MTSwitch: A Web-based System for Translation between Molecules and Texts

Nijia Han, Zimu Wang, Yuqi Wang, Haiyang Zhang, Daiyun Huang, Wei Wang*

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

We introduce MTSwitch, a web-based system for the bidirectional translation between molecules and texts, leveraging various large language models (LLMs). It supports two crucial tasks, including molecule captioning (explaining the properties of a molecule) and molecule generation (designing a molecule based on specific properties). To the best of our knowledge, MTSwitch is currently the first accessible system that allows users to translate between molecular representations and descriptive text contents. The system and a screen-cast can be found in https://github.com/hanninaa/MTSwitch.

Original languageEnglish
Title of host publicationINLG 2024 - 17th International Natural Language Generation Conference
Subtitle of host publicationSystem Demonstrations, Proceedings of the System Demonstrations
EditorsSaad Mahamood, Nguyen Le Minh, Daphne Ippolito
PublisherAssociation for Computational Linguistics (ACL)
Pages4-6
Number of pages3
ISBN (Electronic)9798891761230
DOIs
Publication statusPublished - 2024
Event17th International Natural Language Generation Conference, INLG 2024 - Tokyo, Japan
Duration: 23 Sept 202427 Sept 2024

Publication series

NameINLG 2024 - 17th International Natural Language Generation Conference: System Demonstrations, Proceedings of the System Demonstrations

Conference

Conference17th International Natural Language Generation Conference, INLG 2024
Country/TerritoryJapan
CityTokyo
Period23/09/2427/09/24

Cite this