English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Keyphrase extraction (KE) aims to summarize a set of phrases that accuratelyexpress a concept or a topic covered in a given document. Recently,Sequence-to-Sequence (Seq2Seq) based generative framework is widely used in KEtask, and it has obtained competitive performance on various benchmarks. Themain challenges of Seq2Seq methods lie in acquiring informative latent documentrepresentation and better modeling the compositionality of the targetkeyphrases set, which will directly affect the quality of generated keyphrases.In this paper, we propose to adopt the Dynamic Graph Convolutional Networks(DGCN) to solve the above two problems simultaneously. Concretely, we exploreto integrate dependency trees with GCN for latent representation learning.Moreover, the graph structure in our model is dynamically modified during thelearning process according to the generated keyphrases. To this end, ourapproach is able to explicitly learn the relations within the keyphrasescollection and guarantee the information interchange between encoder anddecoder in both directions. Extensive experiments on various KE benchmarkdatasets demonstrate the effectiveness of our approach.

Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference