Learning Graph Embeddings from WordNet-based Similarity Measures

  title={Learning Graph Embeddings from WordNet-based Similarity Measures},
  author={Andrey Kutuzov and Alexander Panchenko and Sarah Kohail and Mohammad Dorgham and Oleksiy Oliynyk and Chris Biemann},
  • Andrey Kutuzov, Alexander Panchenko, +3 authors Chris Biemann
  • Published 2019
  • Computer Science
  • ArXiv
  • We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based… CONTINUE READING
    4 Citations
    Constructing knowledge graphs and their biomedical applications
    Activity Diagram Similarity Measurement: A Different Approach


    Affinity Measures Based on the Graph Laplacian
    • 16
    • PDF
    On metric embedding for boosting semantic similarity computations
    • 7
    • Highly Influential
    • PDF
    GraRep: Learning Graph Representations with Global Structural Information
    • 757
    • PDF
    Inductive Representation Learning on Large Graphs
    • 2,283
    • PDF
    Unsupervised Graph-basedWord Sense Disambiguation Using Measures of Word Semantic Similarity
    • R. Sinha, R. Mihalcea
    • Computer Science
    • International Conference on Semantic Computing (ICSC 2007)
    • 2007
    • 106
    • PDF
    Glove: Global Vectors for Word Representation
    • 15,708
    • PDF
    Representation Learning on Graphs: Methods and Applications
    • 776
    • Highly Influential
    • PDF
    Evaluating WordNet-based Measures of Lexical Semantic Relatedness
    • 1,478
    • PDF
    Translating Embeddings for Modeling Multi-relational Data
    • 2,370
    • PDF