… space, and treat the label as a meaningless multi-hot vector. In this paper, we put … -label
text classification algorithm LELC(joint learning from Label Embedding and Label Correlation) …

… We analyze low-frequency label performance, label dependency, label combination diversity
and coverage speed to show the effectiveness of our proposed method on label correlation …

… we consider both label correlations and context-label correlations in the same space at the
beginning. Note that when label descriptions are unavailable, we represent each label with a …

… us obtain more accurate label predictions. Therefore, in order to make better use of the
label correlations, we propose a new network architecture, named Correlation Networks (CorNet)…

… correlations. In this subsection, we start with a discussion of the horizontal and vertical
correlations in the hierarchical multi-label text classification … both types of category correlations. …

… label correlation mixture model (LCMM), to depict multi-labeled document data, which can be
utilized for multi-label text classification… labels are generated based on the label correlation …

… areas such as text categorization, … label correlations is helpful while the others are less
informative or even harmful and the instances in the same topic share the same label correlations. …

… -of-the-art text classification approaches perform poorly on multi-label data sets as we … text
classification approach that handles all of them while, at the same time, utilizes the class label …

… -label classification is suitable for many domains such as text … correlation considering as
variables each pair of multi-label … to identify if they are strongly correlated with each other. …

… in text classification leverages implicit correlations among … However, most previous works
treat labels of each task as … -Task Label Embedding to convert labels in text classification into …