[Adapt] [Seminar] Multi-Label Classification

[廖千姿]

Hi Adapters, 

For the seminar in this week, I will talk about Multi-Label Classification. The target of the MLC task is to assign multiple labels to each instance in the dataset. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations between labels. SGM: Sequence Generation Model for Multi-Label Classification captures the correlations between the labels by viewing the multi-label classification task as a sequence generation problem, and applies a sequence generation model with a novel decoder structure to solve it. This model also selects the most informative words automatically when predicting different labels. 

See you there! 

Time: 17:00 Sept 26 
Venue: SEIEE 3-517A 

Best, 
Eve 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20180925/ee4953ec/attachment.html>