更改

{| cellspacingborder="10" cellpadding="1" bordercellspacing="01"

*I am interested in '''Machine Learning and Multi-label Learning'''.   *Specifically, now my first work is to exploit label correlations on multi-label learning, i.e. 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 effectivelymine global label correlations and deeper features. represent the whole The paper '''"An Efficient Framework for Multi-label correlationsText Classification"'''  is accepted in '''IJCNN 2019'''. *My second work is to apply deep Deep learning to 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 information).  First, ly we initialize trainable label embeddings. We obation Then After obationing word-level information base based on Bi-LSTM and , we get semantic understanding of a document texts based on word-level informationby dilated convolution. ThenFinally,  we design a hybrid attention for different labels based on label embeddings.  Besides, we add '''label cooccurrence matrix into loss function '''to guide the whole network to learn and achieve good results.