementations17 Oct 2021 Rui Wang, Weixuan Xiong, Qinghu Hou, Ou wu

Different from deep neural networks for non-graph data classification, graph neural networks (GNNs) leverage the information exchange between nodes (or samples) when representing nodes.

Classification

SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing

no code implementations14 Oct 2021 Junyi Ao, Rui Wang, Long Zhou, Shujie Liu, Shuo Ren, Yu Wu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-training natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning.

automatic-speech-recognition Quantization +4

Multi-View Self-Attention Based Transformer for Speaker Recognition

no code implementations11 Oct 2021 Rui Wang, Junyi Ao, Long Zhou, Shujie Liu, Zhihua Wei, Tom Ko, Qing Li, Yu Zhang

In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer variants with or without the proposed attention mechanism for speaker recognition.

Speaker Recognition

Self-appearance-aided Differential Evolution for Motion Transfer

no code implementations9 Oct 2021 Peirong Liu, Rui Wang, Xuefei Cao, Yipin Zhou, Ashish Shah, Maxime Oquab, Camille Couprie, Ser-Nam Lim

Image animation transfers the motion of a driving video to a static object in a source image, while keeping the source identity unchanged.

Image Animation

Efficient and High-quality Prehensile Rearrangement in Cluttered and Confined Spaces

1 code implementation6 Oct 2021 Rui Wang, Yinglong Miao, Kostas E. Bekris

The new monotone solver is integrated with a global planner to solve non-monotone instances with high-quality solutions fast.

Motion Planning

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition

no code implementations29 Sep 2021 Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Tao Qin, Xiang-Yang Li, Edward Lin, Tie-Yan Liu

Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one sentence at a time, failing to leverage the voting effect from multiple candidates to better detect and correct error tokens.

automatic-speech-recognition Speech Recognition

DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings

no code implementations26 Sep 2021 Che Liu, Rui Wang, Jinghua Liu, Jian Sun, Fei Huang, Luo Si

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability.

Contrastive Learning Semantic Textual Similarity +1

TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method

no code implementations20 Sep 2021 Zeqian Ju, Peiling Lu, Xu Tan, Rui Wang, Chen Zhang, Songruoyao Wu, Kejun Zhang, Xiangyang Li, Tao Qin, Tie-Yan Liu

In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e. g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i. e., the system consists of a lyric-to-template module and a template-to-melody module).

Cross Modification Attention Based Deliberation Model for Image Captioning

no code implementations17 Sep 2021 Zheng Lian, Yanan Zhang, Haichang Li, Rui Wang, Xiaohui Hu

The conventional encoder-decoder framework for image captioning generally adopts a single-pass decoding process, which predicts the target descriptive sentence word by word in temporal order.

Image Captioning

Review of the mechanisms of SARS-CoV-2 evolution and transmission

no code implementations15 Sep 2021 Jiahui Chen, Rui Wang, Guo-Wei Wei

We anticipate that viral evolution will combine RBD co-mutations at these two sites, creating future variants that are tens of times more infectious than the original SARS-CoV-2.

Emerging vaccine-breakthrough SARS-CoV-2 variants

no code implementations9 Sep 2021 Rui Wang, Jiahui Chen, Yuta Hozumi, Changchuan Yin, Guo-Wei Wei

The molecular mechanism underlying such surge is elusive due to 4, 653 non-degenerate mutations on the spike protein, which is the target of most COVID-19 vaccines.

Topological Data Analysis

Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization

no code implementations31 Aug 2021 Shuai Wang, Dachuan Li, Rui Wang, Qi Hao, Yik-Chung Wu, Derrick Wing Kwan Ng

Wireless federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications.

Federated Learning

A Multimodal Framework for Video Ads Understanding

no code implementations29 Aug 2021 Zejia Weng, Lingchen Meng, Rui Wang, Zuxuan Wu, Yu-Gang Jiang

There is a growing trend in placing video advertisements on social platforms for online marketing, which demands automatic approaches to understand the contents of advertisements effectively.

Optical Character Recognition Scene Segmentation +1

PIVODL: Privacy-preserving vertical federated learning over distributed labels

no code implementations25 Aug 2021 Hangyu Zhu, Rui Wang, Yaochu Jin, Kaitai Liang

Federated learning (FL) is an emerging privacy preserving machine learning protocol that allows multiple devices to collaboratively train a shared global model without revealing their private local data.

Federated Learning

Discriminating modelling approaches for Point in Time Economic Scenario Generation

no code implementations19 Aug 2021 Rui Wang

We introduce the notion of Point in Time Economic Scenario Generation (PiT ESG) with a clear mathematical problem formulation to unify and compare economic scenario generation approaches conditional on forward looking market data.

Cross-lingual Transferring of Pre-trained Contextualized Language Models

1 code implementation27 Jul 2021 Zuchao Li, Kevin Parnow, Hai Zhao, Zhuosheng Zhang, Rui Wang, Masao Utiyama, Eiichiro Sumita

Though the pre-trained contextualized language model (PrLM) has made a significant impact on NLP, training PrLMs in languages other than English can be impractical for two reasons: other languages often lack corpora sufficient for training powerful PrLMs, and because of the commonalities among human languages, computationally expensive PrLM training for different languages is somewhat redundant.

