Search Results for author: Hao Zhou

Found 166 papers, 67 papers with code

Augmenting Topic Aware Knowledge-Grounded Conversations with Dynamic Built Knowledge Graphs

no code implementations NAACL (DeeLIO) 2021 Junjie Wu, Hao Zhou

Dialog topic management and background knowledge selection are essential factors for the success of knowledge-grounded open-domain conversations.

Knowledge Graphs Management +1

GLAT: Glancing at Latent Variables for Parallel Text Generation

1 code implementation ACL 2022 Yu Bao, Hao Zhou, ShuJian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei LI

Recently, parallel text generation has received widespread attention due to its success in generation efficiency.

Text Generation

Dispersed EM-VAEs for Interpretable Text Generation

no code implementations ICML 2020 Wenxian Shi, Hao Zhou, Ning Miao, Lei LI

Interpretability is important in text generation for guiding the generation with interpretable attributes.

Text Generation

Improving Constituent Representation with Hypertree Neural Networks

no code implementations NAACL 2022 Hao Zhou, Gongshen Liu, Kewei Tu

Many natural language processing tasks involve text spans and thus high-quality span representations are needed to enhance neural approaches to these tasks.

On Large Language Models' Selection Bias in Multi-Choice Questions

no code implementations7 Sep 2023 Chujie Zheng, Hao Zhou, Fandong Meng, Jie zhou, Minlie Huang

Multi-choice questions (MCQs) serve as a common yet important task format in the research of large language models (LLMs).

Selection bias

TKwinFormer: Top k Window Attention in Vision Transformers for Feature Matching

no code implementations29 Aug 2023 Yun Liao, Yide Di, Hao Zhou, Kaijun Zhu, Mingyu Lu, Yijia Zhang, Qing Duan, Junhui Liu

Local feature matching remains a challenging task, primarily due to difficulties in matching sparse keypoints and low-texture regions.

Towards Codable Text Watermarking for Large Language Models

1 code implementation29 Jul 2023 Lean Wang, Wenkai Yang, Deli Chen, Hao Zhou, Yankai Lin, Fandong Meng, Jie zhou, Xu sun

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs.

Unified Molecular Modeling via Modality Blending

no code implementations12 Jul 2023 Qiying Yu, Yudi Zhang, Yuyan Ni, Shikun Feng, Yanyan Lan, Hao Zhou, Jingjing Liu

Self-supervised molecular representation learning is critical for molecule-based tasks such as AI-assisted drug discovery.

Drug Discovery molecular representation +2

VideoGLUE: Video General Understanding Evaluation of Foundation Models

no code implementations6 Jul 2023 Liangzhe Yuan, Nitesh Bharadwaj Gundavarapu, Long Zhao, Hao Zhou, Yin Cui, Lu Jiang, Xuan Yang, Menglin Jia, Tobias Weyand, Luke Friedman, Mikhail Sirotenko, Huisheng Wang, Florian Schroff, Hartwig Adam, Ming-Hsuan Yang, Ting Liu, Boqing Gong

We evaluate existing foundation models video understanding capabilities using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition, temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring a foundation model (FM) for a downstream task.

Action Recognition Temporal Localization +1

INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classification

1 code implementation3 Jul 2023 Min Li, Hao Zhou, Qun Liu, Yabin Shao, GuoYing Wang

It uses granular balls to simulate the spatial distribution characteristics of datasets, and informed entropy is utilized to further optimize the granular-ball space.

Anchor link prediction imbalanced classification

Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions

no code implementations24 May 2023 Jiahuan Li, Hao Zhou, ShuJian Huang, Shanbo Cheng, Jiajun Chen

Secondly, we find that LLMs' ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages.

Language Modelling Translation

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

no code implementations23 May 2023 Lean Wang, Lei LI, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie zhou, Xu sun

In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks.

Smart Home Energy Management: VAE-GAN synthetic dataset generator and Q-learning

no code implementations14 May 2023 Mina Razghandi, Hao Zhou, Melike Erol-Kantarci, Damla Turgut

In this paper, we propose a novel variational auto-encoder-generative adversarial network (VAE-GAN) technique for generating time-series data on energy consumption in smart homes.

energy management Management +2

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

no code implementations8 May 2023 Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng, Jie zhou, Xu sun

To settle this issue, we propose the Fine-purifying approach, which utilizes the diffusion theory to study the dynamic process of fine-tuning for finding potentially poisonous dimensions.

Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training

no code implementations4 May 2023 Jiaxin Wen, Hao Zhou, Minlie Huang

Large-scale open-domain dialogue data crawled from public social media has greatly improved the performance of dialogue models.

Cooperative Hierarchical Deep Reinforcement Learning based Joint Sleep, Power, and RIS Control for Energy-Efficient HetNet

no code implementations26 Apr 2023 Hao Zhou, Medhat Elsayed, Majid Bavand, Raimundas Gaigalas, Steve Furr, Melike Erol-Kantarci

In this work, we jointly consider sleep and transmission power control for reconfigurable intelligent surface (RIS)-aided energy-efficient heterogeneous networks (Hetnets).

Learning Harmonic Molecular Representations on Riemannian Manifold

1 code implementation27 Mar 2023 Yiqun Wang, Yuning Shen, Shi Chen, Lihao Wang, Fei Ye, Hao Zhou

In this work, we propose a Harmonic Molecular Representation learning (HMR) framework, which represents a molecule using the Laplace-Beltrami eigenfunctions of its molecular surface.

Drug Discovery molecular representation +2

A Survey on Model-based, Heuristic, and Machine Learning Optimization Approaches in RIS-aided Wireless Networks

no code implementations25 Mar 2023 Hao Zhou, Melike Erol-Kantarci, Yuanwei Liu, H. Vincent Poor

Model-based, heuristic, and ML approaches are compared in terms of stability, robustness, optimality and so on, providing a systematic understanding of these techniques.

Federated Learning Graph Learning +2

Towards Diverse Temporal Grounding under Single Positive Labels

1 code implementation12 Mar 2023 Hao Zhou, Chongyang Zhang, Yanjun Chen, Chuanping Hu

In this study, we reformulate this task as a one-vs-many optimization problem under the condition of single positive labels.

Moment Retrieval Retrieval

Cross-modal information fusion for voice spoofing detection

1 code implementation journal 2023 Junxiao Xue, Hao Zhou, Huawei Song, Bin Wu, Lei Shi

Researchers have proposed many methods to defend against these attacks, but in the existing methods, researchers just focus on speech features.

Automatic Speech Recognition fake voice detection +3

Beam Selection for Energy-Efficient mmWave Network Using Advantage Actor Critic Learning

no code implementations1 Feb 2023 Ycaro Dantas, Pedro Enrique Iturria-Rivera, Hao Zhou, Majid Bavand, Medhat Elsayed, Raimundas Gaigalas, Melike Erol-Kantarci

Compared to the ESB and fixed transmission power strategy, the proposed approach achieves more than twice the average EE in the scenarios under test and is closer to the maximum theoretical EE.


On Pre-trained Language Models for Antibody

1 code implementation28 Jan 2023 Danqing Wang, Fei Ye, Hao Zhou

The development of general protein and antibody-specific pre-trained language models both facilitate antibody prediction tasks.

Drug Discovery Language Modelling +1

Graph Contrastive Learning for Skeleton-based Action Recognition

1 code implementation26 Jan 2023 Xiaohu Huang, Hao Zhou, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang, Xinggang Wang, Wenyu Liu, Bin Feng

In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences.

Action Recognition Contrastive Learning +2

Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning

no code implementations25 Jan 2023 Wenkai Yang, Deli Chen, Hao Zhou, Fandong Meng, Jie zhou, Xu sun

Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner.

Federated Learning Privacy Preserving

Hierarchical Reinforcement Learning for RIS-Assisted Energy-Efficient RAN

no code implementations7 Jan 2023 Hao Zhou, Long Kong, Medhat Elsayed, Majid Bavand, Raimundas Gaigalas, Steve Furr, Melike Erol-Kantarci

Reconfigurable intelligent surface (RIS) is emerging as a promising technology to boost the energy efficiency (EE) of 5G beyond and 6G networks.

Hierarchical Reinforcement Learning Management +2

Diff-Glat: Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning

no code implementations20 Dec 2022 Lihua Qian, Mingxuan Wang, Yang Liu, Hao Zhou

Autoregressive models can achieve high generation quality, but the sequential decoding scheme causes slow decoding speed.

Knowledge Distillation

Accelerating Antimicrobial Peptide Discovery with Latent Structure

1 code implementation28 Nov 2022 Danqing Wang, Zeyu Wen, Fei Ye, Lei LI, Hao Zhou

By sampling in the latent space, LSSAMP can simultaneously generate peptides with ideal sequence attributes and secondary structures.


Direct Heterogeneous Causal Learning for Resource Allocation Problems in Marketing

no code implementations28 Nov 2022 Hao Zhou, Shaoming Li, Guibin Jiang, Jiaqi Zheng, Dong Wang

Our key intuition is that we introduce the decision factor to establish a bridge between ML and OR such that the solution can be directly obtained in OR by only performing the sorting or comparison operations on the decision factor.

Decision Making Marketing

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models

1 code implementation18 Oct 2022 Lan Jiang, Hao Zhou, Yankai Lin, Peng Li, Jie zhou, Rui Jiang

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks.

Adversarial Robustness

Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition

1 code implementation13 Oct 2022 Hao Zhou, Man Lan, Yuanbin Wu, Yuefeng Chen, Meirong Ma

Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis.

Multi-Task Learning

PARAGEN : A Parallel Generation Toolkit

1 code implementation7 Oct 2022 Jiangtao Feng, Yi Zhou, Jun Zhang, Xian Qian, Liwei Wu, Zhexi Zhang, Yanming Liu, Mingxuan Wang, Lei LI, Hao Zhou

PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.

Model Selection

IMB-NAS: Neural Architecture Search for Imbalanced Datasets

no code implementations30 Sep 2022 Rahul Duggal, Shengyun Peng, Hao Zhou, Duen Horng Chau

In this paper, we propose a new and complementary direction for improving performance on long tailed datasets - optimizing the backbone architecture through neural architecture search (NAS).

Neural Architecture Search Representation Learning

Towards Regression-Free Neural Networks for Diverse Compute Platforms

no code implementations27 Sep 2022 Rahul Duggal, Hao Zhou, Shuo Yang, Jun Fang, Yuanjun Xiong, Wei Xia

With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important.

Neural Architecture Search regression

Fraud Dataset Benchmark and Applications

2 code implementations30 Aug 2022 Prince Grover, Julia Xu, Justin Tittelfitz, Anqi Cheng, Zheng Li, Jakub Zablocki, Jianbo Liu, Hao Zhou

Standardized datasets and benchmarks have spurred innovations in computer vision, natural language processing, multi-modal and tabular settings.

AutoML Feature Engineering +1

Joint Sensing and Communications for Deep Reinforcement Learning-based Beam Management in 6G

no code implementations3 Aug 2022 Yujie Yao, Hao Zhou, Melike Erol-Kantarci

Then we propose a UK-medoids based method for user clustering with location uncertainty, and the clustering results are consequently used for the beam management.

Clustering Management +2

On the Learning of Non-Autoregressive Transformers

no code implementations13 Jun 2022 Fei Huang, Tianhua Tao, Hao Zhou, Lei LI, Minlie Huang

Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to reduce the decoding latency by predicting the whole sentences in parallel.

Text Generation

Directed Acyclic Transformer for Non-Autoregressive Machine Translation

1 code implementation16 May 2022 Fei Huang, Hao Zhou, Yang Liu, Hang Li, Minlie Huang

Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel.

Knowledge Distillation Machine Translation +1

Enhancing Cross-lingual Transfer by Manifold Mixup

1 code implementation ICLR 2022 Huiyun Yang, Huadong Chen, Hao Zhou, Lei LI

Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances.

Cross-Lingual Transfer

Deep Reinforcement Learning-based Radio Resource Allocation and Beam Management under Location Uncertainty in 5G mmWave Networks

no code implementations23 Apr 2022 Yujie Yao, Hao Zhou, Melike Erol-Kantarci

In this paper, we propose a UK-means-based clustering and deep reinforcement learning-based resource allocation algorithm (UK-DRL) for radio resource allocation and beam management in 5G mmWave networks.

Clustering Management +2

One-Class Model for Fabric Defect Detection

1 code implementation20 Apr 2022 Hao Zhou, Yixin Chen, David Troendle, Byunghyun Jang

Our model takes advantage of a well-designed Gabor filter bank to analyze fabric texture.

Defect Detection

$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation

1 code implementation5 Apr 2022 Yu Bao, Hao Zhou, ShuJian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei LI

Recently, parallel text generation has received widespread attention due to its success in generation efficiency.

Text Generation

E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning

no code implementations Findings (ACL) 2022 Jiangjie Chen, Rui Xu, Ziquan Fu, Wei Shi, Zhongqiao Li, Xinbo Zhang, Changzhi Sun, Lei LI, Yanghua Xiao, Hao Zhou

Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR).

