Search Results for author: Chen Wu

Found 38 papers, 15 papers with code

PALM: Pre-training an Autoencoding\&Autoregressive Language Model for Context-conditioned Generation

no code implementations EMNLP 2020 Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.

Abstractive Text Summarization Conversational Response Generation +6

Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer

no code implementations18 Sep 2021 Hongruixuan Chen, Chen Wu, Yonghao Xu, Bo Du

To this end, a semantic-edge domain adaptation architecture is proposed, which uses an independent edge stream to process edge information, thereby generating high-quality semantic boundaries over the target domain.

Self-Supervised Learning Semantic Segmentation +1

Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images

1 code implementation18 Aug 2021 Hongruixuan Chen, Chen Wu, Bo Du

With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet.

Distilling Transformers for Neural Cross-Domain Search

no code implementations6 Aug 2021 Colin B. Clement, Chen Wu, Dawn Drain, Neel Sundaresan

Pre-trained transformers have recently clinched top spots in the gamut of natural language tasks and pioneered solutions to software engineering tasks.

Code Search Data Augmentation +1

Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix

no code implementations17 Jul 2021 Wenshuo Wang, Chen Wu, Liang Cheng, Yang Zhang

The advance in machine learning (ML)-driven natural language process (NLP) points a promising direction for automatic bug fixing for software programs, as fixing a buggy program can be transformed to a translation task.

Program Repair

Generating Bug-Fixes Using Pretrained Transformers

no code implementations16 Apr 2021 Dawn Drain, Chen Wu, Alexey Svyatkovskiy, Neel Sundaresan

In this work we introduce DeepDebug: a data-driven program repair approach which learns to detect and fix bugs in Java methods mined from real-world GitHub repositories.

Denoising Program Repair

Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers

no code implementations12 Apr 2021 Dawn Drain, Changran Hu, Chen Wu, Mikhail Breslav, Neel Sundaresan

To demonstrate the effectiveness of our model designs, we perform extensive experiments with CodeSearchNet which contains template functions and CoNaLa which contains Stack Overflow intent-snippet pairs.

Code Search

Transportation Density Reduction Caused by City Lockdowns Across the World during the COVID-19 Epidemic: From the View of High-resolution Remote Sensing Imagery

no code implementations2 Mar 2021 Chen Wu, Sihan Zhu, Jiaqi Yang, Meiqi Hu, Bo Du, Liangpei Zhang, Lefei Zhang, Chengxi Han, Meng Lan

Considering that public transportation was mostly reduced or even forbidden, our results indicate that city lockdown policies are effective at limiting human transmission within cities.

Learning to Truncate Ranked Lists for Information Retrieval

no code implementations25 Feb 2021 Chen Wu, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Xueqi Cheng

One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search.

Information Retrieval

Mitigating Backdoor Attacks in Federated Learning

no code implementations28 Oct 2020 Chen Wu, Xian Yang, Sencun Zhu, Prasenjit Mitra

To minimize the pruning influence on test accuracy, we can fine-tune after pruning, and the attack success rate drops to 6. 4%, with only a 1. 7% loss of test accuracy.

Federated Learning

Hyperspectral Anomaly Change Detection Based on Auto-encoder

no code implementations27 Oct 2020 Meiqi Hu, Chen Wu, Liangpei Zhang, Bo Du

In the ACDA model, two systematic auto-encoder (AE) networks are deployed to construct two predictors from two directions.

An Investigation of Traffic Density Changes inside Wuhan during the COVID-19 Epidemic with GF-2 Time-Series Images

no code implementations26 Jun 2020 Chen Wu, Yinong Guo, HaoNan Guo, Jingwen Yuan, Lixiang Ru, Hongruixuan Chen, Bo Du, Liangpei Zhang

The significant reduction and recovery of traffic density indicates that the lockdown policy in Wuhan show effectiveness in controlling human transmission inside the city, and the city returned to normal after lockdown lift.

Anomaly Detection Time Series

DSDANet: Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection

no code implementations16 Jun 2020 Hongruixuan Chen, Chen Wu, Bo Du, Liangpei Zhang

By optimizing the network parameters and kernel coefficients with the source labeled data and target unlabeled data, DSDANet can learn transferrable feature representation that can bridge the discrepancy between two domains.

