“Sunwei”的版本间的差异

来自南京大学IIP
跳转至： 导航， 搜索
   （更改可见性）
Lhy（讨论 | 贡献）
   （更改可见性）
第26行： 第26行：
 
<span style="font-size:larger;"><span style="color:#3498db">'''Research Interest'''</span></span>
 
<span style="font-size:larger;"><span style="color:#3498db">'''Research Interest'''</span></span>
  
−
<span style="font-size:larger;">&nbsp;'''Machine Learning &&nbsp;Multi-label Learning'''.&nbsp;</span>
+
<span style="font-size:larger;">&nbsp;</span><span style="font-size:larger;">'''Multi-label Learning'''&nbsp;'''& Sentiment Analysis.'''&nbsp;</span>
−
 
 
−
*<span style="font-size:larger;">On '''Multi-label Text Classification (MLTC),''' text features can be regarded as '''detailed description of documents''' and label sets can be '''a summarization of documents'''. '''Hybrid Topics''' from text features and label sets by LDA (a method of '''topic model''') can effectively mine global label correlations and deeper&nbsp;features. Meanwhile, a pair including topics and labels can mitigate the imbalanced problem of labels.</span>
 
−
*<span style="font-size:larger;">Deep learning For multi-label text classification. We utilize '''dilated convolution''' to obtain the '''semantic understanding''' of the text and design a hybrid '''attention mechansim''' for '''different labels''' (Specifically, each label should attend to most relevant textual contents).&nbsp; Firstly,&nbsp;we initialize trainable label embeddings. Then After obationing word-level information based on Bi-LSTM, we&nbsp;get semantic understanding of texts&nbsp;based on word-level information by dilated convolution. Finally,&nbsp;we design a hybrid attention for different labels based on label embeddings.&nbsp; Besides, we add '''label cooccurrence matrix into loss function '''to guide the whole network to learn and achieve good results.&nbsp;&nbsp;</span>
 
−
*<span style="font-size:larger;">'''GCN (Graph Convolution Network) '''can be used to exploit more complex label correlations on&nbsp;Multi-label Learning.</span>  
 
  
 
<span style="font-size:larger;"><font color="#3498db">'''Publications'''</font></span>
 
<span style="font-size:larger;"><font color="#3498db">'''Publications'''</font></span>

2019年8月8日 (四) 22:20的版本

M.Sc. Student @ IIP Group
Department of Computer Science and Technology
Nanjing University

Email: weisun_@outlook.com

   

Supervisor

  • Professor Jun-Yuan Xie

Biography

  • I received my B.Sc. degree in of Soochow University in June 2017. In the same year, I was admitted to study for a Master degree in Nanjing University without entrance examination.  Currently I am a second year M.Sc. student of Department of Computer Science and Technology in Nanjing University and a member of IIP Group, led by professor Jun-Yuan Xie and  Chong-Jun Wang.

Research Interest

 Multi-label Learning & Sentiment Analysis. 

Publications

  • Ran X., Pan Y., Sun W. and Wang C.. Learn to Select via Hierarchical Gate Mechanism for Aspect-Based Sentiment Analysis. In Proceedings of IJCAL 2019.
  • Sun W., Wang C..Multi-label Classification: Select Distinct Semantic Understanding for Different Labels[C]. In Proceedings of ApWeb-WAIM 2019.
  • Sun W., Ran X.. Luo X., and Wang C..An Efficient Framework by Topic Model for Multi-label Text Classification. In Proceedings of IJCNN 2019.
  • Xu Y., Ran X.. Sun W., Luo X. and Wang C..Gated Neural Network with Regularized Loss for Multi-label Text Classification. In Proceedings of IJCNN 2019.
  • Ran X., Pan Y., Sun W. and Wang C.. Modeling More Globally: A Hierarchical Attention Network via Multi-Task Learning for Aspect-Based Sentiment Analysis. In Proceedings of DASFAA 2019, Chiang Mai, Thailand, Apr. 22-25, 2019: 505-509.

Resources

Rewards or Honors

  • Second-Class Academic Scholarship, 2018-2019
  • First-Class Academic Scholarship, 2017-2018
  • Outstanding Graduate Student, 2017.06
  • CCF Excellent University Student, 2016.10
  • National Scholarship, 2015.11
取自“http://iip.nju.edu.cn/index.php?title=Sunwei&oldid=1112”