Search Results for author: Wei Peng

Found 42 papers, 15 papers with code

When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training

1 code implementation EMNLP (insights) 2021 Qi Zhu, Yuxian Gu, Lingxiao Luo, Bing Li, Cheng Li, Wei Peng, Minlie Huang, Xiaoyan Zhu

Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.


Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings

no code implementations EMNLP 2021 Weixuan Wang, Wei Peng, Meng Zhang, Qun Liu

Neural Machine Translation (NMT) has shown a strong ability to utilize local context to disambiguate the meaning of words.

Machine Translation Translation

Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer

1 code implementation ICCV 2021 Haoyu Chen, Hao Tang, Henglin Shi, Wei Peng, Nicu Sebe, Guoying Zhao

With the strength of deep generative models, 3D pose transfer regains intensive research interests in recent years.

Pose Transfer

TPRM: A Topic-based Personalized Ranking Model for Web Search

no code implementations13 Aug 2021 Minghui Huang, Wei Peng, Dong Wang

Ranking models have achieved promising results, but it remains challenging to design personalized ranking systems to leverage user profiles and semantic representations between queries and documents.

Document Ranking

A novel meta-learning initialization method for physics-informed neural networks

no code implementations23 Jul 2021 Xu Liu, Xiaoya Zhang, Wei Peng, Weien Zhou, Wen Yao

Inspired by this idea, we propose the new Reptile initialization to sample more tasks from the parameterized PDEs and adapt the penalty term of the loss.


IDRLnet: A Physics-Informed Neural Network Library

1 code implementation9 Jul 2021 Wei Peng, Jun Zhang, Weien Zhou, Xiaoyu Zhao, Wen Yao, Xiaoqian Chen

Physics Informed Neural Network (PINN) is a scientific computing framework used to solve both forward and inverse problems modeled by Partial Differential Equations (PDEs).

Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering

no code implementations4 Jul 2021 Luxi Xing, Yue Hu, Jing Yu, Yuqiang Xie, Wei Peng

It is prevalent to utilize external knowledge to help machine answer questions that need background commonsense, which faces a problem that unlimited knowledge will transmit noisy and misleading information.

Question Answering

Physics-Informed Deep Reversible Regression Model for Temperature Field Reconstruction of Heat-Source Systems

1 code implementation22 Jun 2021 Zhiqiang Gong, Weien Zhou, Jun Zhang, Wei Peng, Wen Yao

To solve this problem, this work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems (TFR-HSS), which can better reconstruct the temperature field with limited monitoring points unsupervisedly.

Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Tracking

no code implementations16 Jun 2021 Ting Han, Chongxuan Huang, Wei Peng

Dialogue State Tracking (DST), which is the process of inferring user goals by estimating belief states given the dialogue history, plays a critical role in task-oriented dialogue systems.

Dialogue State Tracking Task-Oriented Dialogue Systems

MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension

no code implementations8 Mar 2021 Wei Peng, Yue Hu, Jing Yu, Luxi Xing, Yuqiang Xie, Zihao Zhu, Yajing Sun

Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions.

Machine Reading Comprehension Question Answering

Hyperbolic Deep Neural Networks: A Survey

1 code implementation12 Jan 2021 Wei Peng, Tuomas Varanka, Abdelrahman Mostafa, Henglin Shi, Guoying Zhao

Recently, there has been a rising surge of momentum for deep representation learning in hyperbolic spaces due to theirhigh capacity of modeling data like knowledge graphs or synonym hierarchies, possessing hierarchical structure.

Hierarchical structure Knowledge Graphs +1

Robustness Testing of Language Understanding in Task-Oriented Dialog

2 code implementations ACL 2021 Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang

Most language understanding models in task-oriented dialog systems are trained on a small amount of annotated training data, and evaluated in a small set from the same distribution.

Data Augmentation Language understanding +1

A hybrid quantum-classical neural network with deep residual learning

no code implementations14 Dec 2020 Yanying Liang, Wei Peng, Zhu-Jun Zheng, Olli Silvén, Guoying Zhao

In this paper, a novel hybrid quantum-classical neural network with deep residual learning (Res-HQCNN) is proposed.

Quantum Machine Learning

Bi-directional CognitiveThinking Network for Machine Reading Comprehension

no code implementations COLING 2020 Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei

We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.

Machine Reading Comprehension

Bi-directional Cognitive Thinking Network for Machine Reading Comprehension

no code implementations20 Oct 2020 Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei

We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.

Machine Reading Comprehension

MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation

4 code implementations12 Oct 2020 Ting Han, Ximing Liu, Ryuichi Takanobu, Yixin Lian, Chongxuan Huang, Dazhen Wan, Wei Peng, Minlie Huang

In this paper, we introduce MultiWOZ 2. 3, in which we differentiate incorrect annotations in dialogue acts from dialogue states, identifying a lack of co-reference when publishing the updated dataset.

Dialogue State Tracking Language understanding +2

2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework

no code implementations10 Aug 2020 Haoyu Chen, Zitong Yu, Xin Liu, Wei Peng, Yoon Lee, Guoying Zhao

To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems.

