Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test
Independent Component Analysis (ICA) is an algorithm originally developed for finding separate sources in a mixed signal, such as a recording of multiple people in the same room speaking at the same time. Unlike Principal Component Analysis (PCA), ICA permits the representation of a word as an unstr...
Saved in:
Main Authors | , |
---|---|
Format | Journal Article |
Language | English |
Published |
19.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Independent Component Analysis (ICA) is an algorithm originally developed for
finding separate sources in a mixed signal, such as a recording of multiple
people in the same room speaking at the same time. Unlike Principal Component
Analysis (PCA), ICA permits the representation of a word as an unstructured set
of features, without any particular feature being deemed more significant than
the others. In this paper, we used ICA to analyze word embeddings. We have
found that ICA can be used to find semantic features of the words, and these
features can easily be combined to search for words that satisfy the
combination. We show that most of the independent components represent such
features. To quantify the interpretability of the components, we use the word
intruder test, performed both by humans and by large language models. We
propose to use the automated version of the word intruder test as a fast and
inexpensive way of quantifying vector interpretability without the need for
human effort. |
---|---|
DOI: | 10.48550/arxiv.2212.09580 |