Adjusting Interpretable Dimensions in Embedding Space with Human Judgments
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSimilar Papers 제목 키워드 기반
Interpreting Word Embeddings with Eigenvector Analysis
Dense word vectors have proven their values in many downstream NLP tasks over the past few years. However, the dimensions of such embeddings are not easily interpretable. Out of the d-dimensions in a word vector, we woul…
Word EmbeddingsThe POLAR Framework: Polar Opposites Enable Interpretability of Pre-Trained Word Embeddings
We introduce POLAR - a framework that adds interpretability to pre-trained word embeddings via the adoption of semantic differentials. Semantic differentials are a psychometric construct for measuring the semantics of a …
Word EmbeddingsUsing Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge
Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble…
DINE: Dimensional Interpretability of Node Embeddings
Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches…
Graph Representation LearningLink PredictionRepresentation LearningVICE: Variational Interpretable Concept Embeddings
A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bay…
Experimental DesignObjectOdd One OutPAC learning+2