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 a new approach for learning graph embeddings, that relies on structural measures of node similarities for generation of training data. The model learns node embeddings that are able to approximate a given measure, such as the shortest path distance or any other. Evaluations of the proposed model on semantic similarity and word sense disambiguation tasks (using WordNet as the source of gold similarities) show that our method yields state-of-the-art results, but also is capable in… CONTINUE READING


    Publications referenced by this paper.
    Glove: Global Vectors for Word Representation
    • 14,654
    • PDF
    Distributed Representations of Words and Phrases and their Compositionality
    • 18,883
    • Highly Influential
    • PDF
    Adam: A Method for Stochastic Optimization
    • 49,762
    • PDF
    WordNet: a lexical database for English
    • 11,777
    • PDF
    Inductive Representation Learning on Large Graphs
    • 2,049
    • PDF
    node2vec: Scalable Feature Learning for Networks
    • 3,301
    • PDF
    Translating Embeddings for Modeling Multi-relational Data
    • 2,215
    • PDF
    Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy
    • 3,165
    • PDF
    DeepWalk: online learning of social representations
    • 3,419
    • Highly Influential
    • PDF
    Evaluating WordNet-based Measures of Lexical Semantic Relatedness
    • 1,462
    • PDF