Principal Engineer, Noah’s Ark Lab, Singapore Research Center, Huawei International

Biography

ZHANG Hao is a principal engineer at Noah’s Ark Lab, Singapore Research Center, Huawei International. He obtained his Ph.D in computer science at Nanyang Technological University (NTU), advised by Prof. Aixin SUN (NTU) and Dr. Joey Tianyi ZHOU (A*STAR). His research interests include vision-language, natural language processing, conversational system, recommendation, and machine learning.

Email: hzhang26 AT outlook DOT com

Interests

  • Vision-and-Language
  • Natural Language Processing
  • Computational Linguistics
  • Artificial Intelligence
  • Machine & Deep Learning

Education

  • Ph.D in Computer Science, 2019-2022

    Nanyang Technological University

  • M.Sc in Communications Engineering, 2015-2016

    Nanyang Technological University

  • B.Eng in Communications Engineering, 2011-2015

    Dalian University of Technology

Work Experience

 
 
 
 
 

Principal Engineer

Noah’s Ark Lab, Singapore Research Center (2012 Laboratories), Huawei International

Jul 2022 – Present Singapore
 
 
 
 
 

Senior Research Engineer & Principal Investigator

Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research

Jan 2022 – May 2022 Singapore
 
 
 
 
 

Research Engineer

Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research

Jun 2018 – Dec 2021 Singapore
  • Computational AI Group at Computing & Intelligence Department (Aug 2020 - Dec 2021)
  • Human-Centric AI Group at Artificial Intelligence Initiative (Jun 2018 - Jul 2020)
 
 
 
 
 

Research Associate

Temasek Laboratories, Nanyang Technological University

Jul 2016 – May 2018 Singapore
  • Collaborated with Social & Cognitive Computing Department, IHPC, A*STAR

Selected Publications

Quickly discover relevant content by filtering publications.

Interventional Training for Out-Of-Distribution Natural Language Understanding

Out-of-distribution (OOD) settings are used to measure a model’s performance when the distribution of the test data is different …
Sicheng Yu, Jing Jiang, Hao Zhang, Yulei Niu, Qianru Sun, Lidong Bing
Preprint PDF Code Poster
Interventional Training for Out-Of-Distribution Natural Language Understanding

Translate-Train Embracing Translationese Artifacts

Translate-train is a general training approach to multilingual tasks. The key idea is to use the translator of the target language to …
Sicheng Yu, Qianru Sun, Hao Zhang, Jing Jiang
PDF Poster Slides
Translate-Train Embracing Translationese Artifacts

An Embarrassingly Simple Model for Dialogue Relation Extraction

Dialogue relation extraction (RE) is to predict the relation type of two entities mentioned in a dialogue. In this paper, we propose a …
Fuzhao Xue, Aixin Sun, Hao Zhang, Jinjie Ni, Eng-Siong Chng
Preprint PDF Code Poster Slides DOI
An Embarrassingly Simple Model for Dialogue Relation Extraction

Context Modeling with Evidence Filter for Multiple-Choice Question Answering

Multiple-Choice Question Answering (MCQA) is a challenging task in machine reading comprehension. The main challenge in MCQA is to …
Sicheng Yu, Hao Zhang, Wei Jing, Jing Jiang
Preprint PDF Poster Slides DOI
Context Modeling with Evidence Filter for Multiple-Choice Question Answering

Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model

In this paper we present SA-CNN, a hierarchical and lightweight self-attention based encoding and decoding architecture for …
En Yen Puang, Hao Zhang, Hongyuan Zhu, Wei Jing
Preprint PDF DOI
Hierarchical Point Cloud Encoding and Decoding with Lightweight Self-Attention based Model

The Elements of Temporal Sentence Grounding in Videos: A Survey and Future Directions

Temporal sentence grounding in videos (TSGV), a.k.a., natural language video localization (NLVL) or video moment retrieval (VMR), aims …
Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou
Preprint
The Elements of Temporal Sentence Grounding in Videos: A Survey and Future Directions

