Feature analysis of sentence vectors by an image-generation model using Sentence-BERT
Masato Izumi, Kenya Jin’no · Nonlinear Theory and Its Applications IEICE · 2023
In this study, using k-means and UMAP, we verified that the sentence vectors generated by Sentence-BERT as distributed representations of sentences capture the meaning of sentences well. To this end, we visualized the sentence vectors by generating images matching the meaning of the sentence from the sentence vectors generated by Sentence-BERT. The results confirm that although there were differences in the information represented by each dimension as distributional features of the sentence vector, this information overlapped substantially.