Corpus ID: 222124859

SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces

@inproceedings{Vani2020SSTBERTAS,
  title={SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces},
  author={K. Vani and S. Mitrovic and Alessandro Antonucci and F. Rinaldi},
  booktitle={SemEval@COLING},
  year={2020}
}
  • K. Vani, S. Mitrovic, +1 author F. Rinaldi
  • Published in SemEval@COLING 2020
  • Computer Science
  • Lexical semantic change detection (also known as semantic shift tracing) is a task of identifying words that have changed their meaning over time. Unsupervised semantic shift tracing, focal point of SemEval2020, is particularly challenging. Given the unsupervised setup, in this work, we propose to identify clusters among different occurrences of each target word, considering these as representatives of different word meanings. As such, disagreements in obtained clusters naturally allow to… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 31 REFERENCES
    Diachronic word embeddings and semantic shifts: a survey
    • 109
    • PDF
    SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection
    • 41
    • PDF
    Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
    • 348
    • PDF
    Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change
    • 460
    • PDF
    Survey of Computational Approaches to Lexical Semantic Change
    • 38
    • PDF
    Statistically Significant Detection of Linguistic Change
    • 280
    • PDF