Conference programme

The main conference takes place from Wednesday (October 09) to Friday (October 11). The GermEval workshop and the statistics tutorial take place on Tuesday (October 08).

The main conference fee covers the welcome reception at the Orangerie and the conference dinner at Bratwurst Röslein with a preceding city tour of Nürnberg or a tour through the rock-cut cellars.

On Tuesday evening, we will meet for a warm-up at Steinbach-Bräu (self-paying).

Detailed conference programme: konvens-2019-programme-2019-10-07.pdf (updated on 07.10.)

Plenary talks

Plenary Talk 1

Computational linguistics and linguistic theory
  • Gemma Boleda (Barcelona)
  • Wednesday 09.10.2019, 9:30–11:00

Computational Linguistics has recently made enormous progress in modeling natural languages. It looks like we are getting something right about language, and this merits close inspection and analysis: we should understand what it is that we are getting right, and incorporate it into current linguistic theories. However, sadly, the impact of our methods and results in theoretical linguistics is to date quite limited. I will discuss ways in which we can interface with linguistics, exemplify it with my own work and that of others, and discuss challenges and ways forward.

About the speaker

Gemma Boleda works as a tenure-track researcher at Universitat Pompeu Fabra (Barcelona, Spain). After earning a PhD at U. Pompeu Fabra, she moved on to post-doctoral positions including The University of Texas at Austin (USA) and University of Trento (Italy). She has served as Area Chair for ACL 2016, as co-editor of a Special Issue on Formal Distributional Semantics of the Computational Linguistics journal, and as a member of the standing review committee of TACL since 2017, a.o. In her research, Dr. Boleda uses quantitative and computational methods to better understand the semantics of natural language. In her current ERC Starting Grant, she and her team investigate the interplay between conceptual and referential aspects of meaning.

Plenary Talk 2

Hybrid natural language understanding: neural network, logic and beyond
About the speakers

Daisuke Bekki is a formal semanticist who advocated a new framework for a theory of meaning, called dependent type semantics (DTS). DTS is one of the proof-theoretic frameworks that have attracted attention in recent years as an alternative to model-theoretic semantics. Bekki is also known as a formal syntactician by research on Japanese syntax employing combinatory categorial grammar (CCG). In the past five years, he has led a NLP research project in which a neural wide-coverage CCG parser, Montagovian higher-order logical semantics, and proof automation techniques are integrated into the RTE system ccg2lambda.

Hitomi Yanaka is a research scientist at RIKEN Center for Advanced Intelligence Project (AIP). She works on natural language inference a.k.a. recognizing textual entailment, and integration of logic-based approaches and vector-based approaches.

List of Accepted Papers

Short Papers

  • Gertrud Faaß and Sonja Bosch. Towards a gold standard corpus for detecting valencies of Zulu verbs.
  • Roman Schneider. “Konservenglück in Tiefkühl-Town” – Das Songkorpus als empirische Ressource interdisziplinärer Erforschung deutschsprachiger Poptexte.
  • Stefan Schweter. Contextualized String Embeddings for PoS Tagging: A Multilingual Evaluation.
  • Finn Årup Nielsen and Lars Kai Hansen. Combining embedding methods for a word intrusion task.
  • Annelen Brunner, Ngoc Duyen Tanja Tu, Lukas Weimer and Fotis Jannidis. Deep learning for Free Indirect Representation.
  • Jon Stevens, Brandon Punturo, Derek Chen, Mike Kim and Jacob Zimmer. Representing document-level semantics of biomedical literature using pre-trained embedding models: Novel assessments.
  • Stefan Schweter and Sajawel Ahmed. Deep-EOS: General-Purpose Neural Networks for Sentence Boundary Detection.
  • Ozge Alacam, Wolfgang Menzel and Tobias Staron. How Does Visual Complexity Influence Predictive Language Processing in a Situated Context?.
  • Yash Bhalgat, Zhe Liu, Pritam Gundecha, Jalal Mahmud and Amita Misra. Teacher-Student Learning Paradigm for Tri-training: An Efficient Method for Unlabeled Data Exploitation.
Long Papers
  • Maria Skeppstedt, Rafal Rzepka, Andreas Kerren and Kenji Araki. Visualising and evaluating the effects of combining active learning with word embedding features.
  • Ritavan and Harald Koppen. Label Propagation of Polarity Lexica on Word Vectors.
  • Katrin Ortmann, Adam Roussel and Stefanie Dipper. Evaluating Off-the-Shelf NLP Tools for German.
  • Kai Labusch, Clemens Neudecker and David Zellhöfer. BERT for Named Entity Recognition in Contemporary and Historic German.
  • Michael Wiegand, Margarita Chikobava and Josef Ruppenhofer. A Supervised Learning Approach for the Extraction of Sources and Targets from German Text.
  • Michael Wiegand, Leonie Lapp and Josef Ruppenhofer. A Descriptive Analysis of a German Corpus Annotated with Opinion Sources and Targets.
  • Edit Szügyi, Sören Etler, Andrew Beaton and Manfred Stede. Automated Assessment of Language Proficiency on German Data.
  • Christian Wartena. A Probabilistic Morphology Model for German Lemmatization.
  • Veronika Hintzen and Alexander Fraser. To Act Or Not To Act - Annotating and Classifying Email Regarding Necessary Action.
  • Anna Hätty, Ulrich Heid, Anna Moskvina, Julia Bettinger, Michael Dorna and Sabine Schulte Im Walde. AkkuBohrHammer vs. AkkuBohrhammer: Experiments towards the Evaluation of Compound Splitting Tools for General Language and Specific Domains.
  • Dirk Johannßen and Chris Biemann. Neural classification with attention assessment of the implicit-association test OMT and prediction of subsequent academic success.
  • Sebastian Zepf, Deniz Cevher and Roman Klinger. Towards Multimodal Emotion Recognition in German Speech Events in Cars using Transfer Learning.
  • Fabian Karl, Chris Biemann and Mikko Lauri. Communication with Human Motivation: How solving the Image Captioning-Retrieval problem creates conversations.
  • Aashish Agarwal and Torsten Zesch. German End-to-end Speech Recognition based on DeepSpeech.
  • Josef Ruppenhofer and Ines Rehbein. Detecting the boundaries of sentence-like units in spoken German.
  • Eckhard Bick. Dependency Trees for Greenlandic.
  • Ines Reinig and Ines Rehbein. Metaphor detection for German Poetry.
  • Gregor Wiedemann, Avi Chawla, Steffen Remus and Chris Biemann. Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings.
  • Jennifer Fest, Arndt Heilmann, Oliver Hohlfeld, Stella Neumann, Jens Helge Reelfs, Marco Schmitt and Alina Vogelgesang. Determining Response-generating Contexts on Microblogging Platforms.
  • Luise Schricker, Manfred Stede and Peer Trilcke. Extraction and Classification of Speech, Thought, and Writing in German Narrative Texts.
  • Juri Opitz. Argumentative Relation Classification as Plausibility Ranking.
  • Enendu. Predicting Semantic Labels of Text Regions in Heterogeneous Document Images.