Adjusting Interpretable Dimensions in Embedding Space with Human Judgments

• Main Authors: Erk, Katrin, Apidianaki, Marianna
• Format: Journal Article
• Language: English
• Published: 03-04-2024
• Subjects: Computer Science - Computation and Language
• DOI: 10.48550/arxiv.2404.02619

Embedding spaces contain interpretable dimensions indicating gender,
formality in style, or even object properties. This has been observed multiple
times. Such interpretable dimensions are becoming valuable tools in different
areas of study, from social science to neuroscience. The standard way to
compute these dimensions uses contrasting seed words and computes difference
vectors over them. This is simple but does not always work well. We combine
seed-based vectors with guidance from human ratings of where words fall along a
specific dimension, and evaluate on predicting both object properties like size
and danger, and the stylistic properties of formality and complexity. We obtain
interpretable dimensions with markedly better performance especially in cases
where seed-based dimensions do not work well.