Corpus ID: 208547731

Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift

@article{Martinc2020LeveragingCE,
  title={Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift},
  author={Matej Martinc and Petra Kralj Novak and Senja Pollak},
  journal={ArXiv},
  year={2020},
  volume={abs/1912.01072}
}
  • Matej Martinc, Petra Kralj Novak, Senja Pollak
  • Published 2020
  • Computer Science
  • ArXiv
  • We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings. The results of our experiments in the domain specific LiverpoolFC corpus suggest that the proposed method has performance comparable to the current state-of-the-art without requiring any time consuming domain adaptation on large corpora. The results on the newly created Brexit news corpus suggest that the method… 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 40 REFERENCES

    Deep contextualized word representations

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Neural Models of Semantic Shift

    VIEW 2 EXCERPTS

    Lexical Semantic Change Analysis with Contextualised Word Representations

    • MARIO GIULIANELLI
    • 2019
    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Efficient Estimation of Word Representations in Vector Space

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL