Creating Linguistic Embedding Space for Odors

To obtain a genuine meaning for a natural language sentence, it is necessary to understand the connection between words in the language and various kinds of real-world information. One kind might be odors. Previous studies investigated whether word embeddings from word2vec can acquire odor information. However, their model, trained with general corpora, does not have much odor information due to the small volume of odor-related corpora for training. In this paper, we propose Thesaurus-enhanced Odor-adaptive Linguistic Embeddings (TOLE). TOLE retains odor information with domain adaptation and word-level contrastive learning on pre-trained language models. As a result, it can improve the similarity between odor embeddings from odor descriptors and linguistic embeddings.