
Optimumstatistical collaboration towards efficient blackbox optimization
With increasingly more hyperparameters involved in their training, machi...
read it

Distributed ZerothOrder Stochastic Optimization in Timevarying Networks
We consider a distributed convex optimization problem in a network which...
read it

Distributed Derivativefree Learning Method for Stochastic Optimization over a Network with Sparse Activity
This paper addresses a distributed optimization problem in a communicati...
read it

Data Distillation for Text Classification
Deep learning techniques have achieved great success in many fields, whi...
read it

A Graphguided Multiround Retrieval Method for Conversational Opendomain Question Answering
In recent years, conversational agents have provided a natural and conve...
read it

A Simple Unified Framework for High Dimensional Bandit Problems
Stochastic high dimensional bandit problems with low dimensional structu...
read it

Incremental Knowledge Based Question Answering
In the past years, KnowledgeBased Question Answering (KBQA), which aims...
read it

Variance Reduction on Adaptive Stochastic Mirror Descent
We study the idea of variance reduction applied to adaptive stochastic m...
read it

Factlevel Extractive Summarization with Hierarchical Graph Mask on BERT
Most current extractive summarization models generate summaries by selec...
read it

Improving Accent Conversion with Reference Encoder and EndToEnd TextToSpeech
Accent conversion (AC) transforms a nonnative speaker's accent into a n...
read it

Increasedconfidence adversarial examples for improved transferability of CounterForensic attacks
Transferability of adversarial examples is a key issue to study the secu...
read it

AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
Although adaptive optimization algorithms such as Adam show fast converg...
read it

How Does BN Increase Collapsed Neural Network Filters?
Improving sparsity of deep neural networks (DNNs) is essential for netwo...
read it

Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
Semantic parsing aims to transform natural language (NL) utterances into...
read it

Knowledge Graph Convolutional Networks for Recommender Systems with Label Smoothness Regularization
Knowledge graphs capture interlinked information between entities and th...
read it

Knowledgeaware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems
Knowledge graphs capture structured information and relations between a ...
read it

Knowledgeaware Graph Neural Networks with Label Smoothness Regularization for Recommendation
Knowledge graphs capture structured information and relations between a ...
read it

Quality of Experience from Cache Hierarchies: Keep your lowbitrate close, and highbitrate closer
Recent studies into streaming media delivery suggest that performance ga...
read it

Knowledge Graph Convolutional Networks for Recommender Systems
To alleviate sparsity and cold start problem of collaborative filtering ...
read it

When Collaborative Filtering Meets Reinforcement Learning
In this paper, we study a multistep interactive recommendation problem,...
read it

MultiTask Feature Learning for Knowledge Graph Enhanced Recommendation
Collaborative filtering often suffers from sparsity and cold start probl...
read it

VisualTexual Emotion Analysis with Deep Coupled Video and Danmu Neural Networks
User emotion analysis toward videos is to automatically recognize the ge...
read it

Incorporating Relevant Knowledge in Context Modeling and Response Generation
To sustain engaging conversation, it is critical for chatbots to make go...
read it

Metapath Augmented Response Generation
We propose a chatbot, namely Mocha to make good use of relevant entities...
read it

NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
SequencetoSequence (seq2seq) models have become overwhelmingly popular...
read it

Distributed Stochastic Optimization in Networks with Low Informational Exchange
We consider a distributed stochastic optimization problem in networks wi...
read it

Large scale classification in deep neural network with Label Mapping
In recent years, deep neural network is widely used in machine learning....
read it

Unpaired SentimenttoSentiment Translation: A Cycled Reinforcement Learning Approach
The goal of sentimenttosentiment "translation" is to change the underl...
read it

Ripple Network: Propagating User Preferences on the Knowledge Graph for Recommender Systems
To address the sparsity and cold start problem of collaborative filterin...
read it

Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
Most recent approaches use the sequencetosequence model for paraphrase...
read it

Word Embedding Attention Network: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
Most recent approaches use the sequencetosequence model for paraphrase...
read it

Matrix Exponential Learning for Resource Allocation with Low Informational Exchange
We consider a distributed resource allocation problem in a multicarrier ...
read it

Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
Recent systems on structured prediction focus on increasing the level of...
read it

Faithful to the Original: Fact Aware Neural Abstractive Summarization
Unlike extractive summarization, abstractive summarization has to fuse d...
read it

DailyDialog: A Manually Labelled Multiturn Dialogue Dataset
We develop a highquality multiturn dialog dataset, DailyDialog, which ...
read it

Improving Semantic Relevance for SequencetoSequence Learning of Chinese Social Media Text Summarization
Current Chinese social media text summarization models are based on an e...
read it

A Conditional Variational Framework for Dialog Generation
Deep latent variable models have been shown to facilitate the response g...
read it

MaximumLikelihood Augmented Discrete Generative Adversarial Networks
Despite the successes in capturing continuous distributions, the applica...
read it

Mode Regularized Generative Adversarial Networks
Although Generative Adversarial Networks achieve stateoftheart result...
read it

Improving MultiDocument Summarization via Text Classification
Developed so far, multidocument summarization has reached its bottlenec...
read it

Joint Copying and Restricted Generation for Paraphrase
Many natural language generation tasks, such as abstractive summarizatio...
read it

AttSum: Joint Learning of Focusing and Summarization with Neural Attention
Query relevance ranking and sentence saliency ranking are the two main t...
read it

TGSum: Build Tweet Guided MultiDocument Summarization Dataset
The development of summarization research has been significantly hampere...
read it

ComponentEnhanced Chinese Character Embeddings
Distributed word representations are very useful for capturing semantic ...
read it

A Confident Information First Principle for Parametric Reduction and Model Selection of Boltzmann Machines
Typical dimensionality reduction (DR) methods are often dataoriented, f...
read it

Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle
Typical dimensionality reduction methods focus on directly reducing the ...
read it

On Tsallis Entropy Bias and Generalized Maximum Entropy Models
In density estimation task, maximum entropy model (Maxent) can effective...
read it
Wenjie Li
is this you? claim profile
Associate Professor, Department of Computing at The Hong Kong Polytechnic University