@article{wangbeyond,

title = {Beyond Pareto Analysis: A Decision Support Model for the Prioritization of Deviations with Natural Language Processing},

author = {Yuxi Wang and Lukas Longard and Christian Hertle and Joachim Metternich},

year  = {2023},

date = {2023-03-02},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MULLER2022179,

title = {Comparison of preprocessing approaches for text data in digital shop floor management systems},

author = {Marvin Müller and Lukas Longard and Joachim Metternich},

url = {https://www.sciencedirect.com/science/article/pii/S2212827122002463},

doi = {https://doi.org/10.1016/j.procir.2022.04.030},

issn = {2212-8271},

year  = {2022},

date = {2022-01-01},

journal = {Procedia CIRP},

volume = {107},

pages = {179-184},

abstract = {In an increasing number of production companies shop floor management (SFM) is supported by digital systems. The data generated while working with these systems can be used for assistance systems to further enhance the value of digital SFM. Several assistance systems using text data from problem-solving processes have been suggested but had limited quality due to the domain specific language characteristics: short texts with spelling errors and the usage of synonyms. This research aims to quantify the improvement potentials of different preprocessing approaches on the quality of the assistance systems. For that and for comparison in the research community a public, labeled data set is needed. This paper introduces such a data set based on the characteristics identified in three real industry data sets. To overcome the problems in text processing of shop floor data (e.g. domain specific synonyms), several approaches are suggested, tested, and compared to a generic approach for text clustering. The study identifies best practices for the handling of shop floor text data and provides a data set with the goal of simplifying and stimulating research on this topic.},

note = {Leading manufacturing systems transformation – Proceedings of the 55th CIRP Conference on Manufacturing Systems 2022},

keywords = {:text mining, data quality improvement, natural language processing},

pubstate = {published},

tppubtype = {article}

}

@article{10.1162/coli_a_00436,

title = {Annotation Curricula to Implicitly Train Non-Expert 

 Annotators},

author = {Ji-Ung Lee and Jan-Christoph Klie and Iryna Gurevych},

url = {https://doi.org/10.1162/coli_a_00436},

doi = {10.1162/coli_a_00436},

issn = {0891-2017},

year  = {2022},

date = {2022-01-01},

journal = {Computational Linguistics},

volume = {48},

number = {2},

pages = {343-373},

abstract = {Annotation studies often require annotators to familiarize themselves with the 

 task, its annotation scheme, and the data domain. This can be overwhelming in 

 the beginning, mentally taxing, and induce errors into the resulting 

 annotations; especially in citizen science or crowdsourcing scenarios where 

 domain expertise is not required. To alleviate these issues, this work proposes 

 annotation curricula, a novel approach to implicitly train annotators. The goal 

 is to gradually introduce annotators into the task by ordering instances to be 

 annotated according to a learning curriculum. To do so, this work formalizes 

 annotation curricula for sentence- and paragraph-level annotation tasks, defines 

 an ordering strategy, and identifies well-performing heuristics and 

 interactively trained models on three existing English datasets. Finally, we 

 provide a proof of concept for annotation curricula in a carefully designed user 

 study with 40 voluntary participants who are asked to identify the most fitting 

 misconception for English tweets about the Covid-19 pandemic. The results 

 indicate that using a simple heuristic to order instances can already 

 significantly reduce the total annotation time while preserving a high 

 annotation quality. Annotation curricula thus can be a promising research 

 direction to improve data collection. To facilitate future research—for 

 instance, to adapt annotation curricula to specific tasks and expert annotation 

 scenarios—all code and data from the user study consisting of 2,400 

 annotations is made available.1},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{glockner2022missing,

title = {Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation},

author = {Max Glockner and Yufang Hou and Iryna Gurevych},

year  = {2022},

date = {2022-01-01},

journal = {arXiv preprint arXiv:2210.13865},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bigoulaeva2022effective,

title = {Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5},

author = {Irina Bigoulaeva and Rachneet Sachdeva and Harish Tayyar Madabushi and Aline Villavicencio and Iryna Gurevych},

year  = {2022},

date = {2022-01-01},

journal = {arXiv preprint arXiv:2210.17301},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lee2022annotation,

title = {Annotation Curricula to Implicitly Train Non-Expert Annotators},

author = {Ji-Ung Lee and Jan-Christoph Klie and Iryna Gurevych},

year  = {2022},

date = {2022-01-01},

journal = {Computational Linguistics},

volume = {48},

number = {2},

pages = {343–373},

publisher = {MIT Press One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA~…},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{baumgartner2022ukp,

title = {UKP-SQUARE: An Online Platform for Question Answering Research},

author = {Tim Baumgärtner and Kexin Wang and Rachneet Sachdeva and Max Eichler and Gregor Geigle and Clifton Poth and Hannah Sterz and Haritz Puerto and Leonardo FR Ribeiro and Jonas Pfeiffer and others},

year  = {2022},

date = {2022-01-01},

journal = {arXiv preprint arXiv:2203.13693},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{article,

title = {Assistenzsysteme durch Natural Language Processing - Umsetzungsstrategien für den Shopfloor},

author = {Marvin Müller and Joachim Metternich},

doi = {10.30844/I40M_21-6_S11-14},

year  = {2021},

date = {2021-01-01},

journal = {Industrie 4.0 Management},

volume = {2021},

pages = {11-14},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{articleb,

title = {Production specific language characteristics to improve NLP applications on the shop floor},

author = {Marvin Müller and Joachim Metternich},

doi = {10.1016/j.procir.2021.11.319},

year  = {2021},

date = {2021-01-01},

journal = {Procedia CIRP},

volume = {104},

pages = {1890-1895},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{articlec,

title = {Extracting problem related entities from production chats to enhance the data base for assistance functions on the shop floor},

author = {Marvin Müller and Ji-Ung Lee and Nicholas Frick and Lorenz Stangier and Iryna Gurevych and Joachim Metternich},

doi = {10.1016/j.procir.2021.10.037},

year  = {2021},

date = {2021-01-01},

journal = {Procedia CIRP},

volume = {103},

pages = {231-236},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{articled,

title = {Digital shop floor management enhanced by natural language processing},

author = {Marvin Müller and Emanuel Alexandi and Joachim Metternich},

doi = {10.1016/j.procir.2021.01.046},

year  = {2021},

date = {2021-01-01},

journal = {Procedia CIRP},

volume = {96},

pages = {21-26},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Müller2020,

title = {Chats als Datengrundlage für KIAnwendungen in der Produktion},

author = {Marvin Müller and Nicholas Frick and Ji-Ung Lee and Joachim Metternich and Iryna Gurevych},

doi = {10.3139/104.112360},

issn = {2511-0896},

year  = {2020},

date = {2020-07-01},

volume = {115},

number = {7-8},

pages = {520--523},

publisher = {Walter de Gruyter GmbH},

keywords = {General Engineering, Management Science and Operations Research, Strategy and Management},

pubstate = {published},

tppubtype = {article}

}

@article{articlee,

title = {Knowledge management on the shop floor through recommender engines},

author = {Marvin Müller and Georgi Terziev and Joachim Metternich and Nils Landmann},

doi = {10.1016/j.promfg.2020.11.057},

year  = {2020},

date = {2020-01-01},

journal = {Procedia Manufacturing},

volume = {52},

pages = {344-349},

keywords = {},

pubstate = {published},

tppubtype = {article}

}