Graph-based term weighting for information retrieval

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Text Categorization as a Graph Classification Problem (2015, methodology): “We refer to (Blanco and Lioma, 2012) for an in-depth review of the graph representations of text in NLP. system softwar implement disciplin scienc span topic theoret studi rang limit algorithm issu practic hardwar comput As a discipline, computer science spans a range of topics from theoretical…”
Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval (2019, methodology): “, [2, 3, 5, 18, 27, 36]), however frequency-based signals continue to dominate in both industry and academia.”
Context-Aware Document Term Weighting for Ad-Hoc Search (2020, methodology): “Another alternative is graph-based methods [4, 26, 33].”
Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks (2020, methodology): “The text is preprocessed in a standard way, including tokenisation and stopword removal (Blanco and Lioma, 2012; Rousseau et al., 2015).”