• Publications
  • Influence
Incorporating GAN for Negative Sampling in Knowledge Representation Learning
This paper proposes a novel knowledge representation learning framework based on Generative Adversarial Networks (GAN) that takes advantage of a generator to obtain high-quality negative samples and outperforms baselines on triplets classification and link prediction tasks.
Tag-Weighted Topic Model for Mining Semi-Structured Documents
This paper proposes a novel method to model tagged documents by a topic model, called Tag-Weighted Topic Model (TWTM), a framework that leverages the tags in each document to infer the topic components for the documents.
Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning
This paper presents a deep reinforcement learning based model named by AttnPath, which incorporates LSTM and Graph Attention Mechanism as the memory components, and defines two metrics, Mean Selection Rate (MSR) and Mean Replacement Rate (MRR), to quantitatively measure how difficult it is to learn the query relations.
Personalizing a Dialogue System With Transfer Reinforcement Learning
This work proposes "PETAL"(PErsonalized Task-oriented diALogue), a transfer-learning framework based on POMDP to learn a personalized dialogue system that can avoid the negative transfer problem by considering differences between source and target users.
Recurrent Attentional Topic Model
A Recurrent Attentional Topic Model (RATM) for document embedding that fully utilizes the sequential information of the sentences in a document and outperforms state-of-the-art methods on document modeling and classification.
Design and Study on Ocean Energy with the Horizontal Axis Tidal Current Turbine's Blade Especially for China's Low Tidal Current Velocity
Tidal current energy of sea surface is a kind of renewable energy with wide prospect of development. Because of its relatively high utilization ratio, the horizontal-axis turbine generation system
Length Adaptive Recurrent Model for Text Classification
A Length Adaptive Recurrent Model (LARM) which can automatically determine the minimum text length that is necessary to perform the classification of a text.
Tag-Weighted Topic Model For Large-scale Semi-Structured Documents
This work proposes a novel method to model the SSDs by a so-called Tag-Weighted Topic Model (TWTM), a framework that leverages both the tags and words information, not only to learn the document-topic and topic-word distributions, but also to infer the tag-topic distributions for text mining tasks.
Spring-back analysis in the cold-forming process of ship hull plates
Hull structures and offshore structures are composed of curved thick plates. Line heating method has traditionally been used to produce such curved plates. However, it is recognized that the
Bi-Directional Recurrent Attentional Topic Model
The proposed bi-RATM takes advantage of the sequential orders among sentences but also uses the attention mechanism to model the relations among successive sentences and outperforms state-of-the-art methods on document modeling and classification.