Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with Pseudowords
Taelin Karidi, Yichu Zhou, Nathan Schneider, Omri Abend, Vivek Srikumar
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” vector 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 highly 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.
BibTeX
@inproceedings{karidi-etal-2021-putting,
title = "Putting Words in {BERT}`s Mouth: Navigating Contextualized Vector Spaces with Pseudowords",
author = "Karidi, Taelin and
Zhou, Yichu and
Schneider, Nathan and
Abend, Omri and
Srikumar, Vivek",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.806/",
doi = "10.18653/v1/2021.emnlp-main.806",
pages = "10300--10313"
}