5th SwissText & 16th KONVENS
Joint Conference 2020

Scientific Track


Paper title

Manuel Sage, Pietro Cruciata, Raed Abdo, Jackie Cheung and Fiona Zhao

Investigating the Influence of Selected Linguistic Features on Authorship Attribution using German News Articles

Matthias Aßenmacher and Christian Heumann

On the comparability of pre-trained language models

Jingyuan Feng, Özge Sevgili, Steffen Remus, Eugen Ruppert and Chris Biemann

Supervised Pun Detection and Location with Feature Engineering and Logistic Regression

Manuela Weibel and Muriel Peter

Compiling a Large Swiss German Dialect Corpus

Annelen Brunner, Ngoc Duyen Tanja Tu, Lukas Weimer and Fotis Jannidis

To BERT or not to BERT — Comparing contextual embeddings in a deep learning architecture for the automatic recognition of four types of speech, thought and writing representation

Mascha Kurpicz-Briki

Cultural Differences in Bias? Origin and Gender Bias in Pre-Trained German and French Word Embeddings

Karolina Zaczynska, Nils Feldhus, Robert Schwarzenberg, Aleksandra Gabryszak and Sebastian Möller

Evaluating German Transformer Language Models with Syntactic Agreement Tests

Jean Charbonnier and Christian Wartena

Predicting the Concreteness of German Words

Jannis Vamvas and Rico Sennrich

X-Stance: A Multilingual Multi-Target Dataset for Stance Detection

Manfred Klenner, Anne Göhring and Michael Amsler

Harmonization sometimes Harms

Simone Griesser

Psychological Distance in German and English Brand Language of 6 International Brands

Janis Goldzycher, Isabel Meraner, Martin Volk and Simon Clematide

Ranking Georeferences for Efficient Crowdsourcing of Toponym Annotations in a Historical Corpus of Alpine Texts

Albin Zehe, Julia Arns, Lena Hettinger and Andreas Hotho

HarryMotions – Classifying Relationships in Harry Potter based on Emotion Analysis

Anastassia Shaitarova, Lenz Furrer and Fabio Rinaldi

Cross-lingual transfer learning approach to negation scope resolution

Applied Track


Paper title

Ela Pustulka-Hunt, Thomas Hanne, Phillip Gachnang and Pasquale Biafora

FLIE: Form Labelling for Information Extraction

Piroska Lendvai, Uwe Reichel, Simone Rebora and Moniek Kuijpers

Ranking of Social Reading Reviews Based on Richness in Narrative Absorption

Paula Reichenberg, Artūrs Vasiļevskis and Manuel Herranz

The “Multilingual Anonymisation Toolkit for Public Administrations” (MAPA) Project

Holger Keibel, Elisabeth Maier and Tobias Christen

Showcase: Language analytics and semantic search for unknown document varieties

Péter Jeszenszky, Burcu Demiray, Carina Steiner and Adrian Leemann

Towards a regionally representative and socio-demographically diverse resource of Swiss German

Albert Weichselbraun, Christian Hauser, Sandro Hörler and Anina Havelka

Deep learning and visual tools for analyzing and monitoring integrity risks

Branden Chan, Stefan Schweter and Timo Möller

Exploring German BERT model pre-training from scratch

Manuela Hürlimann, Malgorzata Anna Ulasik, Philippe Schläpfer, Fernando Benites de Azevedo E Souza, Katsiaryna Mlynchyk, Pius von Däniken, Flurin Gishamer, Lina Scarborough, Olesya Ogorodnikova, Tracey Etheridge, Nitin Kumar, Badrudin Stanicki and Mark Cieliebak

Speech-to-Text Insights

Daniele Puccinelli, Sandra Mitrovic, Denis Broggini, Giancarlo Corti, Luca Chiarabini, Riccardo Mazza, Fabio Rinaldi and Andrea Laus

Enabling conversational-based leadership training through advanced natural language understanding

Andrei Popescu-Belis, Aris Xanthos, Valentin Minder, Àlex R. Atrio, Gabriel Luthier and Antonio Rodriguez

Interactive Poem Generation: when Language Models support Human Creativity

Sandra Mitrović, Vani Kanjirangat, Denis Broggini, Lorenzo Cimasoni, Marco Alberti, Alessandro Antonucci and Fabio Rinaldi

A conversational recommender system based on neural NLP models

Iuliia Nigmatulina, Tannon Kew and Tanja Samardžić

Swiss German speech-to-text with Kaldi

Vani Kanjirangat and Fabio Rinaldi

Biomedical relation extraction with state-of-the-art neural models

Joseph Cornelius, Tilia Ellendorff, Nico Colic, Lenz Furrer, Albert Weichselbraun, Raul Rodriguez-Esteban, Philipp Kuntschik, Mathias Leddin, Juergen Gottowik and Fabio Rinaldi

MedMon: multilingual social media mining for disease monitoring

Jan Deriu, Katsiaryna Mlynchyk, Philippe Schläpfer, Alvaro Rodrigo, Dirk von Grünigen, Kurt Stockinger, Eneko Agirre and Mark Cieliebak

A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation

Alexandros Paramythis, Doris Paramythis and Andreas Putzinger

Following, understanding, and supporting service-oriented person-to-person communications

Fabio Rinaldi, Anne Goehring, Corinne Gurtner, John Berezowski, Michele Bodmer, Irene Zuehlke and Celine Faverjon

Text Mining Technologies for Animal Health Surveillance

Anne Jorstad

Assigning Grant Applications to Reviewers via Text Analysis

Dina Wieman, Khan Ozol, Natalia Korchagina, Claudio Bonesana, Anastassia Shaitarova and Fabio Rinaldi

Named entity recognition for job description mining

Ahmad Aghaebrahimian and Mark Cieliebak

Company Name Disambiguation

Demo Track


Paper title

Daniel Niklaus

Become a Compliance Hero with automated text analyses

Alena Schmickl, Thomas Bögel, Andrea Giovannini and Matthias Reumann

Combining NLP and domain knowledge induction into knowledge graphs to automate medical coding

Matthias Sommer

Twitter Sentiment Analysis in MATLAB

Andrei Popescu-Belis, Aris Xanthos, Valentin Minder, Àlex R. Atrio, Gabriel Luthier and Antonio Rodriguez

Interactive Poem Generation Demo

Alexandros Paramythis, Doris Paramythis and Andreas Putzinger

SmartCC: Combining NLU and semantic business case modelling in customer care support