更改

Sunwei

添加781字节, 2019年5月26日 (日) 23:30
无编辑摘要
<span style="font-size:larger"><span style="color:#3498db">'''Research Interest'''</span></span>
 
&nbsp;'''Machine Learning &&nbsp;Multi-label Learning'''.&nbsp;
 
*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.
*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;
*'''GCN (Graph Convolution Network) '''can be used to exploit more complex label correlations on Image Multi-label Learning.
 
<font color="#3498db"><span style="font-size:15.6px">'''Publications'''</span></font>
----
I am interested in '''Machine Learning *Ran X., Pan Y., Sun W. and Multi&nbsp;Wang C.. Learn to Select via Hierarchical Gate Mechanism for Aspect-label Learning'''Based Sentiment Analysis.&nbsp; *On In&nbsp;''Proceedings of IJCAL 2019.''*Sun W., Wang C..Multi-label Text Classification (MLTC),''' text features can be regarded as '''detailed description of documents''' and label sets can be '''a summarization of documents''': Select Distinct Semantic Understanding for Different Labels[C]. In&nbsp;'''Hybrid Topics''' from text features and label sets by LDA (a method Proceedings of '''topic model''') can effectively mine global label correlations and deeper&nbsp;featuresApWeb-WAIM 2019.&nbsp; The paper '''"*Sun W., Ran X.. Luo X., and Wang C..An Efficient Framework by Topic Model for Multi-label Text Classification"'''&nbsp; has been. In&nbsp;accepted in '''Proceedings of IJCNN 2019.'''. *Deep learning For multi-label text classificationXu Y. 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)Ran X.. Sun W.&nbsp; Firstly,Luo X.&nbsp;we initialize trainable label embeddingsand Wang C. 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 Gated Neural Network with Regularized Loss for different labels based on Multi-label embeddingsText Classification.In&nbsp; Besides, we add ''Proceedings of IJCNN 2019.'label cooccurrence matrix into loss function '''to guide the whole network to learn *Ran X., Pan Y., Sun W. and achieve good results.&nbsp; The paperWang C.. Modeling More Globally: A Hierarchical Attention Network via Multi-Task Learning for Aspect-Based Sentiment Analysis. In&nbsp;"'''Multi-label Classification: Select Distinct Semantic Understanding Proceedings of Text for Different LabelsDASFAA 2019'''" has been accepted in'''APWEB-WAIM 2019, Chiang Mai, Thailand, Apr.''' *'''GCN (Graph Convolution Network) '''can be used to exploit more complex label correlations on Image Multi22-label Learning.25,&nbsp; 2019: 505-509.
<span style="font-size:larger"><span style="color:#3498db">'''Resources'''</span></span>
*[http://manikvarma.org/downloads/XC/XMLRepository.html Extreme Classification Repository]: for large-scale multi-label datasets and off-the-shelf eXtreme Multi-Label Learning (XML) solvers.
*[http://mulan.sourceforge.net/datasets-mlc.html Mulan Multi-Label Learning Datasets]: regular/traditional multi-label learning datasets.
*[https://github.com/XSilverBullet/Multi-label-Paper Related WorksWork]: This page categorizes a list of works of my interest, mainly in Multi-Label Learning.
<span style="font-size:larger"><span style="color:#3498db">'''Rewards or Honors'''</span></span>
456
个编辑