Language Modelling Machine Translation +1

Accelerating Edge Intelligence via Integrated Sensing and Communication

no code implementations20 Jul 2021 Tong Zhang, Shuai Wang, Guoliang Li, Fan Liu, Guangxu Zhu, Rui Wang

Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and uploading time.

Rethinking the Tradeoff in Integrated Sensing and Communication: Recognition Accuracy versus Communication Rate

no code implementations20 Jul 2021 Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Fan Liu, Meihong Zhang, Xiaohui Peng, Tony Xiao Han

Integrated sensing and communication (ISAC) is a promising technology to improve the band-utilization efficiency via spectrum sharing or hardware sharing between radar and communication systems.

MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis

no code implementations13 Jul 2021 Haocheng Ren, Hao Zhang, Jia Zheng, Jiaxiang Zheng, Rui Tang, Rui Wang, Hujun Bao

With the rapid development of data-driven techniques, data has played an essential role in various computer vision tasks.

Image Generation

A Survey on Low-Resource Neural Machine Translation

no code implementations9 Jul 2021 Rui Wang, Xu Tan, Renqian Luo, Tao Qin, Tie-Yan Liu

Neural approaches have achieved state-of-the-art accuracy on machine translation but suffer from the high cost of collecting large scale parallel data.

Low-Resource Neural Machine Translation Translation

Physics-Guided Deep Learning for Dynamical Systems: A Survey

no code implementations2 Jul 2021 Rui Wang, Rose Yu

Modeling complex physical dynamics is a fundamental task in science and engineering.

A New Channel Estimation Strategy in Intelligent Reflecting Surface Assisted Networks

no code implementations22 Jun 2021 Rui Wang, Liang Liu, Shuowen Zhang, Changyuan Yu

Specifically, in Phase I, the correlation coefficients between the channels of a typical BS antenna and those of the other antennas are estimated; while in Phase II, the cascaded channel of the typical antenna is estimated.

Cross-domain Contrastive Learning for Unsupervised Domain Adaptation

no code implementations10 Jun 2021 Rui Wang, Zuxuan Wu, Zejia Weng, Jingjing Chen, Guo-Jun Qi, Yu-Gang Jiang

In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification.

Contrastive Learning Self-Supervised Learning +1

MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training

1 code implementation10 Jun 2021 Mingliang Zeng, Xu Tan, Rui Wang, Zeqian Ju, Tao Qin, Tie-Yan Liu

Inspired by the success of pre-training models in natural language processing, in this paper, we develop MusicBERT, a large-scale pre-trained model for music understanding.

Classification Emotion Classification +2

A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents

1 code implementation NAACL 2021 Qingrong Xia, Bo Zhang, Rui Wang, Zhenghua Li, Yue Zhang, Fei Huang, Luo Si, Min Zhang

Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of {``}Who expressed what opinions towards what{''} in one sentence.

Multi-Task Learning Opinion Mining

Variational Gaussian Topic Model with Invertible Neural Projections

no code implementations21 May 2021 Rui Wang, Deyu Zhou, Yuxuan Xiong, Haiping Huang

Based on the variational auto-encoder, the proposed VaGTM models each topic with a multivariate Gaussian in decoder to incorporate word relatedness.

Topic Models Word Embeddings

Model Pruning Based on Quantified Similarity of Feature Maps

no code implementations13 May 2021 Zidu Wang, Xuexin Liu, Long Huang, Yunqing Chen, Yufei Zhang, Zhikang Lin, Rui Wang

However, there are few methods can figure out the redundant information of the parameters stored in the high-dimensional tensors, which leads to the lack of theoretical guidance for the compression of CNNs.

Long Short-Term Temporal Meta-learning in Online Recommendation

no code implementations8 May 2021 Ruobing Xie, Yalong Wang, Rui Wang, Yuanfu Lu, Yuanhang Zou, Feng Xia, Leyu Lin

To address this, we propose a novel Long Short-Term Temporal Meta-learning framework (LSTTM) for online recommendation, which captures user preferences from a global long-term graph and an internal short-term graph.

Meta-Learning

Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model

no code implementations21 Apr 2021 Guoliang Li, Shuai Wang, Jie Li, Rui Wang, Xiaohui Peng, Tony Xiao Han

Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing.

Scene Understanding

Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysis

no code implementations20 Apr 2021 Zezhong Zhang, Guangxu Zhu, Rui Wang, Vincent K. N. Lau, Kaibin Huang

The novelty of this design lies in exploiting channel noise to accelerate the descent in the region around each saddle point encountered by gradient descent, thereby increasing the convergence speed of over-the-air PCA.

Data Compression

Shapley Explanation Networks

2 code implementations ICLR 2021 Rui Wang, Xiaoqian Wang, David I. Inouye

This intrinsic explanation approach enables layer-wise explanations, explanation regularization of the model during training, and fast explanation computation at test time.

Advances and Challenges in Unsupervised Neural Machine Translation

no code implementations EACL 2021 Rui Wang, Hai Zhao

Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results.

Denoising Machine Translation +1

EfficientTDNN: Efficient Architecture Search for Speaker Recognition in the Wild

no code implementations25 Mar 2021 Rui Wang, Zhihua Wei, Haoran Duan, Shouling Ji, Zhen Hong

Secondly, the supernet is progressively trained with multi-condition data augmentation to mitigate interference between subnets and overcome the challenge of optimizing a huge search space.

Data Augmentation Network Pruning +2

Vaccine-escape and fast-growing mutations in the United Kingdom, the United States, Singapore, Spain, South Africa, and other COVID-19-devastated countries

no code implementations14 Mar 2021 Rui Wang, Jiahui Chen, Kaifu Gao, Guo-Wei Wei

We further unveil that mutation N501Y involved in United Kingdom (UK), South Africa, and Brazil variants may moderately weaken the binding between the RBD and many known antibodies, while mutations E484K and K417N found in South Africa and Brazilian variants can potentially disrupt the binding between the RDB and many known antibodies.

Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization

no code implementations2 Mar 2021 Jinyun Zhou, Rui Wang, Xu Liu, Yifei Jiang, Shu Jiang, Jiaming Tao, Jinghao Miao, Shiyu Song

Detailed ablation and visualization analysis are included to further demonstrate each of our proposed modules' effectiveness in our method.

Autonomous Driving Data Augmentation +1 Robotics

Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles

no code implementations1 Mar 2021 Rui Wang, Heju Li, Erwu Liu

The rapid increase of the data scale in Internet of Vehicles (IoV) system paradigm, hews out new possibilities in boosting the service quality for the emerging applications through data sharing.

Edge-computing Federated Learning

Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control

no code implementations28 Feb 2021 Chen Wang, Rui Wang, Ajay Mandlekar, Li Fei-Fei, Silvio Savarese, Danfei Xu

Key to such capability is hand-eye coordination, a cognitive ability that enables humans to adaptively direct their movements at task-relevant objects and be invariant to the objects' absolute spatial location.

Imitation Learning

Meta-Learning Dynamics Forecasting Using Task Inference

no code implementations20 Feb 2021 Rui Wang, Robin Walters, Rose Yu

DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain.

Meta-Learning

High-α-Metal-Rich stars in the LAMOST-MRS survey and its connection with the galactic bulge

no code implementations11 Feb 2021 Haopeng Zhang, Yuqin Chen, Gang Zhao, Jingkun Zhao, Xilong Liang, Haining Li, Yaqian Wu, Ali Luo, Rui Wang

A tentative interpretation of this special group is that its stars were formed in the X-shaped bar/bulge region, close to its corotation radius, where radial migration is the most intense, and brings them to present locations at 9 kpc and beyond.

Astrophysics of Galaxies Solar and Stellar Astrophysics

Text Compression-aided Transformer Encoding

no code implementations11 Feb 2021 Zuchao Li, Zhuosheng Zhang, Hai Zhao, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita

In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily.

Text Compression

Methodology-centered review of molecular modeling, simulation, and prediction of SARS-CoV-2

no code implementations1 Feb 2021 Kaifu Gao, Rui Wang, Jiahui Chen, Limei Cheng, Jaclyn Frishcosy, Yuta Huzumi, Yuchi Qiu, Tom Schluckbier, Guo-Wei Wei

To provide the reader a quick update about the status of molecular modeling, simulation, and prediction of SARS-CoV-2, we present a comprehensive and systematic methodology-centered narrative in the nick of time.

Drug Discovery

Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry

no code implementations1 Feb 2021 Mariia Gladkova, Rui Wang, Niclas Zeller, Daniel Cremers

To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely on feature matching to associate online visual odometry (VO) with a previously built map.

Visual Odometry

Uniform Object Rearrangement: From Complete Monotone Primitives to Efficient Non-Monotone Informed Search

no code implementations28 Jan 2021 Rui Wang, Kai Gao, Daniel Nakhimovich, Jingjin Yu, Kostas E. Bekris

DFSDP is extended to solve single-buffer, non-monotone instances, given a choice of an object and a buffer.

Edge Federated Learning Via Unit-Modulus Over-The-Air Computation (Extended Version)

no code implementations28 Jan 2021 Shuai Wang, Yuncong Hong, Rui Wang, Qi Hao, Yik-Chung Wu, Derrick Wing Kwan Ng

Simulation results show that the proposed UM-AirComp framework with PAM algorithm not only achieves a smaller mean square error of model parameters' estimation, training loss, and testing error, but also requires a significantly shorter runtime than that of other benchmark schemes.

Autonomous Driving Federated Learning

To Understand Representation of Layer-aware Sequence Encoders as Multi-order-graph

no code implementations16 Jan 2021 Sufeng Duan, Hai Zhao, Rui Wang

In this paper, we propose a unified explanation of representation for layer-aware neural sequence encoders, which regards the representation as a revisited multigraph called multi-order-graph (MoG), so that model encoding can be viewed as a processing to capture all subgraphs in MoG.

Machine Translation Translation

Theory of competing Chern-Simons orders and emergent phase transitions

no code implementations13 Jan 2021 Rui Wang, Z. Y. Xie, Baigeng Wang, Tigran Sedrakyan

Namely, the Chern-Simons superconductor describes the planar N\'{e}el state, while the Chern-Simons exciton insulator corresponds to the non-uniform chiral spin-liquid.

Strongly Correlated Electrons

Turbulence suppression by streamwise-varying wall rotation in pipe flow

no code implementations6 Jan 2021 Xu Liu, Hongbo Zhu, Rui Wang, Yan Bao, Dai Zhou, Zhaolong Han, Chuanqing Zhou, Yegao Qu, Hui Xu

Direct numerical simulations of turbulent pipe flow subjected to streamwise-varying wall rotation are performed.

Fluid Dynamics

On Secure Degrees of Freedom of the MIMO Interference Channel with Local Output Feedback

no code implementations3 Jan 2021 Tong Zhang, Yinfei Xu, Shuai Wang, Miaowen Wen, Rui Wang

This paper studies the problem of sum-secure degrees of freedom (SDoF) of the (M, M, N, N) multiple-input multiple-output (MIMO) interference channel with local output feedback, so as to build an information-theoretic foundation and provide practical transmission schemes for 6G-enabled vehicles-to-vehicles (V2V).

Information Theory Information Theory

Prior Knowledge Representation for Self-Attention Networks

no code implementations1 Jan 2021 Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita

Self-attention networks (SANs) have shown promising empirical results in various natural language processing tasks.

Translation

Cross-lingual Transfer Learning for Pre-trained Contextualized Language Models

no code implementations1 Jan 2021 Zuchao Li, Kevin Barry Parnow, Hai Zhao, Zhuosheng Zhang, Rui Wang, Masao Utiyama, Eiichiro Sumita

Though the pre-trained contextualized language model (PrLM) has made a significant impact on NLP, training PrLMs in languages other than English can be impractical for two reasons: other languages often lack corpora sufficient for training powerful PrLMs, and because of the commonalities among human languages, computationally expensive PrLM training for different languages is somewhat redundant.

Cross-Lingual Transfer Language Modelling +3

PreDet: Large-Scale Weakly Supervised Pre-Training for Detection

no code implementations ICCV 2021 Vignesh Ramanathan, Rui Wang, Dhruv Mahajan

State-of-the-art object detection approaches typically rely on pre-trained classification models to achieve better performance and faster convergence.

Classification Contrastive Learning +2

SG-Net: Syntax Guided Transformer for Language Representation

no code implementations27 Dec 2020 Zhuosheng Zhang, Yuwei Wu, Junru Zhou, Sufeng Duan, Hai Zhao, Rui Wang

In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.

Machine Reading Comprehension Machine Translation +2

Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks

no code implementations25 Dec 2020 Shanfeng Huang, Shuai Wang, Rui Wang, Miaowen Wen, Kaibin Huang

The ever-growing popularity and rapid improving of artificial intelligence (AI) have raised rethinking on the evolution of wireless networks.

3D Object Detection Autonomous Driving +1

Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network

no code implementations11 Dec 2020 Yuanzhe Geng, Erwu Liu, Rui Wang, Yiming Liu, Jie Wang, Gang Shen, Zhao Dong

Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication.

Information Theory Systems and Control Systems and Control Information Theory

SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis

1 code implementation COLING 2020 Jie zhou, Junfeng Tian, Rui Wang, Yuanbin Wu, Wenming Xiao, Liang He

However, due to the variety of users{'} emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain.

Language Modelling Sentiment Analysis

Semantic Role Labeling with Heterogeneous Syntactic Knowledge

1 code implementation COLING 2020 Qingrong Xia, Rui Wang, Zhenghua Li, Yue Zhang, Min Zhang

Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention.

Semantic Role Labeling

SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition

1 code implementation CVPR 2021 Yan Xia, Yusheng Xu, Shuang Li, Rui Wang, Juan Du, Daniel Cremers, Uwe Stilla

We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors.

Metric Learning Point Cloud Retrieval +1

Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems

2 code implementations20 Nov 2020 Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu

While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.

Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network

no code implementations10 Nov 2020 Yuanzhe Geng, Erwu Liu, Rui Wang, Yiming Liu

Simulation results reveal that compared with traditional DRL method, the HRL training algorithm can reach convergence 30 training iterations earlier and reduce the outage probability by 5% in two-hop relay network with the same outage threshold.

Hierarchical Reinforcement Learning

Chunk-based Chinese Spelling Check with Global Optimization

no code implementations Findings of the Association for Computational Linguistics 2020 Zuyi Bao, Chen Li, Rui Wang

Chinese spelling check is a challenging task due to the characteristics of the Chinese language, such as the large character set, no word boundary, and short word length.

Global Optimization Optical Character Recognition

Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment

no code implementations29 Oct 2020 Liangkai Zhou, Yuncong Hong, Shuai Wang, Ruihua Han, Dachuan Li, Rui Wang, Qi Hao

Edge intelligence is an emerging network architecture that integrates sensing, communication, computing components, and supports various machine learning applications, where a fundamental communication question is: how to allocate the limited wireless resources (such as time, energy) to the simultaneous model training of heterogeneous learning tasks?

Edge-computing

Prediction and mitigation of mutation threats to COVID-19 vaccines and antibody therapies

no code implementations13 Oct 2020 Jiahui Chen, Kaifu Gao, Rui Wang, GuoWei Wei

This discovery implies the vulnerability of current vaccines and antibody drugs to new mutations.

Investigating Constraint Relationship in Evolutionary Many-Constraint Optimization

no code implementations9 Oct 2020 Mengjun Ming, Rui Wang, Tao Zhang

This paper contributes to the treatment of extensive constraints in evolutionary many-constraint optimization through consideration of the relationships between pair-wise constraints.

Neural Topic Modeling with Cycle-Consistent Adversarial Training

no code implementations EMNLP 2020 Xuemeng Hu, Rui Wang, Deyu Zhou, Yuxuan Xiong

ToMCAT employs a generator network to interpret topics and an encoder network to infer document topics.

Text Classification

Neural Topic Modeling by Incorporating Document Relationship Graph

no code implementations EMNLP 2020 Deyu Zhou, Xuemeng Hu, Rui Wang

Graph Neural Networks (GNNs) that capture the relationships between graph nodes via message passing have been a hot research direction in the natural language processing community.

Graph-to-Sequence Neural Machine Translation

no code implementations16 Sep 2020 Sufeng Duan, Hai Zhao, Rui Wang

In the light of the current NMT models more or less capture graph information among the sequence in a latent way, we present a graph-to-sequence model facilitating explicit graph information capturing.

Graph-to-Sequence Machine Translation +1

Host immune response driving SARS-CoV-2 evolution

no code implementations17 Aug 2020 Rui Wang, Yuta Hozumi, Yong-Hui Zheng, Changchuan Yin, Guo-Wei Wei

Additionally, we show that children under age five and the elderly may be at high risk from COVID-19 because of their overreacting to the viral infection.

What leads to generalization of object proposals?

no code implementations13 Aug 2020 Rui Wang, Dhruv Mahajan, Vignesh Ramanathan

It is lucrative to train a good proposal model, that generalizes to unseen classes.

Object Proposal Generation

Safe and Effective Picking Paths in Clutter given Discrete Distributions of Object Poses

no code implementations11 Aug 2020 Rui Wang, Chaitanya Mitash, Shiyang Lu, Daniel Boehm, Kostas E. Bekris

This work proposes first a perception process for 6D pose estimation, which returns a discrete distribution of object poses in a scene.

6D Pose Estimation

Characterizing SARS-CoV-2 mutations in the United States

no code implementations24 Jul 2020 Rui Wang, Jiahui Chen, Kaifu Gao, Yuta Hozumi, Changchuan Yin, Guo-Wei Wei

Using genotyping, sequence-alignment, time-evolution, $k$-means clustering, protein-folding stability, algebraic topology, and network theory, we reveal that the US SARS-CoV-2 has four substrains and five top US SARS-CoV-2 mutations were first detected in China (2 cases), Singapore (2 cases), and the United Kingdom (1 case).

Protein Folding

Learning Centric Power Allocation for Edge Intelligence

no code implementations21 Jul 2020 Shuai Wang, Rui Wang, Qi Hao, Yik-Chung Wu, H. Vincent Poor

While machine-type communication (MTC) devices generate massive data, they often cannot process this data due to limited energy and computation power.

Fairness

DeepNetQoE: Self-adaptive QoE Optimization Framework of Deep Networks

no code implementations17 Jul 2020 Rui Wang, Min Chen, Nadra Guizani, Yong Li, Hamid Gharavi, Kai Hwang

A self-adaptive QoE model is set up that relates the model's accuracy with the computing resources required for training which will allow the experience value of the model to improve.

Crowd Counting

Accuracy Prediction with Non-neural Model for Neural Architecture Search

1 code implementation9 Jul 2020 Renqian Luo, Xu Tan, Rui Wang, Tao Qin, Enhong Chen, Tie-Yan Liu

Considering that most architectures are represented as sequences of discrete symbols which are more like tabular data and preferred by non-neural predictors, in this paper, we study an alternative approach which uses non-neural model for accuracy prediction.

Neural Architecture Search

Decoding asymptomatic COVID-19 infection and transmission

no code implementations2 Jul 2020 Rui Wang, Yuta Hozumi, Changchuan Yin, Guo-Wei Wei

By analyzing the distribution of 11083G>T in various countries, we unveil that 11083G>T may correlate with the hypotoxicity of SARS-CoV-2.

Topological Data Analysis

Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks

no code implementations ACL 2020 Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang

The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9. 29 over the syntax-agnostic baseline.

Fine-Grained Opinion Analysis Multi-Task Learning

Content Word Aware Neural Machine Translation

no code implementations ACL 2020 Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita

Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-by-word.

Machine Translation Translation

Beamspace Channel Estimation for Wideband Millimeter-Wave MIMO: A Model-Driven Unsupervised Learning Approach

no code implementations30 Jun 2020 Hengtao He, Rui Wang, Weijie Jin, Shi Jin, Chao-Kai Wen, Geoffrey Ye Li

By utilizing the Stein's unbiased risk estimator loss, the LDGEC network can be trained only with limited measurements corresponding to the pilot symbols, instead of the real channel data.

