Corpus ID: 218971881

Cats climb entails mammals move: preserving hyponymy in compositional distributional semantics

@article{Cuevas2020CatsCE,
  title={Cats climb entails mammals move: preserving hyponymy in compositional distributional semantics},
  author={Gemma de las Cuevas and A. Klinger and Martha Lewis and Tim Netzer},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.14134}
}
  • Gemma de las Cuevas, A. Klinger, +1 author Tim Netzer
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • To give vector-based representations of meaning more structure, one approach is to use positive semidefinite (psd) matrices. These allow us to model similarity of words as well as the hyponymy or is-a relationship. Psd matrices can be learnt relatively easily in a given vector space $M\otimes M^*$, but to compose words to form phrases and sentences, we need representations in larger spaces. In this paper, we introduce a generic way of composing the psd matrices corresponding to words. We… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Compositional Hyponymy with Positive Operators

    VIEW 6 EXCERPTS

    Meaning updating of density matrices

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A Categorical compositional distributional semantics In this appendix we give a brief introduction to the categorical compositional approach to distributional semantics -for details see

    • J Van De Wetering
    • Ordering information on distributions
    • 2017

    Composition in Distributional Models of Semantics

    VIEW 1 EXCERPT

    Compositionality for Recursive Neural Networks

    VIEW 2 EXCERPTS