Action Recognition Optical Flow Estimation

Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition

no code implementations30 Jul 2020 Wei Peng, Jingang Shi, Zhaoqiang Xia, Guoying Zhao

In human action recognition, current works introduce a dynamic graph generation mechanism to better capture the underlying semantic skeleton connections and thus improves the performance.

Action Recognition Graph Generation +1

Revealing the Invisible with Model and Data Shrinking for Composite-database Micro-expression Recognition

no code implementations17 Jun 2020 Zhaoqiang Xia, Wei Peng, Huai-Qian Khor, Xiaoyi Feng, Guoying Zhao

In this paper, we analyze the influence of learning complexity, including the input complexity and model complexity, and discover that the lower-resolution input data and shallower-architecture model are helpful to ease the degradation of deep models in composite-database task.

Micro-Expression Recognition Neural Architecture Search

Accelerating Physics-Informed Neural Network Training with Prior Dictionaries

1 code implementation17 Apr 2020 Wei Peng, Weien Zhou, Jun Zhang, Wen Yao

Physics-Informed Neural Networks (PINNs) can be regarded as general-purpose PDE solvers, but it might be slow to train PINNs on particular problems, and there is no theoretical guarantee of corresponding error bounds.

Applying Cyclical Learning Rate to Neural Machine Translation

no code implementations6 Apr 2020 Choon Meng Lee, Jianfeng Liu, Wei Peng

In training deep learning networks, the optimizer and related learning rate are often used without much thought or with minimal tuning, even though it is crucial in ensuring a fast convergence to a good quality minimum of the loss function that can also generalize well on the test dataset.

Machine Translation Translation

Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation

no code implementations6 Apr 2020 Wei Peng, Chongxuan Huang, Tian-Hao Li, Yun Chen, Qun Liu

Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora.

Data Augmentation Machine Translation +1

BLiMP: The Benchmark of Linguistic Minimal Pairs for English

3 code implementations TACL 2020 Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, Samuel R. Bowman

We introduce The Benchmark of Linguistic Minimal Pairs (shortened to BLiMP), a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English.

Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching

1 code implementation11 Nov 2019 Wei Peng, Xiaopeng Hong, Haoyu Chen, Guoying Zhao

Human action recognition from skeleton data, fueled by the Graph Convolutional Network (GCN), has attracted lots of attention, due to its powerful capability of modeling non-Euclidean structure data.

Action Recognition Neural Architecture Search +1

Huawei's NMT Systems for the WMT 2019 Biomedical Translation Task

no code implementations WS 2019 Wei Peng, Jianfeng Liu, Liangyou Li, Qun Liu

This paper describes Huawei{'}s neural machine translation systems for the WMT 2019 biomedical translation shared task.

Domain Adaptation Machine Translation +2

Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement

no code implementations ICCV 2019 Zitong Yu, Wei Peng, Xiaobai Li, Xiaopeng Hong, Guoying Zhao

The method includes two parts: 1) a Spatio-Temporal Video Enhancement Network (STVEN) for video enhancement, and 2) an rPPG network (rPPGNet) for rPPG signal recovery.

Video Compression Video Enhancement

Video Action Recognition Via Neural Architecture Searching

no code implementations10 Jul 2019 Wei Peng, Xiaopeng Hong, Guoying Zhao

Deep neural networks have achieved great success for video analysis and understanding.

Action Recognition

Asymptotic Distributions and Rates of Convergence for Random Forests via Generalized U-statistics

no code implementations25 May 2019 Wei Peng, Tim Coleman, Lucas Mentch

Random forests remain among the most popular off-the-shelf supervised learning algorithms.

Scalable and Efficient Hypothesis Testing with Random Forests

2 code implementations16 Apr 2019 Tim Coleman, Wei Peng, Lucas Mentch

Throughout the last decade, random forests have established themselves as among the most accurate and popular supervised learning methods.

Two-sample testing

An Integrated Autoencoder-Based Filter for Sparse Big Data

no code implementations13 Apr 2019 Baogui Xin, Wei Peng

We propose a novel filter for sparse big data, called an integrated autoencoder (IAE), which utilizes auxiliary information to mitigate data sparsity.

SPMF: A Social Trust and Preference Segmentation-based Matrix Factorization Recommendation Algorithm

no code implementations11 Mar 2019 Wei Peng, Baogui Xin

The traditional social recommendation algorithm ignores the following fact: the preferences of users with trust relationships are not necessarily similar, and the consideration of user preference similarity should be limited to specific areas.

Training GANs with Centripetal Acceleration

no code implementations24 Feb 2019 Wei Peng, Yu-Hong Dai, HUI ZHANG, Li-Zhi Cheng

Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates.

A Boost in Revealing Subtle Facial Expressions: A Consolidated Eulerian Framework

no code implementations23 Jan 2019 Wei Peng, Xiaopeng Hong, Yingyue Xu, Guoying Zhao

Facial Micro-expression Recognition (MER) distinguishes the underlying emotional states of spontaneous subtle facialexpressions.

Micro-Expression Recognition

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