Explanation Generation Question Answering

Variational Autoencoder Generative Adversarial Network for Synthetic Data Generation in Smart Home

no code implementations19 Jan 2022 Mina Razghandi, Hao Zhou, Melike Erol-Kantarci, Damla Turgut

To this end, in this paper, we propose a Variational AutoEncoder Generative Adversarial Network (VAE-GAN) as a smart grid data generative model which is capable of learning various types of data distributions and generating plausible samples from the same distribution without performing any prior analysis on the data before the training phase. We compared the Kullback-Leibler (KL) divergence, maximum mean discrepancy (MMD), and Wasserstein distance between the synthetic data (electrical load and PV production) distribution generated by the proposed model, vanilla GAN network, and the real data distribution, to evaluate the performance of our model.

Synthetic Data Generation

Unsupervised Editing for Counterfactual Stories

1 code implementation10 Dec 2021 Jiangjie Chen, Chun Gan, Sijie Cheng, Hao Zhou, Yanghua Xiao, Lei LI

We also propose a new metric to alleviate the shortcomings of current automatic metrics and better evaluate the trade-off.

Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failures

no code implementations22 Nov 2021 Hao Zhou, Atakan Aral, Ivona Brandic, Melike Erol-Kantarci

Microgrids (MGs) are important players for the future transactive energy systems where a number of intelligent Internet of Things (IoT) devices interact for energy management in the smart grid.

energy management Management +3

A Survey on Green Deep Learning

no code implementations8 Nov 2021 Jingjing Xu, Wangchunshu Zhou, Zhiyi Fu, Hao Zhou, Lei LI

In recent years, larger and deeper models are springing up and continuously pushing state-of-the-art (SOTA) results across various fields like natural language processing (NLP) and computer vision (CV).

Knowledge Distillation Model Compression

Sliding Sequential CVAE with Time Variant Socially-aware Rethinking for Trajectory Prediction

no code implementations28 Oct 2021 Hao Zhou, Dongchun Ren, Xu Yang, Mingyu Fan, Hai Huang

First, with the continuation of time, the prediction error at each time step increases significantly, causing the final displacement error to be impossible to ignore.

Autonomous Driving Pedestrian Trajectory Prediction +3

CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level

no code implementations21 Oct 2021 Danqing Wang, Jiaze Chen, Xianze Wu, Hao Zhou, Lei LI

In this paper, we present a large-scale Chinese news summarization dataset CNewSum, which consists of 304, 307 documents and human-written summaries for the news feed.

News Summarization Text Summarization

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

1 code implementation Findings (ACL) 2022 Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, Minlie Huang

We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.

Simulated annealing for optimization of graphs and sequences

no code implementations1 Oct 2021 Xianggen Liu, Pengyong Li, Fandong Meng, Hao Zhou, Huasong Zhong, Jie zhou, Lili Mou, Sen Song

The key idea is to integrate powerful neural networks into metaheuristics (e. g., simulated annealing, SA) to restrict the search space in discrete optimization.

Paraphrase Generation

Generating Antimicrobial Peptides from Latent Secondary Structure Space

no code implementations29 Sep 2021 Danqing Wang, Zeyu Wen, Lei LI, Hao Zhou

By sampling in the latent secondary structure space, we can generate peptides with ideal amino acids and secondary structures at the same time.

Drug Discovery

NAIL: A Challenging Benchmark for Na\"ive Logical Reasoning

no code implementations29 Sep 2021 Xinbo Zhang, Changzhi Sun, Yue Zhang, Lei LI, Hao Zhou

Logical reasoning over natural text is an important capability towards human level intelligence.

Logical Reasoning

Smart Home Energy Management: Sequence-to-Sequence Load Forecasting and Q-Learning

no code implementations25 Sep 2021 Mina Razghandi, Hao Zhou, Melike Erol-Kantarci, Damla Turgut

A smart home energy management system (HEMS) can contribute towards reducing the energy costs of customers; however, HEMS suffers from uncertainty in both energy generation and consumption patterns.

energy management Load Forecasting +2

Learning from Peers: Deep Transfer Reinforcement Learning for Joint Radio and Cache Resource Allocation in 5G RAN Slicing

no code implementations16 Sep 2021 Hao Zhou, Melike Erol-Kantarci, Vincent Poor

In this paper, we propose a deep transfer reinforcement learning (DTRL) scheme for joint radio and cache resource allocation to serve 5G RAN slicing.

