Dr. Alexander Henlein

@inproceedings{Henlein:et:al:2024-vicom,
  title     = {An Outlook for AI Innovation in Multimodal Communication Research},
  author    = {Henlein, Alexander and Bauer, Anastasia and Bhattacharjee, Reetu
               and Ćwiek, Aleksandra and Gregori, Alina and Kügler, Frank and Lemanski, Jens
               and Lücking, Andy and Mehler, Alexander and Prieto, Pilar and Sánchez-Ramón, Paula G.
               and Schepens, Job and Schulte-Rüther, Martin and Schweinberger, Stefan R.
               and von Eiff, Celina I.},
  keywords  = {own,conference},
  author+an = {8=highlight},
  editor    = {Duffy, Vincent G.},
  year      = {2024},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management.},
  series    = {HCII 2024. Lecture Notes in Computer Science},
  publisher = {Springer},
  address   = {Cham},
  pubstate  = {inpress},
  note      = {Forthcoming}
}

@inproceedings{Luecking:Mehler:Henlein:2024-classifier,
  title     = {The Linguistic Interpretation of Non-emblematic Gestures Must
               be agreed in Dialogue: Combining Perceptual Classifiers and Grounding/Clarification
               Mechanisms},
  author    = {Lücking, Andy and Mehler, Alexander and Henlein, Alexander},
  year      = {2024},
  booktitle = {Proceedings of the 28th Workshop on The Semantics and Pragmatics of Dialogue},
  series    = {SemDial'24 -- TrentoLogue},
  location  = {Università di Trento, Palazzo Piomarta, Rovereto}
}

@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}
}

@inproceedings{Henlein:et:al:2023b,
  author    = {Henlein, Alexander and Kett, Attila and Baumartz, Daniel and Abrami, Giuseppe
               and Mehler, Alexander and Bastian, Johannes and Blecher, Yannic and Budgenhagen, David
               and Christof, Roman and Ewald, Tim-Oliver and Fauerbach, Tim and Masny, Patrick
               and Mende, Julian and Schn{\"u}re, Paul and Viel, Marc},
  editor    = {Duffy, Vincent G.},
  title     = {Semantic Scene Builder: Towards a Context Sensitive Text-to-3D Scene Framework},
  booktitle = {Digital Human Modeling and Applications in Health, Safety, Ergonomics
               and Risk Management},
  year      = {2023},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {461--479},
  abstract  = {We introduce Semantic Scene Builder (SeSB), a VR-based text-to-3D
               scene framework using SemAF (Semantic Annotation Framework) as
               a scheme for annotating discourse structures. SeSB integrates
               a variety of tools and resources by using SemAF and UIMA as a
               unified data structure to generate 3D scenes from textual descriptions.
               Based on VR, SeSB allows its users to change annotations through
               body movements instead of symbolic manipulations: from annotations
               in texts to corrections in editing steps to adjustments in generated
               scenes, all this is done by grabbing and moving objects. We evaluate
               SeSB in comparison with a state-of-the-art open source text-to-scene
               method (the only one which is publicly available) and find that
               our approach not only performs better, but also allows for modeling
               a greater variety of scenes.},
  isbn      = {978-3-031-35748-0},
  doi       = {10.1007/978-3-031-35748-0_32}
}

@article{Henlein:et:al:2023a,
  author    = {Henlein, Alexander and Gopinath, Anju and Krishnaswamy, Nikhil
               and Mehler, Alexander and Pustejovsky, James},
  doi       = {10.3389/frai.2023.1084740},
  issn      = {2624-8212},
  journal   = {Frontiers in Artificial Intelligence},
  title     = {Grounding human-object interaction to affordance behavior in multimodal datasets},
  url       = {https://www.frontiersin.org/articles/10.3389/frai.2023.1084740},
  volume    = {6},
  year      = {2023}
}

@phdthesis{Henlein:2023,
  author    = {Alexander Henlein},
  title     = {Toward context-based text-to-3D scene generation},
  type      = {doctoralthesis},
  pages     = {199},
  school    = {Johann Wolfgang Goethe-Universität},
  doi       = {10.21248/gups.73448},
  year      = {2023},
  pdf       = {https://publikationen.ub.uni-frankfurt.de/files/73448/main.pdf}
}

@inproceedings{Abrami:et:al:2023,
  author    = {Abrami, Giuseppe and Mehler, Alexander and Bagci, Mevl\"{u}t and Schrottenbacher, Patrick
               and Henlein, Alexander and Spiekermann, Christian and Engel, Juliane
               and Schreiber, Jakob},
  title     = {Va.Si.Li-Lab as a Collaborative Multi-User Annotation Tool in
               Virtual Reality and Its Potential Fields of Application},
  year      = {2023},
  isbn      = {9798400702327},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3603163.3609076},
  doi       = {10.1145/3603163.3609076},
  abstract  = {During the last thirty years a variety of hypertext approaches
               and virtual environments -- some virtual hypertext environments
               -- have been developed and discussed. Although the development
               of virtual and augmented reality technologies is rapid and improving,
               and many technologies can be used at affordable conditions, their
               usability for hypertext systems has not yet been explored. At
               the same time, even for virtual three-dimensional virtual and
               augmented environments, there is no generally accepted concept
               that is similar or nearly as elegant as hypertext. This gap will
               have to be filled in the next years and a good concept should
               be developed; in this article we aim to contribute in this direction
               and also introduce a prototype for a possible implementation of
               criteria for virtual hypertext simulations.},
  booktitle = {Proceedings of the 34th ACM Conference on Hypertext and Social Media},
  articleno = {22},
  numpages  = {9},
  keywords  = {VaSiLiLab, virtual hypertext, virtual reality, virtual reality simulation, authoring system},
  location  = {Rome, Italy},
  series    = {HT '23},
  pdf       = {https://dl.acm.org/doi/pdf/10.1145/3603163.3609076}
}

@inproceedings{Henlein:et:al:2023c,
  title     = {Towards grounding multimodal semantics in interaction data with Va.Si.Li-Lab},
  author    = {Henlein, Alexander and Lücking, Andy and Bagci, Mevlüt and Mehler, Alexander},
  booktitle = {Proceedings of the 8th Conference on Gesture and Speech in Interaction (GESPIN)},
  location  = {Nijmegen, Netherlands},
  year      = {2023},
  keywords  = {vasililab},
  pdf       = {https://www.gespin2023.nl/documents/talks_and_posters/GeSpIn_2023_papers/GeSpIn_2023_paper_1692.pdf}
}

@inproceedings{Henlein:Mehler:2022,
  title     = {What do Toothbrushes do in the Kitchen? How Transformers Think
               our World is Structured},
  author    = {Henlein, Alexander and Mehler, Alexander},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter
               of the Association for Computational Linguistics: Human Language
               Technologies},
  year      = {2022},
  address   = {Seattle, United States},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2022.naacl-main.425},
  doi       = {10.18653/v1/2022.naacl-main.425},
  pages     = {5791--5807},
  abstract  = {Transformer-based models are now predominant in NLP.They outperform
               approaches based on static models in many respects. This success
               has in turn prompted research that reveals a number of biases
               in the language models generated by transformers. In this paper
               we utilize this research on biases to investigate to what extent
               transformer-based language models allow for extracting knowledge
               about object relations (X occurs in Y; X consists of Z; action
               A involves using X).To this end, we compare contextualized models
               with their static counterparts. We make this comparison dependent
               on the application of a number of similarity measures and classifiers.
               Our results are threefold:Firstly, we show that the models combined
               with the different similarity measures differ greatly in terms
               of the amount of knowledge they allow for extracting. Secondly,
               our results suggest that similarity measures perform much worse
               than classifier-based approaches. Thirdly, we show that, surprisingly,
               static models perform almost as well as contextualized models
               {--} in some cases even better.}
}

@inproceedings{Abrami:et:al:2021,
  author    = {Abrami, Giuseppe and Henlein, Alexander and Lücking, Andy and Kett, Attila
               and Adeberg, Pascal and Mehler, Alexander},
  title     = {Unleashing annotations with {TextAnnotator}: Multimedia, multi-perspective
               document views for ubiquitous annotation},
  booktitle = {Proceedings of the 17th Joint ACL - ISO Workshop on Interoperable
               Semantic Annotation},
  series    = {ISA-17},
  publisher = {Association for Computational Linguistics},
  address   = {Groningen, The Netherlands (online)},
  month     = {June},
  editor    = {Bunt, Harry},
  year      = {2021},
  url       = {https://aclanthology.org/2021.isa-1.7},
  pages     = {65--75},
  keywords  = {textannotator},
  pdf       = {https://iwcs2021.github.io/proceedings/isa/pdf/2021.isa-1.7.pdf},
  abstract  = {We argue that mainly due to technical innovation in the landscape
               of annotation tools, a conceptual change in annotation models
               and processes is also on the horizon. It is diagnosed that these
               changes are bound up with multi-media and multi-perspective facilities
               of annotation tools, in particular when considering virtual reality
               (VR) and augmented reality (AR) applications, their potential
               ubiquitous use, and the exploitation of externally trained natural
               language pre-processing methods. Such developments potentially
               lead to a dynamic and exploratory heuristic construction of the
               annotation process. With TextAnnotator an annotation suite is
               introduced which focuses on multi-mediality and multi-perspectivity
               with an interoperable set of task-specific annotation modules
               (e.g., for word classification, rhetorical structures, dependency
               trees, semantic roles, and more) and their linkage to VR and mobile
               implementations. The basic architecture and usage of TextAnnotator
               is described and related to the above mentioned shifts in the
               field.}
}

@inproceedings{Klement:et:al:2021,
  author    = {Klement, Mark and Henlein, Alexander and Mehler, Alexander},
  title     = {VoxML Annotation Tool Review and Suggestions for Improvement},
  booktitle = {Proceedings of the Seventeenth Joint ACL - ISO Workshop on Interoperable
               Semantic Annotation (ISA-17, Note for special track on visual
               information annotation)},
  series    = {ISA-17},
  location  = {Groningen, Netherlands},
  month     = {June},
  year      = {2021},
  pdf       = {https://sigsem.uvt.nl/isa17/32_Klement-Paper.pdf}
}

@incollection{Henlein:et:al:2021,
  author    = {Alexander Henlein and Giuseppe Abrami and Attila Kett and Christian Spiekermann
               and Alexander Mehler},
  title     = {Digital Learning, Teaching and Collaboration in an Era of ubiquitous Quarantine},
  editor    = {Linda Daniela and Anna Visvizin},
  booktitle = {Remote Learning in Times of Pandemic - Issues, Implications and Best Practice},
  publisher = {Routledge},
  address   = {Thames, Oxfordshire, England, UK},
  year      = {2021},
  chapter   = {3}
}

@inproceedings{Henlein:Mehler:2020,
  author    = {Henlein, Alexander and Mehler, Alexander},
  title     = {{On the Influence of Coreference Resolution on Word Embeddings
               in Lexical-semantic Evaluation Tasks}},
  booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference},
  month     = {May},
  year      = {2020},
  address   = {Marseille, France},
  publisher = {European Language Resources Association},
  pages     = {27--33},
  abstract  = {Coreference resolution (CR) aims to find all spans of a text that
               refer to the same entity. The F1-Scores on these task have been
               greatly improved by new developed End2End-approaches and transformer
               networks. The inclusion of CR as a pre-processing step is expected
               to lead to improvements in downstream tasks. The paper examines
               this effect with respect to word embeddings. That is, we analyze
               the effects of CR on six different embedding methods and evaluate
               them in the context of seven lexical-semantic evaluation tasks
               and instantiation/hypernymy detection. Especially in the last
               tasks we hoped for a significant increase in performance. We show
               that all word embedding approaches do not benefit significantly
               from pronoun substitution. The measurable improvements are only
               marginal (around 0.5\% in most test cases). We explain this result
               with the loss of contextual information, reduction of the relative
               occurrence of rare words and the lack of pronouns to be replaced.},
  url       = {https://www.aclweb.org/anthology/2020.lrec-1.4},
  pdf       = {http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.4.pdf}
}

@inproceedings{Henlein:et:al:2020,
  author    = {Henlein, Alexander and Abrami, Giuseppe and Kett, Attila and Mehler, Alexander},
  title     = {Transfer of ISOSpace into a 3D Environment for Annotations and Applications},
  booktitle = {Proceedings of the 16th Joint ACL - ISO Workshop on Interoperable
               Semantic Annotation},
  month     = {May},
  year      = {2020},
  address   = {Marseille},
  publisher = {European Language Resources Association},
  pages     = {32--35},
  abstract  = {People's visual perception is very pronounced and therefore it
               is usually no problem for them to describe the space around them
               in words. Conversely, people also have no problems imagining a
               concept of a described space. In recent years many efforts have
               been made to develop a linguistic concept for spatial and spatial-temporal
               relations. However, the systems have not really caught on so far,
               which in our opinion is due to the complex models on which they
               are based and the lack of available training data and automated
               taggers. In this paper we describe a project to support spatial
               annotation, which could facilitate annotation by its many functions,
               but also enrich it with many more information. This is to be achieved
               by an extension by means of a VR environment, with which spatial
               relations can be better visualized and connected with real objects.
               And we want to use the available data to develop a new state-of-the-art
               tagger and thus lay the foundation for future systems such as
               improved text understanding for Text2Scene.},
  url       = {https://www.aclweb.org/anthology/2020.isa-1.4},
  pdf       = {http://www.lrec-conf.org/proceedings/lrec2020/workshops/ISA16/pdf/2020.isa-1.4.pdf}
}

@article{Mehler:et:al:2020b,
  author    = {Mehler, Alexander and Jussen, Bernhard and Geelhaar, Tim and Henlein, Alexander
               and Abrami, Giuseppe and Baumartz, Daniel and Uslu, Tolga and Hemati, Wahed},
  title     = {{The Frankfurt Latin Lexicon. From Morphological Expansion and
               Word Embeddings to SemioGraphs}},
  journal   = {Studi e Saggi Linguistici},
  doi       = {10.4454/ssl.v58i1.276},
  year      = {2020},
  volume    = {58},
  number    = {1},
  pages     = {121--155},
  abstract  = {In this article we present the Frankfurt Latin Lexicon (FLL),
               a lexical resource for Medieval Latin that is used both for the
               lemmatization of Latin texts and for the post-editing of lemmatizations.
               We describe recent advances in the development of lemmatizers
               and test them against the Capitularies corpus (comprising Frankish
               royal edicts, mid-6th to mid-9th century), a corpus created as
               a reference for processing Medieval Latin. We also consider the
               post-correction of lemmatizations using a limited crowdsourcing
               process aimed at continuous review and updating of the FLL. Starting
               from the texts resulting from this lemmatization process, we describe
               the extension of the FLL by means of word embeddings, whose interactive
               traversing by means of SemioGraphs completes the digital enhanced
               hermeneutic circle. In this way, the article argues for a more
               comprehensive understanding of lemmatization, encompassing classical
               machine learning as well as intellectual post-corrections and,
               in particular, human computation in the form of interpretation
               processes based on graph representations of the underlying lexical
               resources.},
  url       = {https://www.studiesaggilinguistici.it/index.php/ssl/article/view/276},
  pdf       = {https://www.studiesaggilinguistici.it/index.php/ssl/article/download/276/219}
}

