Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 9 of 9 for “"Citation graph"”.

  1. A Citation-Graph Enhanced Language Model for Scientific Applications

    … a language model architecture that utilizes the citation graph structure of scientific literature to enhance its contextual understanding. By being able to leverage the citation graph, the model is able to go beyond the limitations of an individual paper's content and find hidden connections to …

    tamu Repository record for A Citation-Graph Enhanced Language Model for Scientific Applications (opens in a new tab) Embargoed until 2027-05-01

  2. Evaluation of Citation Graph Thematic Dataset Construction and Paper Filtering Methods for Research Literature Recommendation

    … a novel approach for constructing datasets using citation graph networks. These networks consist of nodes representing research papers and edges representing citations between them. By leveraging citation graph networks, we gain a more comprehensive understanding of the relationships and …

    concordia Download PDF for Evaluation of Citation Graph Thematic Dataset Construction and Paper Filtering Methods for Research Literature Recommendation (opens in a new tab)

  3. Design and Benchmarking of a Citation Graph DB Across Neo4j, ArangoDB, and MASS Graph DB Systems

    Academic collaboration, citation influence, and institutional research visibility are increasingly reflected through scholarly relationship networks. However, existing academic platforms remain largely profile-centered and do not provide an institution-focused, interactive, and queryable graph …

    washington Repository record for Design and Benchmarking of a Citation Graph DB Across Neo4j, ArangoDB, and MASS Graph DB Systems (opens in a new tab)

  4. Metapath of Thoughts: Verbalized Metapaths in Heterogeneous Graph as Contextual Augmentation to LLM

    Heterogeneous graph neural networks (HGNNs) excel in cap- turing graph topology and structural information. However, they are ineffective in processing the textual components present in nodes and edges and thus producing suboptimal performance in downstream tasks such as node-classification. …

    washington Repository record for Metapath of Thoughts: Verbalized Metapaths in Heterogeneous Graph as Contextual Augmentation to LLM (opens in a new tab)

  5. Using Graphs For Topic Discovery

    … surge of research interest in the task. We use graphs for topic discovery and topic evolution discovery by mining the statistical properties of graphs associated with the text data. Considering that an increasing number of text collections have some kind of networks associated with the data …

    cornell Repository record for Using Graphs For Topic Discovery (opens in a new tab)

  6. Capturing and Exploiting Citation Knowledge for the Recommendation of Scientific Publications

    … investigates the <b>use of fine-grained forms of citation knowledge</b>, extracted from the full textual content of scientific publications, to enhance recommendations: citation proximity, citation context, citation section, citation graph and citation intention. We <b>design and develop new …

    the-open-u Download PDF for Capturing and Exploiting Citation Knowledge for the Recommendation of Scientific Publications (opens in a new tab)

  7. Using natural language processing to address health professionals’ information needs

    … methods, BERT-based models, and graph-informed approaches that incorporate features derived from citation networks. Among these, BERTbased models achieved the highest classification performance, highlighting the effectiveness of deep contextual language representations in …

    kings Repository record for Using natural language processing to address health professionals’ information needs (opens in a new tab) Download PDF for Using natural language processing to address health professionals’ information needs (opens in a new tab)

  8. Bibliographic database analysis: citation graphs and indirect indicators

    … of knowledge is one of the areas where Citation Analysis can be of great use. The different techniques, metrics and approaches defined by Citation Analysis allow scientists to identify publications of particular interest, follow the published research of influential scientists and even …

    greece Repository record for Bibliographic database analysis: citation graphs and indirect indicators (opens in a new tab)