Search Results for author: Lei Yu

Found 48 papers, 10 papers with code

Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining

1 code implementation10 Sep 2021 Lei Yu, Yang Xu

Natural language relies on a finite lexicon to express an unbounded set of emerging ideas.

Diverse Pretrained Context Encodings Improve Document Translation

no code implementations ACL 2021 Domenic Donato, Lei Yu, Chris Dyer

We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining approaches for generating these signals, (2) the quantity of parallel data for which document context is available, and (3) conditioning on source, target, or source and target contexts.

Document Translation

Pretraining the Noisy Channel Model for Task-Oriented Dialogue

no code implementations18 Mar 2021 Qi Liu, Lei Yu, Laura Rimell, Phil Blunsom

Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses.

Event-based Synthetic Aperture Imaging with a Hybrid Network

no code implementations CVPR 2021 Xiang Zhang, Wei Liao, Lei Yu, Wen Yang, Gui-Song Xia

Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images.

Style Transfer

ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

1 code implementation6 Nov 2020 Hao Li, Huai Yu, Wen Yang, Lei Yu, Sebastian Scherer

Targeting at the unified line segment detection (ULSD) for both distorted and undistorted images, we propose to represent line segments with the Bezier curve model.

Line Segment Detection

Inferring symmetry in natural language

1 code implementation Findings of the Association for Computational Linguistics 2020 Chelsea Tanchip, Lei Yu, Aotao Xu, Yang Xu

Our results show that a hybrid transfer learning model that integrates linguistic features with contextualized language models most faithfully predicts the empirical data.

Transfer Learning

Improving Spiking Sparse Recovery via Non-Convex Penalties

no code implementations19 Sep 2020 Xiang Zhang, Lei Yu, Gang Zheng

Compared with digital methods, sparse recovery based on spiking neural networks has great advantages like high computational efficiency and low power-consumption.

Mixed Noise Removal with Pareto Prior

no code implementations27 Aug 2020 Zhou Liu, Lei Yu, Gui-Song Xia, Hong Sun

To address this problem, we exploit the Pareto distribution as the priori of the weighting matrix, based on which an accurate and robust weight estimator is proposed for mixed noise removal.


Event Enhanced High-Quality Image Recovery

1 code implementation ECCV 2020 Bishan Wang, Jingwei He, Lei Yu, Gui-Song Xia, Wen Yang

To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras.

Denoising Sparse Learning +1

Implicit Euler ODE Networks for Single-Image Dehazing

no code implementations13 Jul 2020 Jiawei Shen, Zhuoyan Li, Lei Yu, Gui-Song Xia, Wen Yang

Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem.

Image Dehazing Single Image Dehazing

Kernel Learning for High-Resolution Time-Frequency Distribution

1 code implementation1 Jul 2020 Lei Jiang, Haijian Zhang, Lei Yu, Guang Hua

To break the current limitation, we propose a data-driven kernel learning model directly based on Wigner-Ville distribution (WVD).

IsarStep: a Benchmark for High-level Mathematical Reasoning

no code implementations ICLR 2021 Wenda Li, Lei Yu, Yuhuai Wu, Lawrence C. Paulson

In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models.

Mathematical Proofs

Robust Time-Frequency Reconstruction by Learning Structured Sparsity

no code implementations30 Apr 2020 Lei Jiang, Haijian Zhang, Lei Yu

Time-frequency distributions (TFDs) play a vital role in providing descriptive analysis of non-stationary signals involved in realistic scenarios.

Capturing document context inside sentence-level neural machine translation models with self-training

no code implementations11 Mar 2020 Elman Mansimov, Gábor Melis, Lei Yu

Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level.

Document-level Machine Translation

Matching Neuromorphic Events and Color Images via Adversarial Learning

no code implementations2 Mar 2020 Fang Xu, Shijie Lin, Wen Yang, Lei Yu, Dengxin Dai, Gui-Song Xia

The event camera has appealing properties: high dynamic range, low latency, low power consumption and low memory usage, and thus provides complementariness to conventional frame-based cameras.

Image Retrieval

Edge-Isoperimetric Inequalities and Ball-Noise Stability: Linear Programming and Probabilistic Approaches

no code implementations9 Feb 2020 Lei Yu

Our bound derived by using the second approach is asymptotically sharp as $n\to\infty$ when $r=2\left\lfloor \frac{\beta n}{2}\right\rfloor +1$ and $M=\left\lfloor \alpha2^{n}\right\rfloor $ for fixed $\alpha,\beta\in(0, 1)$, and sharp up to a constant factor when $r=2\left\lfloor \frac{\beta n}{2}\right\rfloor $ and $M=\left\lfloor \alpha2^{n}\right\rfloor $.

Combinatorics Information Theory Information Theory Probability

Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability

no code implementations21 Nov 2019 Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Wenqi Wei, Lei Yu

Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed.

Inference Attack Membership Inference Attack

Maximum Entropy Diverse Exploration: Disentangling Maximum Entropy Reinforcement Learning

no code implementations3 Nov 2019 Andrew Cohen, Lei Yu, Xingye Qiao, Xiangrong Tong

A theoretical investigation shows that the set of policies learned by MEDE capture the same modalities as the optimal maximum entropy policy.

A Mutual Information Maximization Perspective of Language Representation Learning

no code implementations ICLR 2020 Lingpeng Kong, Cyprien de Masson d'Autume, Wang Ling, Lei Yu, Zihang Dai, Dani Yogatama

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i. e., a sentence).

Representation Learning

Learning Cluster Structured Sparsity by Reweighting

no code implementations11 Oct 2019 Yulun Jiang, Lei Yu, Haijian Zhang, Zhou Liu

Recently, the paradigm of unfolding iterative algorithms into finite-length feed-forward neural networks has achieved a great success in the area of sparse recovery.

Sparse Learning

Better Document-Level Machine Translation with Bayes' Rule

no code implementations TACL 2020 Lei Yu, Laurent Sartran, Wojciech Stokowiec, Wang Ling, Lingpeng Kong, Phil Blunsom, Chris Dyer

We show that Bayes' rule provides an effective mechanism for creating document translation models that can be learned from only parallel sentences and monolingual documents---a compelling benefit as parallel documents are not always available.

Document-level Document Level Machine Translation +3

Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks

1 code implementation18 Aug 2019 Yanzhao Wu, Ling Liu, Juhyun Bae, Ka-Ho Chow, Arun Iyengar, Calton Pu, Wenqi Wei, Lei Yu, Qi Zhang

Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).

CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network

no code implementations3 Aug 2019 Menglei Zhang, Zhou Liu, Lei Yu

Convolutional Sparse Coding (CSC) has been attracting more and more attention in recent years, for making full use of image global correlation to improve performance on various computer vision applications.

Image Super-Resolution

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.

Facial Feature Embedded CycleGAN for VIS-NIR Translation

no code implementations20 Apr 2019 Huijiao Wang, Li Wang, Xulei Yang, Lei Yu, Haijian Zhang

VIS-NIR face recognition remains a challenging task due to the distinction between spectral components of two modalities and insufficient paired training data.

Face Recognition

Intra-Ensemble in Neural Networks

no code implementations9 Apr 2019 Yuan Gao, Zixiang Cai, Lei Yu

In this work, we propose Intra-Ensemble, an end-to-end ensemble strategy with stochastic channel recombination operations to train several sub-networks simultaneously within one neural network.

Unsupervised Recurrent Neural Network Grammars

1 code implementation NAACL 2019 Yoon Kim, Alexander M. Rush, Lei Yu, Adhiguna Kuncoro, Chris Dyer, Gábor Melis

On language modeling, unsupervised RNNGs perform as well their supervised counterparts on benchmarks in English and Chinese.

Ranked #5 on Constituency Grammar Induction on PTB (Max F1 (WSJ) metric)

Constituency Grammar Induction Language Modelling +1

Differentially Private Model Publishing for Deep Learning

no code implementations3 Apr 2019 Lei Yu, Ling Liu, Calton Pu, Mehmet Emre Gursoy, Stacey Truex

However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage.

Diverse Exploration via Conjugate Policies for Policy Gradient Methods

no code implementations10 Feb 2019 Andrew Cohen, Xingye Qiao, Lei Yu, Elliot Way, Xiangrong Tong

We address the challenge of effective exploration while maintaining good performance in policy gradient methods.

Policy Gradient Methods

Learning and Evaluating General Linguistic Intelligence

no code implementations31 Jan 2019 Dani Yogatama, Cyprien de Masson d'Autume, Jerome Connor, Tomas Kocisky, Mike Chrzanowski, Lingpeng Kong, Angeliki Lazaridou, Wang Ling, Lei Yu, Chris Dyer, Phil Blunsom

We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly.

Natural Language Understanding Question Answering

Variational Smoothing in Recurrent Neural Network Language Models

no code implementations ICLR 2019 Lingpeng Kong, Gabor Melis, Wang Ling, Lei Yu, Dani Yogatama

We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017).

Language Modelling

Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding

no code implementations31 Dec 2018 Menglei Zhang, Zhou Liu, Lei Yu

We extend LISTA to its convolutional version and build the main part of our model by strictly following the convolutional form, which improves the network's interpretability.

Image Super-Resolution

Tackling Sequence to Sequence Mapping Problems with Neural Networks

no code implementations25 Oct 2018 Lei Yu

In Natural Language Processing (NLP), it is important to detect the relationship between two sequences or to generate a sequence of tokens given another observed sequence.

Domain Adaptation Feature Engineering +1

Adversarial Examples in Deep Learning: Characterization and Divergence

no code implementations29 Jun 2018 Wenqi Wei, Ling Liu, Margaret Loper, Stacey Truex, Lei Yu, Mehmet Emre Gursoy, Yanzhao Wu

The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data.

Adversarial Attack

Towards Demystifying Membership Inference Attacks

1 code implementation28 Jun 2018 Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Lei Yu, Wenqi Wei

Our empirical results additionally show that (1) using the type of target model under attack within the attack model may not increase attack effectiveness and (2) collaborative learning in federated systems exposes vulnerabilities to membership inference risks when the adversary is a participant in the federation.

Cryptography and Security

Diverse Exploration for Fast and Safe Policy Improvement

no code implementations22 Feb 2018 Andrew Cohen, Lei Yu, Robert Wright

We study an important yet under-addressed problem of quickly and safely improving policies in online reinforcement learning domains.

Automatic Streaming Segmentation of Stereo Video Using Bilateral Space

no code implementations10 Oct 2017 Wenjing Ke, Yuanjie Zhu, Lei Yu

In this paper, we take advantage of binocular camera and propose an unsupervised algorithm based on semi-supervised segmentation algorithm and extracting foreground part efficiently.

The Neural Noisy Channel

no code implementations8 Nov 2016 Lei Yu, Phil Blunsom, Chris Dyer, Edward Grefenstette, Tomas Kocisky

We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models.

Machine Translation Morphological Inflection

Online Segment to Segment Neural Transduction

no code implementations EMNLP 2016 Lei Yu, Jan Buys, Phil Blunsom

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read.

Morphological Inflection Sentence Summarization

GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring

no code implementations12 Apr 2016 Wenying Ma, Liangliang Cao, Lei Yu, Guoping Long, Yucheng Li

We also applied GPU-FV for realtime video monitoring tasks and found that GPU-FV outperforms a number of previous works.

Neural Variational Inference for Text Processing

6 code implementations19 Nov 2015 Yishu Miao, Lei Yu, Phil Blunsom

We validate this framework on two very different text modelling applications, generative document modelling and supervised question answering.

Answer Selection Latent Variable Models +2

The SYSU System for the Interspeech 2015 Automatic Speaker Verification Spoofing and Countermeasures Challenge

no code implementations24 Jul 2015 Shitao Weng, Shushan Chen, Lei Yu, Xuewei Wu, Weicheng Cai, Zhi Liu, Ming Li

In order to detect these spoofed speech signals as a countermeasure, we propose a score level fusion approach with several different i-vector subsystems.

Speaker Verification Speech Synthesis +1

Small Instance Detection by Integer Programming on Object Density Maps

no code implementations CVPR 2015 Zheng Ma, Lei Yu, Antoni B. Chan

For each region, a sliding window (ROI) is passed over the density map to calculate the instance count within each ROI.

Object Detection

Deep Learning for Answer Sentence Selection

2 code implementations4 Dec 2014 Lei Yu, Karl Moritz Hermann, Phil Blunsom, Stephen Pulman

Answer sentence selection is the task of identifying sentences that contain the answer to a given question.

Feature Engineering Open-Domain Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.