Maxim Konca

@inbook{Mehler:et:al:2024:a,
  author    = {Mehler, Alexander and Bagci, Mevl{\"u}t and Schrottenbacher, Patrick
               and Henlein, Alexander and Konca, Maxim and Abrami, Giuseppe and B{\"o}nisch, Kevin
               and Stoeckel, Manuel and Spiekermann, Christian and Engel, Juliane},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  title     = {Towards New Data Spaces for the Study of Multiple Documents with
               Va.Si.Li-Lab: A Conceptual Analysis},
  booktitle = {Students', Graduates' and Young Professionals' Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  year      = {2024},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {259--303},
  abstract  = {The constitution of multiple documents has so far been studied
               essentially as a process in which a single learner consults a
               number (of segments) of different documents in the context of
               the task at hand in order to construct a mental model for the
               purpose of completing the task. As a result of this research focus,
               the constitution of multiple documents appears predominantly as
               a monomodal, non-interactive process in which mainly textual units
               are studied, supplemented by images, text-image relations and
               comparable artifacts. This approach is reflected in the contextual
               fixity of the research design, in which the learners under study
               search for information using suitably equipped computers. If,
               on the other hand, we consider the openness of multi-agent learning
               situations, this scenario lacks the aspects of interactivity,
               contextual openness and, above all, the multimodality of information
               objects, information processing and information exchange. This
               is where the chapter comes in. It describes Va.Si.Li-Lab as an
               instrument for multimodal measurement for studying and modeling
               multiple documents in the context of interactive learning in a
               multi-agent environment. To this end, the chapter places Va.Si.Li-Lab
               in the spectrum of evolutionary approaches that vary the combination
               of human and machine innovation and selection. It also combines
               the requirements of multimodal representational learning with
               various aspects of contextual plasticity to prepare Va.Si.Li-Lab
               as a system that can be used for experimental research. The chapter
               is conceptual in nature, designing a system of requirements using
               the example of Va.Si.Li-Lab to outline an experimental environment
               in which the study of Critical Online Reasoning (COR) as a group
               process becomes possible. Although the chapter illustrates some
               of these requirements with realistic data from the field of simulation-based
               learning, the focus is still conceptual rather than experimental,
               hypothesis-driven. That is, the chapter is concerned with the
               design of a technology for future research into COR processes.},
  isbn      = {978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0_12},
  url       = {https://doi.org/10.1007/978-3-031-69510-0_12}
}

@inbook{Konca:et:al:2024:a,
  author    = {Konca, Maxim and Mehler, Alexander and L{\"u}cking, Andy and Baumartz, Daniel},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  title     = {Visualizing Domain-specific and Generic Critical Online Reasoning
               Related Structures of Online Texts: A Hybrid Approach},
  booktitle = {Students', Graduates' and Young Professionals' Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  year      = {2024},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {195--239},
  abstract  = {Besides ``traditional'' educational media, young professionals
               in higher education use the Internet to obtain information. To
               utilize their online research in professional contexts, they critically
               evaluate the information they access and its sources. One dimension
               of this evaluation is an assessment of the linguistic state of
               the online sources, either implicitly or explicitly. This computational
               educational linguistic study applies methods from computational
               linguistics to online sources visited by young professionals from
               three fields (law students, teacher trainees, and medicine student)
               and develops partly novel visualizations that allow to quickly
               discover similarities as well as differences between multi-heterogeneous
               Internet sources, that is, sources that exhibit various topics,
               genres, and textual structure, among others. The visualizations
               also allow a comparison of search behaviour between different
               professional fields. In this way, we found that (1) genre classification
               has a significant impact on reliability scores, (2) young professionals'
               search approaches vary by their professional field, and, (3) the
               best predictor of reliability is indeed the linguistic profile
               of an online source.},
  isbn      = {978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0_10},
  url       = {https://doi.org/10.1007/978-3-031-69510-0_10}
}

