paper-with-me

Papers

Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test

2022-12-19 · Tomáš Musil, David Mareček

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.

📄 PDF Abstract BibTeX arXiv:2212.09580

Code (0)

등록된 구현이 없습니다.

Tasks

Word Embeddings

Methods 이 논문이 사용한 방법론

ICA _Independent component analysis (ICA) is a statistical and computational technique for revealing hidden factors that underlie sets of random variables, measurements, or…

Similar Papers 제목 키워드 기반

Exploring Intra and Inter-language Consistency in Embeddings with ICA

2024-06-18 · Rongzhi Li, Takeru Matsuda, Hitomi Yanaka

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 Embeddings

Rotations and Interpretability of Word Embeddings: the Case of the Russian Language

2017-07-14 · Alexey Zobnin

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 Embeddings

Character-level Chinese Backpack Language Models

2023-10-19 · Hao Sun, John Hewitt

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 Modelling

Understanding Higher-Order Correlations Among Semantic Components in Embeddings

2024-09-30 · Momose Oyama, Hiroaki Yamagiwa, Hidetoshi Shimodaira

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

2017-11-11 · Anna Potapenko, Artem Popov, Konstantin Vorontsov

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