Compressive Sensing Denoising

Hardware-irrelevant parallel processing system

no code implementations24 Jun 2020 Xiuting Zou, Shaofu Xu, Anyi Deng, Rui Wang, Weiwen Zou

We propose a hardware-irrelevant PPS of which the performance is unaffected by hardware deviations.

Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage

1 code implementation22 Jun 2020 Shijing Si, Rui Wang, Jedrek Wosik, Hao Zhang, David Dov, Guoyin Wang, Ricardo Henao, Lawrence Carin

Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models.

VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines

no code implementations CVPR 2020 Rui Wang, David Geraghty, Kevin Matzen, Richard Szeliski, Jan-Michael Frahm

Starting from a color image and a Manhattan line map, we use a deep neural network to regress on a dense normal map, and a dense Manhattan label map that identifies planar regions aligned with the Manhattan directions.

Depth Estimation

Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond

1 code implementation13 May 2020 Zhuosheng Zhang, Hai Zhao, Rui Wang

In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches.

Machine Reading Comprehension Text Matching

Aortic Pressure Forecasting with Deep Sequence Learning

no code implementations12 May 2020 Eliza Huang, Rui Wang, Uma Chandrasekaran, Rose Yu

The aim of this study was to forecast the mean aortic pressure five minutes in advance, using the 25 Hz time series data of previous five minutes as input.

Time Series

AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack

no code implementations6 May 2020 Ao Liu, Beibei Li, Tao Li, Pan Zhou, Rui Wang

In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks.

Adversarial Attack Classification +3

Mutations on COVID-19 diagnostic targets

no code implementations5 May 2020 Rui Wang, Yuta Hozumi, Changchuan Yin, Guo-Wei Wei

Effective, sensitive, and reliable diagnostic reagents are of paramount importance for combating the ongoing coronavirus disease 2019 (COVID-19) pandemic at a time there is no preventive vaccine nor specific drug available for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Data-dependent Gaussian Prior Objective for Language Generation

no code implementations ICLR 2020 Zuchao Li, Rui Wang, Kehai Chen, Masso Utiyama, Eiichiro Sumita, Zhuosheng Zhang, Hai Zhao

However, MLE focuses on once-to-all matching between the predicted sequence and gold-standard, consequently treating all incorrect predictions as being equally incorrect.

Image Captioning L2 Regularization +4

Neural Machine Translation with Universal Visual Representation

1 code implementation ICLR 2020 Zhuosheng Zhang, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Zuchao Li, Hai Zhao

Though visual information has been introduced for enhancing neural machine translation (NMT), its effectiveness strongly relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations.

Machine Translation Translation

Decoding SARS-CoV-2 transmission, evolution and ramification on COVID-19 diagnosis, vaccine, and medicine

no code implementations29 Apr 2020 Rui Wang, Yuta Hozumi, Changchuan Yin, Guo-Wei Wei

Tremendous effort has been given to the development of diagnostic tests, preventive vaccines, and therapeutic medicines for coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

COVID-19 Diagnosis

Syntax-aware Data Augmentation for Neural Machine Translation

no code implementations29 Apr 2020 Sufeng Duan, Hai Zhao, Dong-dong Zhang, Rui Wang

Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data.

Data Augmentation Machine Translation +1

Neural Topic Modeling with Bidirectional Adversarial Training

1 code implementation ACL 2020 Rui Wang, Xuemeng Hu, Deyu Zhou, Yulan He, Yuxuan Xiong, Chenchen Ye, Haiyang Xu

Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topic models such as Latent Dirichlet Allocation (LDA).

Text Clustering Topic Models

Multi-Domain Dialogue Acts and Response Co-Generation

1 code implementation ACL 2020 Kai Wang, Junfeng Tian, Rui Wang, Xiaojun Quan, Jianxing Yu

Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed.

Task-Oriented Dialogue Systems

Self Punishment and Reward Backfill for Deep Q-Learning

1 code implementation10 Apr 2020 Mohammad Reza Bonyadi, Rui Wang, Maryam Ziaei

Reinforcement learning agents learn by encouraging behaviours which maximize their total reward, usually provided by the environment.

Atari Games Q-Learning

Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios

no code implementations NAACL 2021 Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks.

Machine Translation Translation

Explicit Reordering for Neural Machine Translation

no code implementations8 Apr 2020 Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita

Thus, we propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT.

Machine Translation Translation

Deep Manifold Prior

no code implementations8 Apr 2020 Matheus Gadelha, Rui Wang, Subhransu Maji

We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization.

Denoising Gaussian Processes

Learning Generative Models of Shape Handles

no code implementations CVPR 2020 Matheus Gadelha, Giorgio Gori, Duygu Ceylan, Radomir Mech, Nathan Carr, Tamy Boubekeur, Rui Wang, Subhransu Maji

We present a generative model to synthesize 3D shapes as sets of handles -- lightweight proxies that approximate the original 3D shape -- for applications in interactive editing, shape parsing, and building compact 3D representations.

Reference Language based Unsupervised Neural Machine Translation

1 code implementation Findings of the Association for Computational Linguistics 2020 Zuchao Li, Hai Zhao, Rui Wang, Masao Utiyama, Eiichiro Sumita

Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism.

Machine Translation Translation

SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization

no code implementations3 Apr 2020 Qi Duan, Guotai Wang, Rui Wang, Chao Fu, Xinjun Li, Maoliang Gong, Xinglong Liu, Qing Xia, Xiaodi Huang, Zhiqiang Hu, Ning Huang, Shaoting Zhang

To this end, we have developed SenseCare research platform for smart healthcare, which is designed to boost translational research on intelligent diagnosis and treatment planning in various clinical scenarios.

Human-Computer Interaction Image and Video Processing

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

1 code implementation ICML 2020 Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeff Clune, Kenneth O. Stanley

Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning.

Fake Generated Painting Detection via Frequency Analysis

no code implementations5 Mar 2020 Yong Bai, Yuanfang Guo, Jinjie Wei, Lin Lu, Rui Wang, Yunhong Wang

With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms. To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts.

Style Transfer

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

no code implementations CVPR 2020 Nan Yang, Lukas von Stumberg, Rui Wang, Daniel Cremers

We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation.

Monocular Depth Estimation Monocular Visual Odometry

Modeling Future Cost for Neural Machine Translation

no code implementations28 Feb 2020 Chaoqun Duan, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Conghui Zhu, Tiejun Zhao

Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible.

Machine Translation Translation

Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

1 code implementation21 Feb 2020 Ashley D. Edwards, Himanshu Sahni, Rosanne Liu, Jane Hung, Ankit Jain, Rui Wang, Adrien Ecoffet, Thomas Miconi, Charles Isbell, Jason Yosinski

In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.

Imitation Learning Transfer Learning

Incorporating Symmetry into Deep Dynamics Models for Improved Generalization

no code implementations ICLR 2021 Rui Wang, Robin Walters, Rose Yu

Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers.

Deep Audio-Visual Learning: A Survey

no code implementations14 Jan 2020 Hao Zhu, Mandi Luo, Rui Wang, Aihua Zheng, Ran He

Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully.

audio-visual learning Representation Learning

Knowledge Graph Embedding via Graph Attenuated Attention Networks

no code implementations IEEE Access 2019 Rui Wang, Bicheng Li, Shengwei Hu, Wenqian Du, Min Zhang

However, these methods assign the same weights on the relation path in the knowledge graph and ignore the rich information presented in neighbor nodes, which result in incomplete mining of triple features.

Knowledge Base Completion Knowledge Graph Completion +3

Explicit Sentence Compression for Neural Machine Translation

1 code implementation27 Dec 2019 Zuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang, Hai Zhao

In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT.

Machine Translation Sentence Compression +1

Towards Physics-informed Deep Learning for Turbulent Flow Prediction

1 code implementation20 Nov 2019 Rui Wang, Karthik Kashinath, Mustafa Mustafa, Adrian Albert, Rose Yu

While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models.

Machine Intelligence at the Edge with Learning Centric Power Allocation

no code implementations12 Nov 2019 Shuai Wang, Yik-Chung Wu, Minghua Xia, Rui Wang, H. Vincent Poor

However, power allocation in this paradigm requires maximizing the learning performance instead of the communication throughput, for which the celebrated water-filling and max-min fairness algorithms become inefficient.

Fairness Learning Theory

Probing Contextualized Sentence Representations with Visual Awareness

no code implementations7 Nov 2019 Zhuosheng Zhang, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Hai Zhao

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations.

Machine Translation Natural Language Inference +1

SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing

no code implementations CONLL 2019 Zuchao Li, Hai Zhao, Zhuosheng Zhang, Rui Wang, Masao Utiyama, Eiichiro Sumita

This paper describes our SJTU-NICT{'}s system for participating in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).

Multi-Task Learning

English-Myanmar Supervised and Unsupervised NMT: NICT's Machine Translation Systems at WAT-2019

no code implementations WS 2019 Rui Wang, Haipeng Sun, Kehai Chen, Chenchen Ding, Masao Utiyama, Eiichiro Sumita

This paper presents the NICT{'}s participation (team ID: NICT) in the 6th Workshop on Asian Translation (WAT-2019) shared translation task, specifically Myanmar (Burmese) - English task in both translation directions.

Language Modelling Machine Translation +1

SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT

no code implementations CONLL 2019 Yue Zhang, Wei Jiang, Qingrong Xia, Junjie Cao, Rui Wang, Zhenghua Li, Min Zhang

Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.

Multi-Task Learning POS

Document-level Neural Machine Translation with Associated Memory Network

no code implementations31 Oct 2019 Shu Jiang, Rui Wang, Zuchao Li, Masao Utiyama, Kehai Chen, Eiichiro Sumita, Hai Zhao, Bao-liang Lu

Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network.

Document-level Machine Translation +1

Attention Optimization for Abstractive Document Summarization

no code implementations IJCNLP 2019 Min Gui, Junfeng Tian, Rui Wang, Zhenglu Yang

Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models.

Document Summarization

Syntax-Enhanced Self-Attention-Based Semantic Role Labeling

no code implementations IJCNLP 2019 Yue Zhang, Rui Wang, Luo Si

As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence.

