@inproceedings{f91ad02608a44d92b0f17bc0aef48ce4,
title = "Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords",
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.",
author = "Taelin Karidi and Yichu Zhou and Nathan Schneider and Omri Abend and Vivek Srikumar",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics; 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 ; Conference date: 07-11-2021 Through 14-11-2021",
year = "2021",
doi = "10.18653/v1/2021.emnlp-main.806",
language = "الإنجليزيّة",
series = "EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "10300--10313",
booktitle = "EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings",
address = "الولايات المتّحدة",
}