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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this study, we investigate using graph neural network (GNN)representations to enhance contextualized representations of pre-trainedlanguage models (PLMs) for keyphrase extraction from lengthy documents. We showthat augmenting a PLM with graph embeddings provides a more comprehensivesemantic understanding of words in a document, particularly for long documents.We construct a co-occurrence graph of the text and embed it using a graphconvolutional network (GCN) trained on the task of edge prediction. We proposea graph-enhanced sequence tagging architecture that augments contextualized PLMembeddings with graph representations. Evaluating on benchmark datasets, wedemonstrate that enhancing PLMs with graph embeddings outperformsstate-of-the-art models on long documents, showing significant improvements inF1 scores across all the datasets. Our study highlights the potential of GNNrepresentations as a complementary approach to improve PLM performance forkeyphrase extraction from long documents.

Enhancing Keyphrase Extraction from Long Scientific Documents using Graph Embeddings