Fairness Management +4

Physiological-Physical Feature Fusion for Automatic Voice Spoofing Detection

no code implementations1 Sep 2021 Junxiao Xue, Hao Zhou, Yabo Wang

This method involves feature extraction, a densely connected convolutional neural network with squeeze and excitation block (SE-DenseNet), multi-scale residual neural network with squeeze and excitation block (SE-Res2Net) and feature fusion strategies.

Speaker Verification Speech Synthesis +1

Impact of Acceleration/deceleration Limits on the String Stability of Adaptive Cruise Control

no code implementations9 Aug 2021 Hao Zhou, Anye Zhou, Tienan Li, Danjue Chen, Srinivas Peeta, Jorge Laval

This paper demonstrates that the acceleration/deceleration limits in ACC systems can make a string stable ACC amplify the speed perturbation in natural driving.

EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training

2 code implementations3 Aug 2021 Hao Zhou, Pei Ke, Zheng Zhang, Yuxian Gu, Yinhe Zheng, Chujie Zheng, Yida Wang, Chen Henry Wu, Hao Sun, Xiaocong Yang, Bosi Wen, Xiaoyan Zhu, Minlie Huang, Jie Tang

Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.

Follow Your Path: a Progressive Method for Knowledge Distillation

no code implementations20 Jul 2021 Wenxian Shi, Yuxuan Song, Hao Zhou, Bohan Li, Lei LI

However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima.

Knowledge Distillation

Short-Term Load Forecasting for Smart HomeAppliances with Sequence to Sequence Learning

no code implementations26 Jun 2021 Mina Razghandi, Hao Zhou, Melike Erol-Kantarci, Damla Turgut

Appliance-level load forecasting plays a critical role in residential energy management, besides having significant importance for ancillary services performed by the utilities.

energy management Load Forecasting +1

Compatibility-aware Heterogeneous Visual Search

no code implementations CVPR 2021 Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto

Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images.

Neural Architecture Search Retrieval

Fundamental Diagrams of Commercial Adaptive Cruise Control: Worldwide Experimental Evidence

no code implementations12 May 2021 Tienan Li, Danjue Chen, Hao Zhou, Yuanchang Xie, Jorge Laval

Experimental measurements on commercial adaptive cruise control (ACC) vehicles \RoundTwo{are} becoming increasingly available from around the world, providing an unprecedented opportunity to study the traffic flow characteristics that arise from this technology.

Significance of Low-level Controller for String Stability under Adaptive Cruise Control

no code implementations15 Apr 2021 Hao Zhou, Anye Zhou, Tienan Li, Danjue Chen, Srinivas Peeta, Jorge Laval

Current commercial adaptive cruise control (ACC) systems consist of an upper-level planner controller that decides the optimal trajectory that should be followed, and a low-level controller in charge of sending the gas/brake signals to the mechanical system to actually move the vehicle.

ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction

1 code implementation EACL 2021 Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei LI, Junchi Yan

Current state-of-the-art systems for joint entity relation extraction (Luan et al., 2019; Wad-den et al., 2019) usually adopt the multi-task learning framework.

coreference-resolution Entity Typing +3

Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding

no code implementations CVPR 2021 Hao Zhou, Chongyang Zhang, Yan Luo, Yanjun Chen, Chuanping Hu

Meanwhile, modified feature assigned with style-like words (including adjectives, adverbs, etc) represents the subjective information, and thus brings personalized predictions; De-bias - We propose a de-bias mechanism to generate diverse predictions, aim to alleviate the bias caused by single-style annotations in the presence of label uncertainty.

Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection

no code implementations18 Mar 2021 Yan Luo, Chongyang Zhang, Muming Zhao, Hao Zhou, Jun Sun

Consequently, we address the weakness of IoU by introducing one geometric sensitive search algorithm as a new assignment and regression metric.

Autonomous Driving Pedestrian Detection +1

Decentralized Microgrid Energy Management: A Multi-agent Correlated Q-learning Approach

no code implementations6 Mar 2021 Hao Zhou, Melike Erol-Kantarci

The EMS of an MG could be rather complicated when renewable energy resources (RER), energy storage system (ESS) and demand side management (DSM) need to be orchestrated.

energy trading Management +1

Triangular Bidword Generation for Sponsored Search Auction

no code implementations27 Jan 2021 Zhenqiao Song, Jiaze Chen, Hao Zhou, Lei LI

Our proposed model is simple yet effective: by using bidword as the bridge between search query and advertisement, the generation of search query, advertisement and bidword can be jointly learned in the triangular training framework.