COSY: COunterfactual SYntax for Cross-Lingual Understanding

Pre-trained multilingual language models, e.g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the …
Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang
PDF Code Slides DOI
COSY: COunterfactual SYntax for Cross-Lingual Understanding

Parallel Attention Network with Sequence Matching for Video Grounding

Given a video, video grounding aims to retrieve a temporal moment that semantically corresponds to a language query. In this work, we …
Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Preprint PDF Code Slides DOI
Parallel Attention Network with Sequence Matching for Video Grounding

Video Corpus Moment Retrieval with Contrastive Learning

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a …
Hao Zhang, Aixin Sun, Wei Jing, Guoshun Nan, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Preprint PDF Code Slides Video DOI
Video Corpus Moment Retrieval with Contrastive Learning

Interventional Video Grounding with Dual Contrastive Learning

Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the …
Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu
Preprint PDF Code DOI
Interventional Video Grounding with Dual Contrastive Learning

Natural Language Video Localization: A Revisit in Span-based Question Answering Framework

Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a …
Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Preprint PDF DOI
Natural Language Video Localization: A Revisit in Span-based Question Answering Framework

GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a …
Fuzhao Xue, Aixin Sun, Hao Zhang, Eng Siong Chng
Preprint PDF Code Poster Slides
GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Deep N-ary Error Correcting Output Codes

Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. …
Hao Zhang, Joey Tianyi Zhou, Tianying Wang, Ivor W. Tsang, Rick Siow Mong Goh
Preprint PDF Code Poster Slides
Deep N-ary Error Correcting Output Codes

Span-based Localizing Network for Natural Language Video Localization

Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that …
Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou
Preprint PDF Code Slides DOI
Span-based Localizing Network for Natural Language Video Localization

Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering

Multiple-choice question answering (MCQA) is one of the most challenging tasks in machine reading comprehension since it requires more …
Ming Yan, Hao Zhang, Di Jin, Joey Tianyi Zhou
Preprint PDF Slides DOI
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering

RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer and Time-efficient Path Optimization

Robotic drawing has become increasingly popular as an entertainment and interactive tool. In this paper we present RoboCoDraw, a …
Tianying Wang*, Wei Qi Toh*, Hao Zhang*, Xiuchao Sui, Shaohua Li, Yong Liu, Wei Jing
Preprint PDF Code Poster Slides DOI
RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer and Time-efficient Path Optimization

Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning

Learning-based methods have been used to program robotic tasks in recent years. However, extensive training is usually required not …
Tianying Wang, Hao Zhang, Wei Qi Toh, Hongyuan Zhu, Cheston Tan, Yan Wu, Yong Liu, Wei Jing
Preprint PDF Slides DOI
Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning

Dual Adversarial Transfer for Sequence Labeling

We propose a new architecture for addressing sequence labeling, termed Dual Adversarial Transfer Network (DATNet). Specifically, the …
Joey Tianyi Zhou*, Hao Zhang*, Di Jing, Xi Peng
Preprint PDF Code DOI
Dual Adversarial Transfer for Sequence Labeling

Dual Adversarial Neural Transfer for Low-resource Named Entity Recognition

We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity …
Joey Tianyi Zhou*, Hao Zhang*, Di Jing, Hongyuan Zhu, Rick Siow Mong Goh, Kenneth Kwok
PDF Code Poster Slides DOI
Dual Adversarial Neural Transfer for Low-resource Named Entity Recognition

RoSeq: Robust Sequence Labeling

In this paper, we mainly investigate two issues for sequence labeling, namely label imbalance and noisy data which are commonly seen in …
Joey Tianyi Zhou*, Hao Zhang*, Di Jing, Xi Peng, Yang Xiao, Zhiguo Cao
Preprint PDF Code DOI
RoSeq: Robust Sequence Labeling

Learning With Annotation of Various Degrees

In this paper, we study a new problem in the scenario of sequences labeling. To be exact, we consider that the training data are with …
Joey Tianyi Zhou, Meng Fang, Hao Zhang, Chen Gong, Xi Peng, Zhiguo Cao, Rick Siow Mong Goh
Preprint PDF Code DOI
Learning With Annotation of Various Degrees