Program
Invited speakers
- Afra Alishahi (Tilburg University)
- Milica Gašić (Heinrich-Heine-Universität Düsseldorf)
- Mirella Lapata (University of Edinburgh)
- Johann-Mattis List (Max-Planck-Institut für Menschheitsgeschichte, Jena)
Program schedule
Monday, September 6th
- 1st Workshop on Computational Linguistics for Political Text Analysis (CPSS) (09:00 – 17:45, online)
- Workshop on Multimodal and Multilingual Hate Speech Detection (09:00 – 12:30, online)
- Shared Task on Scene Segmentation (STSS) (13:30 – 17:00, hybrid)
- GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments (09:00 – 14:00, online)
- Shared Task on the Disambiguation of German Verbal Idioms (14:00 – 17:00, online)
Tuesday, September 7th
08:45 – 09:00 Opening
09:00 – 10:30
Mirella Lapata (invited speaker): Summarization and Paraphrasing in Quantized Transformer Spaces
11:00 – 12:00
Track 1
- Ayush Yadav & Benjamin Milde: forumBERT: Topic Adaptation and Classification of Contextualized Forum Comments in German
- Maike Behrendt & Stefan Harmeling: ArgueBERT: How To Improve BERT Embeddings for Measuring the Similarity of Arguments
Track 2
- Leonhard Hennig, Phuc Tran Truong & Aleksandra Gabryszak: MobIE: A German Dataset for Named Entity Recognition, Entity Linking and Relation Extraction in the Mobility Domain
- Maximilian Wich, Svenja Räther & Georg Groh: German Abusive Language Dataset with Focus on COVID-19
13:30 – 15:00
Track 1
- Janine Siewert, Yves Scherrer & Jörg Tiedemann: Towards a balanced annotated Low Saxon dataset for diachronic investigation of dialectal variation
- Katrin Ortmann: Automatic Phrase Recognition in Historical German
- Stefanie Dipper & Jan Christian Schaffert: Identifikation von Vorkommensformen der Lemmata in Quellenzitaten frühneuhochdeutscher Lexikoneinträge
Track 2
- Niklas von Boguszewski, Sana Moin, Anirban Bhowmick, Seid Muhie Yimam & Chris Biemann: How Hateful are Movies? A Study and Prediction on Movie Subtitles
- Sebastian Reimann & Daniel Dakota: Examining the Effects of Preprocessing on the Detection of Offensive Language in German Tweets
- Svenja Preuß, Tabea Bayha, Luna Pia Bley, Vivien Dehne, Alessa Jordan, Sophie Reimann, Fina Roberto, Josephine Romy Zahm, Hanna Siewerts, Dirk Labudde & Michael Spranger: CNN-Based Online Grooming Chat Identification
15:30 – 17:00
Milica Gašić (invited speaker): Neural dialogue models: growing up confident and independent
Wednesday, September 8th
09:00 – 10:30
Johann-Mattis List (invited speaker): Chances and Challenges for Computational Comparative Linguistics in the 21st Century
11:00 – 12:00
Track 1
- Fynn Schröder, Hans Ole Hatzel & Chris Biemann: Neural End-to-end Coreference Resolution for German in Different Domains
- Ines Rehbein, Josef Ruppenhofer & Julian Bernauer: Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates
Track 2
- Onno Eberhard & Torsten Zesch: Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages
- Aashish Agarwal & Torsten Zesch: Robustness of end-to-end Automatic Speech Recognition Models – A Case Study using Mozilla DeepSpeech
13:30 – 15:30
Presentations of nominees for GSCL Student Awards
- Josua Stadelmaier: Modeling Paths for Explainable Knowledge Base Completion
- Maike Johanna Klepsch: Untersuchung und Visualisierung verschiedener maschineller Lernverfahren zur Topic-Extraktion
- Yannic Bracke: Automatic text classification with imbalanced data – Building a frame classifier from a corpus of editorials
- Marie Bexte: Combined Analysis of Image and Text Using Visio-Linguistic Neural Models – A Case Study on Robustness Within an Educational Scoring Task
- Eva Huber: Differences between inflectional and derivational morphology: a study based on the predictability in a distributional vector space
- Annerose Eichel: Investigating Independence vs. Control: A Computational Analysis of Complex Manipulation Strategies in News on Russian Social Media
16:00 – 17:00
Track 1
- Theresa Kruse & Fritz Kliche: Definition Extraction from Mathematical Texts on Graph Theory in German and English
- Ulrike May, Karolina Zaczynska, Julián Moreno-Schneider & Georg Rehm: Extraction and Normalization of Vague Time Expressions in German
Track 2
- Matthias Aßenmacher, Patrick Schulze & Christian Heumann: Benchmarking down-scaled (not so large) pre-trained language models
Thursday, September 9th
09:00 – 10:30
Track 1
- Felix Casel, Amelie Heindl & Roman Klinger: Emotion Recognition under Consideration of the Emotion Component Process Model
- Bao Minh Doan Dang, Laura Oberländer & Roman Klinger: Emotion Stimulus Detection in German News Headlines
- Anne Göhring, Manfred Klenner & Sophia Conrad: DeInStance: Creating and Evaluating a German Corpus for Fine-Grained Inferred Stance Detection
Track 2
- Abhijeet Gupta, Fritz Günther, Ingo Plag, Laura Kallmeyer & Stefan Conrad: Combining text and vision in compound semantics: Towards a cognitively plausible multimodal model
- Cennet Oguz, André Blessing, Jonas Kuhn & Sabine Schulte im Walde: WordGuess: Using Associations for Guessing, Learning and Exploring Related Words
- Freya Hewett & Manfred Stede: Automatically evaluating the conceptual complexity of German texts
11:00 – 12:00
Track 1
- Sandra Wankmüller & Christian Heumann: How to Estimate Continuous Sentiments From Texts Using Binary Training Data
- Jakob Fehle, Thomas Schmidt & Christian Wolff: Lexicon-based Sentiment Analysis in German: Systematic Evaluation of Resources and Preprocessing Techniques
Track 2
- Benedikt Adelmann, Wolfgang Menzel & Heike Zinsmeister: The Impact of Word Embeddings on Neural Dependency Parsing
- Wei Zhou & Jelke Bloem: Comparing Contextual and Static Word Embeddings with Small Philosophical Data
13:30 – 15:00
Afra Alishahi (invited speaker): Decoding what deep, grounded neural models learn about language
15:00 – 15:30 Awards & Closing