Domain Adaptation

Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion

1 code implementation3 Jun 2020 Lixiang Ru, Bo Du, Chen Wu

In this work, we proposed a CorrFusion module that fuses the highly correlated components in bi-temporal feature embeddings.

General Classification Scene Change Detection +1

The GLEAM 4-Jy (G4Jy) Sample: II. Host-galaxy identification for individual sources

1 code implementation27 Apr 2020 Sarah V. White, Thomas M. O. Franzen, Chris J. Riseley, O. Ivy Wong, Anna D. Kapińska, Natasha Hurley-Walker, Joseph R. Callingham, Kshitij Thorat, Chen Wu, Paul Hancock, Richard W. Hunstead, Nick Seymour, Jesse Swan, Randall Wayth, John Morgan, Rajan Chhetri, Carole Jackson, Stuart Weston, Martin Bell, B. M. Gaensler, Melanie Johnston-Hollitt, André Offringa, Lister Staveley-Smith

This is the GaLactic and Extragalactic All-sky MWA (GLEAM) Survey, and we have previously used a combination of visual inspection, cross-checks against the literature, and internal matching to identify the 'brightest' radio-sources ($S_{\mathrm{151MHz}} >$ 4 Jy) in the extragalactic catalogue (Galactic latitude, $|b| >$ 10 deg).

Astrophysics of Galaxies

The GLEAM 4-Jy (G4Jy) Sample: I. Definition and the catalogue

1 code implementation27 Apr 2020 Sarah V. White, Thomas M. O. Franzen, Chris J. Riseley, O. Ivy Wong, Anna D. Kapińska, Natasha Hurley-Walker, Joseph R. Callingham, Kshitij Thorat, Chen Wu, Paul Hancock, Richard W. Hunstead, Nick Seymour, Jesse Swan, Randall Wayth, John Morgan, Rajan Chhetri, Carole Jackson, Stuart Weston, Martin Bell, Bi-Qing For, B. M. Gaensler, Melanie Johnston-Hollitt, André Offringa, Lister Staveley-Smith

Of these G4Jy sources, 78 are resolved by the MWA (Phase-I) synthesised beam ($\sim$2 arcmin at 200 MHz), and we label 67% of the sample as 'single', 26% as 'double', 4% as 'triple', and 3% as having 'complex' morphology at $\sim$1 GHz (45-arcsec resolution).

Astrophysics of Galaxies

On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond

1 code implementation ACL 2020 Chen Wu, Prince Zizhuang Wang, William Yang Wang

To this end, we propose Coupled-VAE, which couples a VAE model with a deterministic autoencoder with the same structure and improves the encoder and decoder parameterizations via encoder weight sharing and decoder signal matching.

Dialogue Generation Language Modelling +1

PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation

2 code implementations14 Apr 2020 Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.

Abstractive Text Summarization Conversational Response Generation +6

Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection in Multispectral Images

no code implementations13 Apr 2020 Hongruixuan Chen, Chen Wu, Bo Du, Liangepei Zhang

In this paper, we propose a novel deep siamese domain adaptation convolutional neural network (DSDANet) architecture for cross-domain change detection.

Domain Adaptation

Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network

2 code implementations18 Dec 2019 Chen Wu, Hongruixuan Chen, Bo Do, Liangpei Zhang

Based on the KPCA convolution, an unsupervised deep siamese KPCA convolutional mapping network (KPCA-MNet) is designed for binary and multi-class change detection.

Symmetric Regularization based BERT for Pair-wise Semantic Reasoning

1 code implementation8 Sep 2019 Weidi Xu, Xingyi Cheng, Kunlong Chen, Wei Wang, Bin Bi, Ming Yan, Chen Wu, Luo Si, Wei Chu, Taifeng Wang

To remedy this, we propose to augment the NSP task to a 3-class categorization task, which includes a category for previous sentence prediction (PSP).

Document-level Machine Reading Comprehension +2

Incorporating External Knowledge into Machine Reading for Generative Question Answering

no code implementations IJCNLP 2019 Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li

Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate answers in natural language for a given question with context.

