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 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Word EmbeddingsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring Intra and Inter-language Consistency in Embeddings with ICA
Word embeddings represent words as multidimensional real vectors, facilitating data analysis and processing, but are often challenging to interpret. Independent Component Analysis (ICA) creates clearer semantic axes by i…
Word EmbeddingsRotations and Interpretability of Word Embeddings: the Case of the Russian Language
Consider a continuous word embedding model. Usually, the cosines between word vectors are used as a measure of similarity of words. These cosines do not change under orthogonal transformations of the embedding space. We …
Word EmbeddingsCharacter-level Chinese Backpack Language Models
The Backpack is a Transformer alternative shown to improve interpretability in English language modeling by decomposing predictions into a weighted sum of token sense components. However, Backpacks' reliance on token-def…
Language ModelingLanguage ModellingUnderstanding Higher-Order Correlations Among Semantic Components in Embeddings
Independent Component Analysis (ICA) offers interpretable semantic components of embeddings. While ICA theory assumes that embeddings can be linearly decomposed into independent components, real-world data often do not s…
Interpretable probabilistic embeddings: bridging the gap between topic models and neural networks
We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and …
Topic ModelsWord Similarity