Papers with localized convolution filters

1 papers
Glocal: Incorporating Global Information in Local Convolution for Keyphrase Extraction (N19-1)

Copied to clipboard

Challenge: Graph Convolutional Networks (GCNs) model nodes’ local pairwise importance but lack the capability to model global relative importance in tasks where global ranking is a key component for the task.
Approach: They propose to incorporate global relative importance information into the GCN family of models by using scaled node weights.
Outcome: The proposed method improves keyphrase extraction by 2% and improves the baseline by 5%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations