Elamur Research⌕
☰
home / papers / 2026 / Link Prediction for Event Logs in the Process Industry

Link Prediction for Event Logs in the Process Industry

Paper · 2026 · Anastasia Zhukova, Thomas Walton, Christian E. Lobmüller et al.

Summary

Shift books in the process industry often split one incident across several log entries, for example when follow-up details are added later without being formally linked. This fragmentation weakens graph-based RAG tools, such as solution recommenders, which depend on well-connected records. The authors frame record linking as cross-document coreference resolution (CDCR) on German operational logs. In their mapping, a plant's logbook is the topic, a multi-day sliding window is the subtopic, an 8-hour shift is the document, and each log entry is a mention. Borrowing from natural language inference (NLI), they treat linked records as ordered premise–hypothesis chains rather than unordered clusters. The model has two stages: pairwise scoring of records, then clustering. It merges ideas from two CDCR systems: joint [CLS]-based encoding from CDLM and attribute-similarity features from Barhom et al. Built on a domain-adapted GBERT-base, it outperforms the strongest NLI and STS baselines by roughly 11 points. The work shows that standard NLP tasks can be repurposed to improve data connectivity in a low-resource industrial domain.

Key points

  • Record linking is defined as CDCR over passage-level mentions (sentences or short texts with timestamps and machine codes). Coreference chains are ordered and take three forms: P–H, P–H–…–H, or a singleton.
  • The architecture builds on earlier CDCR work by Bugert and Gurevych (2021) as well as Barhom et al. (2019). It encodes record pairs as [CLS] r1 [SEP] r2 [SEP] (following CDLM) and adds a feature vector based on record-attribute similarity.
  • The backbone is a domain-adapted GBERT-base for German process-industry text.
  • The model beats the best NLI baseline by 28% (11.43 points) and the best STS baseline by 27.4% (11.21 points).
  • The intended use is preprocessing (link prediction) to build knowledge graphs for RAG-based knowledge management at production sites.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of GöttingenGöttingen · Germany17 works · 158 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksDecision Sciences · 209 worksManagement Science and Operations Research · 108 works

Cite

Cite as Anastasia Zhukova, Thomas Walton, Christian E. Lobmüller and Bela Gipp. 2026. Link Prediction for Event Logs in the Process Industry. Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5jkczh48a2o9

@inproceedings{zhukova2026link,
  title = {{Link Prediction for Event Logs in the Process Industry}},
  author = {Anastasia Zhukova, Thomas Walton, Christian E. Lobmüller and Bela Gipp},
  booktitle = {Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)},
  year = {2026},
  doi = {10.63317/5jkczh48a2o9},
  url = {https://doi.org/10.63317/5jkczh48a2o9}
}

References

33 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Eneko Agirre, Mona Diab, Daniel Cer, and Aitor Gonzalez-Agirre. 2012. Semeval-2012 task 6: a pilot on semantic textual similarity. In Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the Main Conference and the Shared Task, and Volume 2: Pro…
  2. Gabor Angeli, Melvin Jose Johnson Premkumar, and Christopher D. Manning. 2015. Leveraging linguistic structure for open domain information extraction. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Lang…
  3. Mariam Barry, Gaetan Caillaut, Pierre Halftermeyer, Raheel Qader, Mehdi Mouayad, Fabrice Le Deit, Dimitri Cariolaro, and Joseph Gesnouin. 2025. GraphRAG: Leveraging graph-based efficiency to minimize hallucinations in LLM-driven RAG for finance data. In Proceedings of the Workshop on Generative AI a… find
  4. Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, Lisbon, Portugal. Association for Computati…
  5. Michael Bugert and Iryna Gurevych. 2021. Event coreference data (almost) for free: Mining hyperlinks from online news. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 471–491, Online and Punta Cana, Dominican Republic. Association for Computational Li…
  6. Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew Peters, Arie Cattan, and Ido Dagan. 2021. CDLM: Cross-document language modeling. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2648–2662, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  7. Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, and Ido Dagan. 2021a. Cross-document coreference resolution over predicted mentions. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5100– 5107, Online. Association for Computational Linguistics.
  8. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In In The First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference, pages 563–566.
  9. Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, and Ido Dagan. 2021b. Realistic evaluation principles for cross-document coreference resolution. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 143–151, Online. Association for Computatio…
  10. Shany Barhom, Vered hwartz, Alon Eirew, Michael Bugert, Nils Reimers, and Ido Dagan. 2019. Revisiting joint modeling of cross-document entity Branden Chan, Stefan Schweter, and Timo Möller. 2020. German’s next language model. CoRR, abs/2010.10906.
  11. Xinyu Chen, Peifeng Li, and Qiaoming Zhu. 2025. Employing discourse coherence enhancement to improve cross-document event and entity coreference resolution. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 23272–23286, Vienna,… find
  12. Alton Y.K. Chua. 2009. The dark side of successful knowledge management initiatives. Journal of Knowledge Management, 13(4):32–40. find
  13. Agata Cybulska and Piek Vossen. 2014. Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC‘14), pages 4545–4552, Reykjavik, Iceland. European Language Resources Associa…
  14. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  15. Alon Eirew, Arie Cattan, and Ido Dagan. 2021. WEC: Deriving a large-scale cross-document event coreference dataset from Wikipedia. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2498–2510, Onlin…
  16. Qiang Gao, Bobo Li, Zixiang Meng, Yunlong Li, Jun Zhou, Fei Li, Chong Teng, and Donghong Ji. 2024. Enhancing cross-document event coreference resolution by discourse structure and semantic information. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language R… find
  17. Yan Huang et al. 2000. Anaphora: A cross-linguistic approach. Oxford University Press on Demand. find
  18. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. Association for Computational Linguistics.
  19. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Proc…
  20. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 25–32, Vancouver, British Columbia, Canada. Association for Computational Linguistics.
  21. John Mayfield, Daniel Alexander, Bonnie J Dorr, Jason Eisner, Tarek Elsayed, Tim Finin, Christine Fink, Marc Freedman, Nikesh Garera, Paul McNamee, and Saif M Mohammad. 2009. Cross-document coreference resolution: A key technology for learning by reading. In AAAI Spring Symposium: Learning by Readin… find
  22. Abhijnan Nath, Huma Jamil, Shafiuddin Rehan Ahmed, George Arthur Baker, Rahul Ghosh, James H. Martin, Nathaniel Blanchard, and Nikhil Krishnaswamy. 2024. Multimodal cross-document event coreference resolution using linear semantic transfer and mixed-modality ensembles. In Proceedings of the 2024 Joi…
  23. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. Association for Computational Linguisti…
  24. M. Recasens and E. Hovy. 2011. Blanc: Implementing the rand index for coreference evaluation. Nat. Lang. Eng., 17(4):485–510. find
  25. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
  26. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Conference on Message Understanding, MUC6 ’95, page 45–52, USA. Association for Computational Linguistics.
  27. Xiaodong Yu, Wenpeng Yin, and Dan Roth. 2022. Pairwise representation learning for event coreference. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 69–78, Seattle, Washington. Association for Computational Linguistics.
  28. Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, and Xueqi Cheng. 2020. Event coreference resolution with their paraphrases and argument-aware embeddings. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3084–3094, Barcelona, Spain (Online). International C…
  29. Xin Zhang, Yanzhao Zhang, Dingkun Long, Wen Xie, Ziqi Dai, Jialong Tang, Huan Lin, Baosong Yang, Pengjun Xie, Fei Huang, Meishan Zhang, Wenjie Li, and Min Zhang. 2024. mGTE: Generalized long-context text representation and reranking models for multilingual text retrieval. In Proceedings of the 2024…
  30. Anastasia Zhukova, Felix Hamborg, Karsten Donnay, and Bela Gipp. 2021. Concept identification of directly and indirectly related mentions referring to groups of persons. In Diversity, Divergence, Dialogue, pages 514–526, Cham. Springer International Publishing. find
  31. Anastasia Zhukova, Christian E. Matt, and Bela Gipp. 2025a. Automated collection of evaluation dataset for semantic search in low-resource domain language. In Proceedings of the First Workshop on Language Models for Low-Resource Languages, pages 112–122, Abu Dhabi, United Arab Emirates. Association… find
  32. Anastasia Zhukova, Christian E. Matt, and Bela Gipp. 2025b. Efficient domain-adaptive continual pretraining for the process industry in the german language. In Text, Speech and Dialogue. Proceedings of the 28th International Conference TSD2025, Erlangen, Germany, August 2025, Cham. Springer Nature S… find
  33. Anastasia Zhukova, Lukas von Sperl, Christian E. Matt, and Bela Gipp. 2024. Generative user-experience research for developing domain-specific natural language processing applications. Knowledge and Information Systems, 66:7859–7889. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhukova-2026-link-prediction-event-logs-process/