تقرير
Translation between Molecules and Natural Language
العنوان: | Translation between Molecules and Natural Language |
---|---|
المؤلفون: | Edwards, Carl, Lai, Tuan, Ros, Kevin, Honke, Garrett, Cho, Kyunghyun, Ji, Heng |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
الوصف: | We present $\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. $\textbf{MolT5}$ 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 $\textbf{MolT5}$ 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 $\textbf{MolT5}$-based models are able to generate outputs, both molecules and captions, which in many cases are high quality. Comment: Accepted at EMNLP 2022. Data and code can be found on [Github](https://github.com/blender-nlp/MolT5) |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2204.11817 |
رقم الأكسشن: | edsarx.2204.11817 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |