Directed Criteria Citation Recommendation and Ranking Through Link Prediction
This provides a holistic approach for domains where accurate citation is critical to minimize inconsistencies, addressing a specific need in document management.
The paper tackled the problem of recommending and ranking relevant citations for new documents by using transformer-based graph embeddings on citation networks, achieving performance that outperforms other content-based methods.
We explore link prediction as a proxy for automatically surfacing documents from existing literature that might be topically or contextually relevant to a new document. Our model uses transformer-based graph embeddings to encode the meaning of each document, presented as a node within a citation network. We show that the semantic representations that our model generates can outperform other content-based methods in recommendation and ranking tasks. This provides a holistic approach to exploring citation graphs in domains where it is critical that these documents properly cite each other, so as to minimize the possibility of any inconsistencies