Generative Question Answering Reading Comprehension

Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning

no code implementations13 Aug 2019 Jiangnan Xia, Chen Wu, Ming Yan

This paper focuses on how to take advantage of external relational knowledge to improve machine reading comprehension (MRC) with multi-task learning.

Language Modelling Machine Reading Comprehension +1

StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding

no code implementations ICLR 2020 Wei Wang, Bin Bi, Ming Yan, Chen Wu, Zuyi Bao, Jiangnan Xia, Liwei Peng, Luo Si

Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as sentiment classification, natural language inference, semantic textual similarity and question answering.

Language Modelling Linguistic Acceptability +5

Change Detection in Multi-temporal VHR Images Based on Deep Siamese Multi-scale Convolutional Networks

2 code implementations27 Jun 2019 Hongruixuan Chen, Chen Wu, Bo Du, Liangpei Zhang

Based on the unit two novel deep siamese convolutional neural networks, called as deep siamese multi-scale convolutional network (DSMS-CN) and deep siamese multi-scale fully convolutional network (DSMS-FCN), are designed for unsupervised and supervised change detection, respectively.

A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer

1 code implementation ACL 2019 Chen Wu, Xuancheng Ren, Fuli Luo, Xu sun

Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision.

Style Transfer Text Style Transfer +1

ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data

7 code implementations1 Apr 2019 Foivos I. Diakogiannis, François Waldner, Peter Caccetta, Chen Wu

Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications.

Scene Understanding Semantic Segmentation

Optimizing seed inputs in fuzzing with machine learning

no code implementations7 Feb 2019 Liang Cheng, Yang Zhang, Yi Zhang, Chen Wu, Zhangtan Li, Yu Fu, Haisheng Li

Our experiments on a set of widely used PDF viewers demonstrate that the improved seed inputs produced by our framework could significantly increase the code coverage of the target program and the likelihood of detecting program crashes.

Cryptography and Security

Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images

no code implementations3 Dec 2018 Bo Du, Lixiang Ru, Chen Wu, Liangpei Zhang

In recent years, deep network has shown its brilliant performance in many fields including feature extraction and projection.

A Deep Cascade Model for Multi-Document Reading Comprehension

no code implementations28 Nov 2018 Ming Yan, Jiangnan Xia, Chen Wu, Bin Bi, Zhongzhou Zhao, Ji Zhang, Luo Si, Rui Wang, Wei Wang, Haiqing Chen

To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the document-level and paragraph-level ranking of candidate texts to more precise answer extraction with machine reading comprehension.

Document-level Machine Reading Comprehension +1

The MWA GLEAM 4-Jy (G4Jy) Sample

1 code implementation2 Oct 2018 Sarah V. White, Thomas M. O. Franzen, O. Ivy Wong, Anna D. Kapinska, Chris Riseley, Paul Hancock, Joseph Callingham, Richard Hunstead, Natasha Hurley-Walker, Chen Wu, Nick Seymour, Jesse Swan, Randall Wayth, John S. Morgan, Rajan Chhetri, Carole Jackson, Stuart Weston, Tom Mauch

These were observed at low radio-frequencies as part of the GaLactic and Extragalactic All-sky MWA (GLEAM) Survey, which is a continuum survey conducted using the Murchison Widefield Array (MWA).

Astrophysics of Galaxies

Multi-class Active Learning: A Hybrid Informative and Representative Criterion Inspired Approach

no code implementations6 Mar 2018 Xi Fang, Zengmao Wang, Xinyao Tang, Chen Wu

Simultaneously, our proposed method makes full use of the label information, and the proposed active learning is designed based on multiple classes.

Active Learning

DALiuGE: A Graph Execution Framework for Harnessing the Astronomical Data Deluge

2 code implementations24 Feb 2017 Chen Wu, Rodrigo Tobar, Kevin Vinsen, Andreas Wicenec, Dave Pallot, Baoqiang Lao, Ruonan Wang, Tao An, Mark Boulton, Ian Cooper, Richard Dodson, Markus Dolensky, Ying Mei, Feng Wang

The Data Activated Liu Graph Engine - DALiuGE - is an execution framework for processing large astronomical datasets at a scale required by the Square Kilometre Array Phase 1 (SKA1).

Distributed, Parallel, and Cluster Computing Instrumentation and Detectors

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