Information-theoretic Vocabularization via Optimal Transport

no code implementations1 Jan 2021 Jingjing Xu, Hao Zhou, Chun Gan, Zaixiang Zheng, Lei LI

In this paper, we find an exciting relation between an information-theoretic feature and the performance of NLP tasks such as machine translation with a given vocabulary.

Machine Translation Translation

Non-iterative Parallel Text Generation via Glancing Transformer

no code implementations1 Jan 2021 Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei LI

Although non-autoregressive models with one-iteration generation achieves remarkable inference speed-up, they still falls behind their autoregressive counterparts inprediction accuracy.

Language Modelling Text Generation

Learning from deep model via exploring local targets

no code implementations1 Jan 2021 Wenxian Shi, Yuxuan Song, Hao Zhou, Bohan Li, Lei LI

However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima.

Knowledge Distillation

Adaptive Gradient Methods Can Be Provably Faster than SGD with Random Shuffling

no code implementations1 Jan 2021 Xunpeng Huang, Vicky Jiaqi Zhang, Hao Zhou, Lei LI

Adaptive gradient methods have been shown to outperform SGD in many tasks of training neural networks.

Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal Hashing

1 code implementation25 Dec 2020 Jun Yu, Hao Zhou, Yibing Zhan, DaCheng Tao

Essentially, DGCPN addresses the inaccurate similarity problem by exploring and exploiting the data's intrinsic relationships in a graph.

Quantization Retrieval

Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection

no code implementations CVPR 2020 Yan Luo, Chongyang Zhang, Muming Zhao, Hao Zhou, Jun Sun

i) We generate a bird view map, which is naturally free from occlusion issues, and scan all points on it to look for suitable locations for each pedestrian instance.

Pedestrian Detection

Reciprocal Supervised Learning Improves Neural Machine Translation

1 code implementation5 Dec 2020 Minkai Xu, Mingxuan Wang, Zhouhan Lin, Hao Zhou, Weinan Zhang, Lei LI

Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT).

Image Classification Knowledge Distillation +4

NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions

1 code implementation Findings (EMNLP) 2021 Zhiyu Chen, Honglei Liu, Hu Xu, Seungwhan Moon, Hao Zhou, Bing Liu

As there is no clean mapping for a user's free form utterance to an ontology, we first model the user preferences as estimated distributions over the system ontology and map the users' utterances to such distributions.

Dialogue State Tracking

Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information

1 code implementation EMNLP 2020 Zehui Lin, Xiao Pan, Mingxuan Wang, Xipeng Qiu, Jiangtao Feng, Hao Zhou, Lei LI

We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs?

Ranked #3 on Machine Translation on WMT2014 English-French (using extra training data)

Machine Translation Translation

Consecutive Decoding for Speech-to-text Translation

1 code implementation21 Sep 2020 Qianqian Dong, Mingxuan Wang, Hao Zhou, Shuang Xu, Bo Xu, Lei LI

The key idea is to generate source transcript and target translation text with a single decoder.

Machine Translation speech-recognition +3

Congested Urban Networks Tend to Be Insensitive to Signal Settings: Implications for Learning-Based Control

2 code implementations21 Aug 2020 Jorge Laval, Hao Zhou

Notably, we found that no control (i. e. random policy) can be an effective control strategy for a surprisingly large family of networks.

Generating Fluent Adversarial Examples for Natural Languages

no code implementations ACL 2019 Huangzhao Zhang, Hao Zhou, Ning Miao, Lei LI

Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge.

Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation

no code implementations12 Jul 2020 Yuxuan Song, Ning Miao, Hao Zhou, Lantao Yu, Mingxuan Wang, Lei LI

Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios.

Density Ratio Estimation Text Generation

Xiaomingbot: A Multilingual Robot News Reporter

no code implementations ACL 2020 Runxin Xu, Jun Cao, Mingxuan Wang, Jiaze Chen, Hao Zhou, Ying Zeng, Yu-Ping Wang, Li Chen, Xiang Yin, Xijin Zhang, Songcheng Jiang, Yuxuan Wang, Lei LI

This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.

News Generation Translation +1

ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization

1 code implementation12 Jun 2020 Xunpeng Huang, Runxin Xu, Hao Zhou, Zhe Wang, Zhengyang Liu, Lei LI

Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence.

BIG-bench Machine Learning Stochastic Optimization

Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

no code implementations12 Jun 2020 Xunpeng Huang, Hao Zhou, Runxin Xu, Zhe Wang, Lei LI

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency.

Network On Network for Tabular Data Classification in Real-world Applications

no code implementations20 May 2020 Yuanfei Luo, Hao Zhou, Wei-Wei Tu, Yuqiang Chen, Wenyuan Dai, Qiang Yang

As a result, the intra-field information and the non-linear interactions between those operations (e. g. neural network and factorization machines) are ignored.

General Classification

Mirror-Generative Neural Machine Translation

no code implementations ICLR 2020 Zaixiang Zheng, Hao Zhou, Shu-Jian Huang, Lei LI, Xin-yu Dai, Jia-Jun Chen

Training neural machine translation models (NMT) requires a large amount of parallel corpus, which is scarce for many language pairs.

Machine Translation NMT +1

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation

1 code implementation ACL 2020 Hao Zhou, Chujie Zheng, Kaili Huang, Minlie Huang, Xiaoyan Zhu

The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations.

Domain Adaptation Knowledge Graphs +1

Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip

1 code implementation3 Apr 2020 Yuxuan Song, Minkai Xu, Lantao Yu, Hao Zhou, Shuo Shao, Yong Yu

In this paper, motivated by the inherent connections between neural joint source-channel coding and discrete representation learning, we propose a novel regularization method called Infomax Adversarial-Bit-Flip (IABF) to improve the stability and robustness of the neural joint source-channel coding scheme.

Representation Learning

MajorityNets: BNNs Utilising Approximate Popcount for Improved Efficiency

no code implementations27 Feb 2020 Seyedramin Rasoulinezhad, Sean Fox, Hao Zhou, Lingli Wang, David Boland, Philip H. W. Leong

Binarized neural networks (BNNs) have shown exciting potential for utilising neural networks in embedded implementations where area, energy and latency constraints are paramount.

Importance-Aware Learning for Neural Headline Editing

no code implementations25 Nov 2019 Qingyang Wu, Lei LI, Hao Zhou, Ying Zeng, Zhou Yu

We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers.

Headline Generation

Visual Relationship Detection with Relative Location Mining

1 code implementation2 Nov 2019 Hao Zhou, Chongyang Zhang, Chuanping Hu

Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently.

Relationship Detection Visual Relationship Detection

Kernelized Bayesian Softmax for Text Generation

1 code implementation NeurIPS 2019 Ning Miao, Hao Zhou, Chengqi Zhao, Wenxian Shi, Lei LI

Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase.

Text Generation

Review of Learning-based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps between Self-driving and Traffic Congestion

no code implementations2 Oct 2019 Hao Zhou, Jorge Laval, Anye Zhou, Yu Wang, Wenchao Wu, Zhu Qing, Srinivas Peeta

Some suggestions towards congestion mitigation for future mMP studies are proposed: i) enrich data collection to facilitate the congestion learning, ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and iii) integrate domain knowledge from the traditional car following (CF) theory to improve the string stability of mMP.

Autonomous Vehicles BIG-bench Machine Learning +3

GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition

no code implementations ICCV 2019 Hao Zhou, Xiang Yu, David W. Jacobs

In this work, we propose a Global-Local Spherical Harmonics (GLoSH) lighting model to improve the lighting component, and jointly predict reflectance and surface normals.

Intrinsic Image Decomposition

Deep Single-Image Portrait Relighting

1 code implementation ICCV 2019 Hao Zhou, Sunil Hadap, Kalyan Sunkavalli, David W. Jacobs

In this work, we apply a physically-based portrait relighting method to generate a large scale, high quality, "in the wild" portrait relighting dataset (DPR).

 Ranked #1 on Single-Image Portrait Relighting on Multi-PIE (using extra training data)

Inverse Rendering Single-Image Portrait Relighting

Rethinking Text Attribute Transfer: A Lexical Analysis

1 code implementation WS 2019 Yao Fu, Hao Zhou, Jiaze Chen, Lei LI

We apply this framework to existing datasets and models and show that: (1) the pivot words are strong features for the classification of sentence attributes; (2) to change the attribute of a sentence, many datasets only requires to change certain pivot words; (3) consequently, many transfer models only perform the lexical-level modification, while leaving higher-level sentence structures unchanged.

General Classification Lexical Analysis +1

Towards Making the Most of BERT in Neural Machine Translation

2 code implementations15 Aug 2019 Jiacheng Yang, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Yong Yu, Wei-Nan Zhang, Lei LI

Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pre-training aided NMT by 1. 4 BLEU score.

Machine Translation NMT +1

Large-scale traffic signal control using machine learning: some traffic flow considerations

no code implementations7 Aug 2019 Jorge A. Laval, Hao Zhou

We find that: (i) a policy trained with supervised learning with only two examples outperforms LQF, (ii) random search is able to generate near-optimal policies, (iii) the prevailing average network occupancy during training is the major determinant of the effectiveness of DRL policies.

BIG-bench Machine Learning

Correct-and-Memorize: Learning to Translate from Interactive Revisions

no code implementations8 Jul 2019 Rongxiang Weng, Hao Zhou, Shu-Jian Huang, Lei LI, Yifan Xia, Jia-Jun Chen

Experiments in both ideal and real interactive translation settings demonstrate that our proposed \method enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods.

Machine Translation Translation

Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation

1 code implementation16 Jun 2019 Wenxian Shi, Hao Zhou, Ning Miao, Lei LI

To enhance the controllability and interpretability, one can replace the Gaussian prior with a mixture of Gaussian distributions (GM-VAE), whose mixture components could be related to hidden semantic aspects of data.

Language Modelling Text Generation

Dynamically Fused Graph Network for Multi-hop Reasoning

1 code implementation ACL 2019 Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei LI, Wei-Nan Zhang, Yong Yu

However, many difficult questions require multiple supporting evidence from scattered text among two or more documents.

Question Answering

AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications

no code implementations29 Apr 2019 Yuanfei Luo, Mengshuo Wang, Hao Zhou, Quanming Yao, Wei-Wei Tu, Yuqiang Chen, Qiang Yang, Wenyuan Dai

Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses.

Distributed Computing

Domain-Constrained Advertising Keyword Generation

no code implementations27 Feb 2019 Hao Zhou, Minlie Huang, Yishun Mao, Changlei Zhu, Peng Shu, Xiaoyan Zhu

Second, the inefficient ad impression issue: a large proportion of search queries, which are unpopular yet relevant to many ad keywords, have no ads presented on their search result pages.


CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling

1 code implementation14 Nov 2018 Ning Miao, Hao Zhou, Lili Mou, Rui Yan, Lei LI

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements.

Text Generation

On Tree-Based Neural Sentence Modeling

1 code implementation EMNLP 2018 Haoyue Shi, Hao Zhou, Jiaze Chen, Lei LI

To study the effectiveness of different tree structures, we replace the parsing trees with trivial trees (i. e., binary balanced tree, left-branching tree and right-branching tree) in the encoders.

Sentiment Analysis Text Classification

Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation

1 code implementation NAACL 2019 Hareesh Bahuleyan, Lili Mou, Hao Zhou, Olga Vechtomova

The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the posterior and prior.

Text Generation

Modeling Past and Future for Neural Machine Translation

1 code implementation TACL 2018 Zaixiang Zheng, Hao Zhou, Shu-Jian Huang, Lili Mou, Xin-yu Dai, Jia-Jun Chen, Zhaopeng Tu

The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents.

Machine Translation NMT +1

Dynamic Oracle for Neural Machine Translation in Decoding Phase

no code implementations LREC 2018 Zi-Yi Dou, Hao Zhou, Shu-Jian Huang, Xin-yu Dai, Jia-Jun Chen

However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it.

Machine Translation NMT +1

Augmenting End-to-End Dialog Systems with Commonsense Knowledge

no code implementations16 Sep 2017 Tom Young, Erik Cambria, Iti Chaturvedi, Minlie Huang, Hao Zhou, Subham Biswas

Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence.


A Deep Cascade Network for Unaligned Face Attribute Classification

no code implementations12 Sep 2017 Hui Ding, Hao Zhou, Shaohua Kevin Zhou, Rama Chellappa

First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes.

Classification General Classification +1

Chunk-Based Bi-Scale Decoder for Neural Machine Translation

1 code implementation ACL 2017 Hao Zhou, Zhaopeng Tu, Shu-Jian Huang, Xiaohua Liu, Hang Li, Jia-Jun Chen

In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN.

Machine Translation NMT +1

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

6 code implementations4 Apr 2017 Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, Bing Liu

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents.

Context-aware Natural Language Generation for Spoken Dialogue Systems

no code implementations COLING 2016 Hao Zhou, Minlie Huang, Xiaoyan Zhu

Most tranditional QA systems based on templates or rules tend to generate rigid and stylised responses without the natural variation of human language.

Dialogue Generation Question Answering +1