Embedding Font Impression Word Tags Based on Co-occurrence

Different font styles (i.e., font shapes) convey distinct im-pressions, indicating a close relationship between font shapes and word tags describing those impressions. This paper proposes a novel embedding method for impression tags that leverages these shape-impression relationships. For instance, our method assigns similar vectors to impres-sion tags that frequently co-occur in order to represent im-pressions of fonts, whereas standard word embedding meth-ods (e.g., BERT and CLIP) yield very different vectors. This property is particularly useful for impression-based font generation and font retrieval. Technically, we construct a graph whose nodes represent impression tags and whose edges encode co-occurrence relationships. Then, we apply spectral embedding to obtain the impression vectors for each tag. We compare our method with BERT and CLIP in qualitative and quantitative evaluations, demonstrating that our approach performs better in impression-guided font generation.