We present MolT5− a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. MolT5 allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since MolT5 pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation. Our results show that MolT5-based models are able to generate outputs, both molecules and captions, which in many cases are high quality.
@article{arxiv.2204.11817,
title = {Translation between Molecules and Natural Language},
author = {Carl Edwards and Tuan Lai and Kevin Ros and Garrett Honke and Kyunghyun Cho and Heng Ji},
journal= {arXiv preprint arXiv:2204.11817},
year = {2022}
}
Comments
Accepted at EMNLP 2022. Data and code can be found on [Github](https://github.com/blender-nlp/MolT5)