Evaluating the Stability of Embedding-based Word Similarities

Maria Antoniak, David Mimno, 2018. Transactions of the Association for Computational Linguistics.

Shows that nearest-neighbor similarities from word embeddings shift considerably with small changes to the training corpus, more so for small corpora, and recommends averaging over bootstrap samples rather than trusting one model.

Voynich ManuscriptArticledoi: 10.1162/tacl_a_00008Checked against the original0

What it's used for here

The inductive-methods survey cites it for bootstrap stability checks on embeddings trained on the small Voynich corpus.

Cited by on this site 1 record

1 methods surveys

Inductive methods

SRC

Cite it

Antoniak, M., & Mimno, D. (2018). Evaluating the Stability of Embedding-based Word Similarities. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00008

@article{antoniak2018evaluating,
  author = {Antoniak, Maria and Mimno, David},
  title = {Evaluating the Stability of Embedding-based Word Similarities},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2018},
  doi = {10.1162/tacl_a_00008},
  url = {https://doi.org/10.1162/tacl_a_00008}
}

TY  - JOUR
TI  - Evaluating the Stability of Embedding-based Word Similarities
AU  - Antoniak, Maria
AU  - Mimno, David
PY  - 2018
JO  - Transactions of the Association for Computational Linguistics
DO  - 10.1162/tacl_a_00008
UR  - https://doi.org/10.1162/tacl_a_00008
ER  -

Antoniak, Maria and David Mimno. “Evaluating the Stability of Embedding-based Word Similarities.” Transactions of the Association for Computational Linguistics (2018). https://doi.org/10.1162/tacl_a_00008.