Semantic Role Labeling

First-Order Preconditioning via Hypergradient Descent

1 code implementation18 Oct 2019 Ted Moskovitz, Rui Wang, Janice Lan, Sanyam Kapoor, Thomas Miconi, Jason Yosinski, Aditya Rawal

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space. These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence.

Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards

1 code implementation NeurIPS 2019 Siyuan Li, Rui Wang, Minxue Tang, Chongjie Zhang

In addition, we also theoretically prove that optimizing low-level skills with this auxiliary reward will increase the task return for the joint policy.

Hierarchical Reinforcement Learning

More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation

2 code implementations16 Sep 2019 Kai-Xuan Chen, Xiao-Jun Wu, Jie-Yi Ren, Rui Wang, Josef Kittler

We consider a family of structural descriptors for visual data, namely covariance descriptors (CovDs) that lie on a non-linear symmetric positive definite (SPD) manifold, a special type of Riemannian manifolds.

Regularized Context Gates on Transformer for Machine Translation

no code implementations ACL 2020 Xintong Li, Lemao Liu, Rui Wang, Guoping Huang, Max Meng

This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer.

Machine Translation Translation

Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation

no code implementations26 Aug 2019 Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao, Chenhui Chu

However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs.

Domain Adaptation Machine Translation +1

Open Event Extraction from Online Text using a Generative Adversarial Network

no code implementations IJCNLP 2019 Rui Wang, Deyu Zhou, Yulan He

Experimental results show that our model outperforms the baseline approaches on all the datasets, with more significant improvements observed on the news article dataset where an increase of 15\% is observed in F-measure.

Event Extraction

SG-Net: Syntax-Guided Machine Reading Comprehension

1 code implementation14 Aug 2019 Zhuosheng Zhang, Yuwei Wu, Junru Zhou, Sufeng Duan, Hai Zhao, Rui Wang

In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.

Language Modelling Machine Reading Comprehension +1

Multiple Riemannian Manifold-valued Descriptors based Image Set Classification with Multi-Kernel Metric Learning

no code implementations6 Aug 2019 Rui Wang, Xiao-Jun Wu, Josef Kittler

Specifically, the covariance matrix, linear subspace, and Gaussian distribution are applied for set representation simultaneously.

Classification Emotion Recognition +4

NICT's Supervised Neural Machine Translation Systems for the WMT19 News Translation Task

no code implementations WS 2019 Raj Dabre, Kehai Chen, Benjamin Marie, Rui Wang, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita

In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions.

Machine Translation Transfer Learning +1

Syntax-aware Neural Semantic Role Labeling

1 code implementation22 Jul 2019 Qingrong Xia, Zhenghua Li, Min Zhang, Meishan Zhang, Guohong Fu, Rui Wang, Luo Si

Semantic role labeling (SRL), also known as shallow semantic parsing, is an important yet challenging task in NLP.

Semantic Parsing Semantic Role Labeling

Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors

no code implementations17 Jul 2019 Shaofu Xu, Rui Wang, Jianping Chen, Lei Yu, Weiwen Zou

However, the quality of the signals may be degraded by defective photonic analog links, especially in a complicated MWP system.

Distilling with Residual Network for Single Image Super Resolution

no code implementations5 Jul 2019 Xiaopeng Sun, Wen Lu, Rui Wang, Furui Bai

Recently, the deep convolutional neural network (CNN) has made remarkable progress in single image super resolution(SISR).

Image Reconstruction Image Super-Resolution

Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation

no code implementations ACL 2019 Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT.

Denoising Machine Translation +1

Sentence-Level Agreement for Neural Machine Translation

no code implementations ACL 2019 Mingming Yang, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Min Zhang, Tiejun Zhao

The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references.

Machine Translation Translation

Semi-supervised Domain Adaptation for Dependency Parsing

1 code implementation ACL 2019 Zhenghua Li, Xue Peng, Min Zhang, Rui Wang, Luo Si

During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data.

Chinese Dependency Parsing Dependency Parsing +2

Inferring 3D Shapes from Image Collections using Adversarial Networks

no code implementations11 Jun 2019 Matheus Gadelha, Aartika Rai, Subhransu Maji, Rui Wang

To this end, we present new differentiable projection operators that can be used by PrGAN to learn better 3D generative models.

Deep Reinforcement Learning for Multi-objective Optimization

no code implementations6 Jun 2019 Kaiwen Li, Tao Zhang, Rui Wang

The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time.

Lattice-Based Transformer Encoder for Neural Machine Translation

no code implementations ACL 2019 Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang, Kehai Chen

To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training.

Machine Translation Translation

Discriminative Clustering for Robust Unsupervised Domain Adaptation

no code implementations30 May 2019 Rui Wang, Guoyin Wang, Ricardo Henao

Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset.

Partial Domain Adaptation Unsupervised Domain Adaptation

CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks

1 code implementation28 May 2019 Weicheng Li, Rui Wang, Zhongzhi Luan, Di Huang, Zidong Du, Yunji Chen, Depei Qian

Convolutional Neural Network (CNN) based Deep Learning (DL) has achieved great progress in many real-life applications.

Image Classification