AI Assistant for Process Plant Operations

CONTACT

LINKS

AI-based Decision Assistant for Process Plant Operations (ADAPPO or Plant Assistant in short) is an applied research project conducted as a collaboration between GippLab and eschbach GmbH funded by ZIM (Zentrales Innovationsprogramm Mittelstand) run by the German Ministry of Economic Affairs and Climate Action. The collaboration has already been recognized with multiple industry awards.

NLP-driven Plant Assistant aims to create a tool that supports plant operators in their daily operations in an industrial processing plant. The Plant Assistant aggregates knowledge and experience from logged plant operations and provides fast, efficient, and interactive feedback when users need solutions to encountered problems. A goal of the project is to leverage the recent advances in NLP to tailor language models towards domain-specific text data of multiple languages with uneven data quality, data scarcity, and lack of annotated sources.

Plant Assistant involves the following NLP research and tasks:

Domain adaptation of language models
Document encoders
Information extraction & linking
Text classification
Text summarization
Retrieval-augmented generation
Multi-agent problem solving

Check out our ongoing projects that are available as B.Sc./M.Sc. theses here.

Related Publications

1. Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language
  A. Zhukova, C. E. Matt, and B. Gipp
  Proceedings of the First Workshop on Language Models for Low-Resource Languages (LoResLM) co-located with the 31st International Conference on Computational Linguistics (COLING 2025), Abu Dhabi, the United Arab Emirates, 2025.
  PDF Poster
2. Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications
  A. Zhukova, L. von Sperl, C. E. Matt, and B. Gipp
  Knowledge and Information Systems, DOI 10.1007/s10115-024-02212-5, 2024
  PDF
3. ANEA: Automated (Named) Entity Annotation for German Domain-Specific Texts
  A. Zhukova, F. Hamborg, and B. Gipp
  in Proceedings of the 2nd Workshop on Extraction and Evaluation of Knowledge Entities from Scientific Documents (EEKE 2021) co-located with JCDL 2021, Virtual Event, Illinois, USA, 2021.
  PDF Slides