@inproceedings{Baumartz:et:al:2024,
  author    = {Baumartz, Daniel and Konca, Maxim and Mehler, Alexander and Schrottenbacher, Patrick
               and Braunheim, Dominik},
  title     = {Measuring Group Creativity of Dialogic Interaction Systems by
               Means of Remote Entailment Analysis},
  year      = {2024},
  isbn      = {9798400705953},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3648188.3675140},
  doi       = {10.1145/3648188.3675140},
  abstract  = {We present a procedure for assessing group creativity that allows
               us to compare the contributions of human interlocutors and chatbots
               based on generative AI such as ChatGPT. We focus on everyday creativity
               in terms of dialogic communication and test four hypotheses about
               the difference between human and artificial communication. Our
               procedure is based on a test that requires interlocutors to cooperatively
               interpret a sequence of sentences for which we control for coherence
               gaps with reference to the notion of entailment. Using NLP methods,
               we automatically evaluate the spoken or written contributions
               of interlocutors (human or otherwise). The paper develops a routine
               for automatic transcription based on Whisper, for sampling texts
               based on their entailment relations, for analyzing dialogic contributions
               along their semantic embeddings, and for classifying interlocutors
               and interaction systems based on them. In this way, we highlight
               differences between human and artificial conversations under conditions
               that approximate free dialogic communication. We show that despite
               their obvious classificatory differences, it is difficult to see
               clear differences even in the domain of dialogic communication
               given the current instruments of NLP.},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  pages     = {153–-166},
  numpages  = {14},
  keywords  = {Creative AI, Creativity, Generative AI, Hermeneutics, NLP},
  location  = {Poznan, Poland},
  series    = {HT '24}
}

@inproceedings{Konca:et:al:2024,
  abstract  = {A useful semantic role-annotated resource for training semantic
               role models for the German language is missing. We point out some
               problems of previous resources and provide a new one due to a
               combined translation and alignment process: The gold standard
               CoNLL-2012 semantic role annotations are translated into German.
               Semantic role labels are transferred due to alignment models.
               The resulting dataset is used to train a German semantic role
               model. With F1-scores around 0.7, the major roles achieve competitive
               evaluation scores, but avoid limitations of previous approaches.
               The described procedure can be applied to other languages as well.},
  address   = {Torino, Italy},
  author    = {Konca, Maxim and L{\"u}cking, Andy and Mehler, Alexander},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational
               Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro
               and Sakti, Sakriani and Xue, Nianwen},
  month     = {may},
  pages     = {7717--7727},
  publisher = {ELRA and ICCL},
  title     = {{G}erman {SRL}: Corpus Construction and Model Training},
  url       = {https://aclanthology.org/2024.lrec-main.682},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/05/LREC_2024_Poster_GERMAN_SRL.pdf},
  year      = {2024}
}

@inproceedings{Mehler:et:al:2023:a,
  abstract  = {Simulation-based learning is a method in which learners learn
               to master real-life scenarios and tasks from simulated application
               contexts. It is particularly suitable for the use of VR technologies,
               as these allow immersive experiences of the targeted scenarios.
               VR methods are also relevant for studies on online learning, especially
               in groups, as they provide access to a variety of multimodal learning
               and interaction data. However, VR leads to a trade-off between
               technological conditions of the observability of such data and
               the openness of learner behavior. We present Va.Si.Li-Lab, a VR-L
               ab for Simulation-based Learn ing developed to address this trade-off.
               Va.Si.Li-Lab uses a graph-theoretical model based on hypergraphs
               to represent the data diversity of multimodal learning and interaction.
               We develop this data model in relation to mono- and multimodal,
               intra- and interpersonal data and interleave it with ISO-Space
               to describe distributed multiple documents from the perspective
               of their interactive generation. The paper adds three use cases
               to motivate the broad applicability of Va.Si.Li-Lab and its data
               model.},
  address   = {Cham},
  author    = {Mehler, Alexander and Bagci, Mevl{\"u}t and Henlein, Alexander
               and Abrami, Giuseppe and Spiekermann, Christian and Schrottenbacher, Patrick
               and Konca, Maxim and L{\"u}cking, Andy and Engel, Juliane and Quintino, Marc
               and Schreiber, Jakob and Saukel, Kevin and Zlatkin-Troitschanskaia, Olga},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management},
  editor    = {Duffy, Vincent G.},
  isbn      = {978-3-031-35741-1},
  pages     = {539--565},
  publisher = {Springer Nature Switzerland},
  title     = {A Multimodal Data Model for Simulation-Based Learning with Va.Si.Li-Lab},
  year      = {2023},
  doi       = {10.1007/978-3-031-35741-1_39}
}

@misc{Konca:et:al:2022,
  author    = {Konca, Maxim and L{\"u}cking, Andy and Mehler, Alexander and Nagel, Marie-Theres
               and Zlatkin-Troitschanskaia, Olga},
  howpublished = {Presentation given at the AERA annual meeting, 21.-26.04. 2022, WERA symposium},
  month     = {04},
  title     = {Computational educational linguistics for `Critical Online Reasoning'
               among young professionals in medicine, law and teaching},
  year      = {2022},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2022/10/BRIDGE_WERA_AERA-2022_reduce.pdf}
}