@inproceedings{Stoeckel:et:al:2020,
  author    = {Stoeckel, Manuel and Henlein, Alexander and Hemati, Wahed and Mehler, Alexander},
  title     = {{Voting for POS tagging of Latin texts: Using the flair of FLAIR
               to better Ensemble Classifiers by Example of Latin}},
  booktitle = {Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies
               for Historical and Ancient Languages},
  month     = {May},
  year      = {2020},
  address   = {Marseille, France},
  publisher = {European Language Resources Association (ELRA)},
  pages     = {130--135},
  abstract  = {Despite the great importance of the Latin language in the past,
               there are relatively few resources available today to develop
               modern NLP tools for this language. Therefore, the EvaLatin Shared
               Task for Lemmatization and Part-of-Speech (POS) tagging was published
               in the LT4HALA workshop. In our work, we dealt with the second
               EvaLatin task, that is, POS tagging. Since most of the available
               Latin word embeddings were trained on either few or inaccurate
               data, we trained several embeddings on better data in the first
               step. Based on these embeddings, we trained several state-of-the-art
               taggers and used them as input for an ensemble classifier called
               LSTMVoter. We were able to achieve the best results for both the
               cross-genre and the cross-time task (90.64\% and 87.00\%) without
               using additional annotated data (closed modality). In the meantime,
               we further improved the system and achieved even better results
               (96.91\% on classical, 90.87\% on cross-genre and 87.35\% on cross-time).},
  url       = {https://www.aclweb.org/anthology/2020.lt4hala-1.21},
  pdf       = {http://www.lrec-conf.org/proceedings/lrec2020/workshops/LT4HALA/pdf/2020.lt4hala-1.21.pdf}
}

@inproceedings{Abrami:Henlein:Kett:Mehler:2020,
  author    = {Abrami, Giuseppe and Henlein, Alexander and Kett, Attila and Mehler, Alexander},
  title     = {{Text2SceneVR}: Generating Hypertexts with VAnnotatoR as a Pre-processing
               Step for Text2Scene Systems},
  booktitle = {Proceedings of the 31st ACM Conference on Hypertext and Social Media},
  series    = {HT ’20},
  year      = {2020},
  location  = {Virtual Event, USA},
  isbn      = {9781450370981},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3372923.3404791},
  doi       = {10.1145/3372923.3404791},
  pages     = {177–186},
  numpages  = {10},
  pdf       = {https://dl.acm.org/doi/pdf/10.1145/3372923.3404791}
}

@article{Gleim:Eger:Mehler:2019,
  author    = {Gleim, R\"{u}diger and Eger, Steffen and Mehler, Alexander and Uslu, Tolga
               and Hemati, Wahed and L\"{u}cking, Andy and Henlein, Alexander and Kahlsdorf, Sven
               and Hoenen, Armin},
  title     = {A practitioner's view: a survey and comparison of lemmatization
               and morphological tagging in German and Latin},
  journal   = {Journal of Language Modeling},
  year      = {2019},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2019/07/jlm-tagging.pdf},
  doi       = {10.15398/jlm.v7i1.205},
  url       = {http://jlm.ipipan.waw.pl/index.php/JLM/article/view/205}
}

@inproceedings{Uslu:et:al:2018,
  author    = {Tolga Uslu and Alexander Mehler and Daniel Baumartz and Alexander Henlein
               and Wahed Hemati},
  title     = {fastSense: An Efficient Word Sense Disambiguation Classifier},
  booktitle = {Proceedings of the 11th edition of the Language Resources and
               Evaluation Conference, May 7 - 12},
  series    = {LREC 2018},
  address   = {Miyazaki, Japan},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2018/03/fastSense.pdf},
  year      = {2018}
}

@inproceedings{Uslu:et:al:2018:a,
  author    = {Tolga Uslu and Lisa Miebach and Steffen Wolfsgruber and Michael Wagner
               and Klaus Fließbach and Rüdiger Gleim and Wahed Hemati and Alexander Henlein
               and Alexander Mehler},
  title     = {{Automatic Classification in Memory Clinic Patients and in Depressive Patients}},
  booktitle = {Proceedings of Resources and ProcessIng of linguistic, para-linguistic
               and extra-linguistic Data from people with various forms of cognitive/psychiatric
               impairments (RaPID-2)},
  series    = {RaPID},
  location  = {Miyazaki, Japan},
  year      = {2018}
}