@inproceedings{zhukova-etal-2026-link,
title = "Link Prediction for Event Logs in the Process Industry",
author = {Zhukova, Anastasia and
Walton, Thomas and
Lobm{\"u}ller, Christian E. and
Gipp, Bela},
editor = "Morger, Felix and
Ilinykh, Nikolai and
Scalvini, Barbara and
Dobnik, Simon and
Dann{\'e}lls, Dana",
booktitle = "Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models ({RESOURCEFUL} 2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.resourceful-4.11/",
doi = "10.63317/5jkczh48a2o9",
pages = "107--118",
abstract = "In the era of graph-based retrieval-augmented generation (RAG), link prediction is a significant preprocessing step for improving the quality of fragmented or incomplete domain-specific data for the graph retrieval. Knowledge management in the process industry uses RAG-based applications to optimize operations, ensure safety, and facilitate continuous improvement by effectively leveraging operational data and past insights. A key challenge in this domain is the fragmented nature of event logs in shift books, where related records are often kept separate, even though they belong to a single event or process. This fragmentation hinders the recommendation of previously implemented solutions to users, which is crucial in the timely problem-solving at live production sites. To address this problem, we develop a record linking model, which we define as a cross-document coreference resolution (CDCR) task. Record linking adapts the task definition of CDCR and combines two state-of-the-art CDCR models with the principles of natural language inference (NLI) and semantic text similarity (STS) to perform link prediction. The evaluation shows that our record linking model outperformed the best versions of our baselines, i.e., NLI and STS, by 28 (11.43 p) and 27.4 (11.21 p), respectively. Our work demonstrates that common NLP tasks can be combined and adapted to a domain-specific setting of the German process industry, improving data quality and connectivity in shift logs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhukova-etal-2026-link">
<titleInfo>
<title>Link Prediction for Event Logs in the Process Industry</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Zhukova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Walton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Lobmüller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Gipp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the era of graph-based retrieval-augmented generation (RAG), link prediction is a significant preprocessing step for improving the quality of fragmented or incomplete domain-specific data for the graph retrieval. Knowledge management in the process industry uses RAG-based applications to optimize operations, ensure safety, and facilitate continuous improvement by effectively leveraging operational data and past insights. A key challenge in this domain is the fragmented nature of event logs in shift books, where related records are often kept separate, even though they belong to a single event or process. This fragmentation hinders the recommendation of previously implemented solutions to users, which is crucial in the timely problem-solving at live production sites. To address this problem, we develop a record linking model, which we define as a cross-document coreference resolution (CDCR) task. Record linking adapts the task definition of CDCR and combines two state-of-the-art CDCR models with the principles of natural language inference (NLI) and semantic text similarity (STS) to perform link prediction. The evaluation shows that our record linking model outperformed the best versions of our baselines, i.e., NLI and STS, by 28 (11.43 p) and 27.4 (11.21 p), respectively. Our work demonstrates that common NLP tasks can be combined and adapted to a domain-specific setting of the German process industry, improving data quality and connectivity in shift logs.</abstract>
<identifier type="citekey">zhukova-etal-2026-link</identifier>
<identifier type="doi">10.63317/5jkczh48a2o9</identifier>
<location>
<url>https://aclanthology.org/2026.resourceful-4.11/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>107</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Link Prediction for Event Logs in the Process Industry
%A Zhukova, Anastasia
%A Walton, Thomas
%A Lobmüller, Christian E.
%A Gipp, Bela
%Y Morger, Felix
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Dobnik, Simon
%Y Dannélls, Dana
%S Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F zhukova-etal-2026-link
%X In the era of graph-based retrieval-augmented generation (RAG), link prediction is a significant preprocessing step for improving the quality of fragmented or incomplete domain-specific data for the graph retrieval. Knowledge management in the process industry uses RAG-based applications to optimize operations, ensure safety, and facilitate continuous improvement by effectively leveraging operational data and past insights. A key challenge in this domain is the fragmented nature of event logs in shift books, where related records are often kept separate, even though they belong to a single event or process. This fragmentation hinders the recommendation of previously implemented solutions to users, which is crucial in the timely problem-solving at live production sites. To address this problem, we develop a record linking model, which we define as a cross-document coreference resolution (CDCR) task. Record linking adapts the task definition of CDCR and combines two state-of-the-art CDCR models with the principles of natural language inference (NLI) and semantic text similarity (STS) to perform link prediction. The evaluation shows that our record linking model outperformed the best versions of our baselines, i.e., NLI and STS, by 28 (11.43 p) and 27.4 (11.21 p), respectively. Our work demonstrates that common NLP tasks can be combined and adapted to a domain-specific setting of the German process industry, improving data quality and connectivity in shift logs.
%R 10.63317/5jkczh48a2o9
%U https://aclanthology.org/2026.resourceful-4.11/
%U https://doi.org/10.63317/5jkczh48a2o9
%P 107-118
Markdown (Informal)
[Link Prediction for Event Logs in the Process Industry](https://aclanthology.org/2026.resourceful-4.11/) (Zhukova et al., RESOURCEFUL 2026)
ACL
- Anastasia Zhukova, Thomas Walton, Christian E. Lobmüller, and Bela Gipp. 2026. Link Prediction for Event Logs in the Process Industry. In Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026), pages 107–118, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).