About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Ankit Pal
- sl:arxiv_num : 2003.11644
- sl:arxiv_published : 2020-03-22T17:12:43Z
- sl:arxiv_summary : In Multi-Label Text Classification (MLTC), one sample can belong to more than
one class. It is observed that most MLTC tasks, there are dependencies or
correlations among labels. Existing methods tend to ignore the relationship
among labels. In this paper, a graph attention network-based model is proposed
to capture the attentive dependency structure among the labels. The graph
attention network uses a feature matrix and a correlation matrix to capture and
explore the crucial dependencies between the labels and generate classifiers
for the task. The generated classifiers are applied to sentence feature vectors
obtained from the text feature extraction network (BiLSTM) to enable end-to-end
training. Attention allows the system to assign different weights to neighbor
nodes per label, thus allowing it to learn the dependencies among labels
implicitly. The results of the proposed model are validated on five real-world
MLTC datasets. The proposed model achieves similar or better performance
compared to the previous state-of-the-art models.@en
- sl:arxiv_title : Multi-Label Text Classification using Attention-based Graph Neural Network@en
- sl:arxiv_updated : 2020-03-22T17:12:43Z
- sl:bookmarkOf : https://arxiv.org/abs/2003.11644
- sl:creationDate : 2020-08-14
- sl:creationTime : 2020-08-14T16:11:43Z
- sl:relatedDoc : http://www.semanlink.net/doc/2019/06/_1905_10070_label_aware_docume
Documents with similar tags (experimental)