@misc{Mehler:et:al:2022,
  author    = {Mehler, Alexander and Konca, Maxim and Nagel, Marie-Theres and L\"{u}cking, Andy
               and Zlatkin-Troitschanskaia, Olga},
  year      = {2022},
  month     = {03},
  howpublished = {Presentation at BEBF 2022},
  title     = {On latent domain-specific textual preferences in solving Internet-based
               generic tasks among graduates/young professionals from three domains},
  abstract  = {Although Critical Online Reasoning (COR) is often viewed as a
               general competency (e.g. Alexander et al. 2016), studies have
               found evidence supporting their domain-specificity (Toplak et
               al. 2002). To investigate this assumption, we focus on commonalities
               and differences in textual preferences in solving COR-related
               tasks between graduates/young professionals from three domains.
               For this reason, we collected data by requiring participants to
               solve domain-specific (DOM-COR) and generic (GEN-COR) tasks in
               an authentic Internet-based COR performance assessment (CORA),
               allowing us to disentangle the assumed components of COR abilities.
               Here, we focus on GEN-COR to distinguish between different groups
               of graduates from the three disciplines in the context of generic
               COR tasks. We present a computational model for educationally
               relevant texts that combines features at multiple levels (lexical,
               syntactic, semantic). We use machine learning to predict domain-specific
               group membership based on documents consulted during task solving.
               A major contribution of our analyses is a multi-part text classification
               system that contrasts human annotation and rating of the documents
               used with a semi-automatic classification to predict the document
               type of web pages. That is, we work with competing classifications
               to support our findings. In this way, we develop a computational
               linguistic model that correlates GEN-COR abilities with properties
               of documents consulted for solving the GEN-COR tasks. Results
               show that participants from different domains indeed inquire different
               sets of online sources for the same task. Machine learning-based
               classifications show that the distributional differences can be
               reproduced by computational linguistic models.},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2022/04/On_latent_domain-specific_textual_preferences_in_solving_Internet-based_generic_tasks_among_graduates__young_professionals_from_three_domains.pdf}
}

@article{Konca:et:al:2021,
  title     = {From distinguishability to informativity. A quantitative text
               model for detecting random texts.},
  author    = {Konca, Maxim and Mehler, Alexander and Baumartz, Daniel and Hemati, Wahed},
  journal   = {Language and Text: Data, models, information and applications},
  volume    = {356},
  pages     = {145--162},
  year      = {2021},
  editor    = {Adam Paw{\l}owski, Jan Ma{\v{c}}utek, Sheila Embleton and George Mikros},
  publisher = {John Benjamins Publishing Company},
  doi       = {10.1075/cilt.356.10kon}
}

@article{Mehler:Hemati:Welke:Konca:Uslu:2020,
  abstract  = {We test the hypothesis that the extent to which one obtains information
               on a given topic through Wikipedia depends on the language in
               which it is consulted. Controlling the size factor, we investigate
               this hypothesis for a number of 25 subject areas. Since Wikipedia
               is a central part of the web-based information landscape, this
               indicates a language-related, linguistic bias. The article therefore
               deals with the question of whether Wikipedia exhibits this kind
               of linguistic relativity or not. From the perspective of educational
               science, the article develops a computational model of the information
               landscape from which multiple texts are drawn as typical input
               of web-based reading. For this purpose, it develops a hybrid model
               of intra- and intertextual similarity of different parts of the
               information landscape and tests this model on the example of 35
               languages and corresponding Wikipedias. In the way it measures
               the similarities of hypertexts, the article goes beyond existing
               approaches by examining their structural and semantic aspects
               intra- and intertextually. In this way it builds a bridge between
               reading research, educational science, Wikipedia research and
               computational linguistics.},
  author    = {Mehler, Alexander and Hemati, Wahed and Welke, Pascal and Konca, Maxim
               and Uslu, Tolga},
  doi       = {10.3389/feduc.2020.562670},
  issn      = {2504-284X},
  journal   = {Frontiers in Education},
  pages     = {206},
  title     = {Multiple Texts as a Limiting Factor in Online Learning: Quantifying
               (Dis-)similarities of Knowledge Networks},
  url       = {https://www.frontiersin.org/article/10.3389/feduc.2020.562670},
  pdf       = {https://www.frontiersin.org/articles/10.3389/feduc.2020.562670/pdf},
  volume    = {5},
  year      = {2020}
}