English

Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords

Computation and Language 2021-10-05 v2

Abstract

We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses. By inducing a contextualized "pseudoword" as a stand-in for a static embedding in the input layer, and then performing masked prediction of a word in the sentence, we are able to investigate the geometry of the BERT-space in a controlled manner around individual instances. Using our method on a set of carefully constructed sentences targeting ambiguous English words, we find substantial regularity in the contextualized space, with regions that correspond to distinct word senses; but between these regions there are occasionally "sense voids" -- regions that do not correspond to any intelligible sense.

Keywords

Cite

@article{arxiv.2109.11491,
  title  = {Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords},
  author = {Taelin Karidi and Yichu Zhou and Nathan Schneider and Omri Abend and Vivek Srikumar},
  journal= {arXiv preprint arXiv:2109.11491},
  year   = {2021}
}

Comments

EMNLP 2021 camera-ready version

R2 v1 2026-06-24T06:16:05.010Z