About Us

MatExt was developed by materials researchers together with experts in natural language processing (NLP). It is based on QA information extraction methodology and a text corpus developed through this collaboration in the national project DeeperMaterials.

Collaborating Groups

• Materials Informatics Laboratory (Department of Mechanical and Materials Engineering), University of Turku.
• TurkuNLP (Department of Computing), University of Turku.

People

• Henri Haapanen - main app developer, code design, and implementation
• Matilda Sipilä - author of QA MatSciBERT, tool design, and guidance
• Tomasz Galica - discussion, ideas and suggestions
• Filip Ginter - tool design and guidance
• Milica Todorović - tool design and guidance

Acknowledgements

This tool was supported by:

• Research Council of Finland, with funding through project "Deep Representation Learning and Literature Mining for Materials Discovery (DeeperMaterials)”, grant no. 34569 (2022–2024). PIs: Sampo Pyysalo, Milica Todorović.
• CSC-IT Center for Science Finland, with computational resources through project no. 2006183 “DeeperMaterials: Natural Language Processing for Materials Discovery.”

Citation

Question Answering Models for Information Extraction from Perovskite Materials Science Literature
M. Sipilä, F. Mehryary, S. Pyysalo, F. Ginter, Milica Todorović
arXiv:2405.15290 (2024)

@article{Sipila2024,
  title = {Question Answering Models for Information Extraction from Perovskite Materials Science Literature},
  author = {M. Sipilä and F. Mehryary and S. Pyysalo and F. Ginter and Milica Todorović},
  journal = {arXiv},
  year = {2024},
  eprint = {2405.15290},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2405.15290}
}