09:30 – 10:30 Semantics I – Drift 21 0.32 (chair: Els Lefever)

09:30 – 09:50 Evaluating the consistency of word embeddings from small data Jelke Bloem1, Antske Fokkens2, Aurélie Herbelot3 1University of Amsterdam, 2VU Amsterdam, 3University of Trento

09:50 – 10:10 Type-Driven Composition of Word Embeddings in the age of BERT Gijs Wijnholds Utrecht University

10:10 – 10:30 A diachronic study on the compositionality of English noun-noun compounds using vector-based semantics Prajit Dhar1, Janis Pagel2, Lonneke van der Plas3, Sabine Schulte im Walde4 1University of Groningen, 2Institute for Natural Language Processing, University of Stuttgart, 3University of Malta, 4University of Stuttgart

09:30 – 10:30 Machine Learning – Drift 21 1.05 (chair: Marco Spruit)

09:30 – 09:50 Investigating The Generalization Capacity Of Convolutional Neural Networks For Interpreted Languages Daniel Bezema and Denis Paperno Utrecht University

09:50 – 10:10 Predicting the number of citations of scientific articles with shallow and deep models Gideon Maillette de Buy Wenniger1, Herbert Teun Kruitbosch2, Lambert Schomaker1, Valentijn A. Valentijn3 1Autonomous Perceptive Systems group – Bernoulli Institute, University of Groningen, 2University of Groningen, 3Kapteyn Astronomical Institute, University of Groningen,

10:10 – 10:30 A Non-negative Tensor Train Decomposition Framework for Language Data Tim Van de Cruys IRIT & CNRS

09:30 – 10:30 Text Analytics I – Drift 25 1.02 (chair: Ineke Schuurman)

09:30 – 09:50 Language features and social media metadata for age prediction using CNN Abhinay Pandya1, Mourad Oussalah1, Paola Monachesi2, Panos Kostakos1 1University of Oulu, 2Utrecht University

09:50 – 10:10 EventDNA: Identifying event mention spans in Dutch-language news text Camiel Colruyt, Orphée De Clercq, Véronique Hoste LT3, Ghent University

10:10 – 10:30 Cross-context News Corpus of Protest Events Ali Hürriyetoğlu, Erdem Yoruk, Deniz Yuret, Osman Mutlu, Burak Gurel, Cagri Yoltar, Firat Durusan Koç University

09:30 – 10:30 Syntax & Parsing I – Drift 21 0.05 (chair: Michael Moortgat)

09:30 – 09:50 Linguistic enrichment of historical Dutch using deep learning Silke Creten1, Peter Dekker2, Vincent Vandeghinste3 1KU Leuven, 2Vrije Universiteit Brussel & Instituut voor de Nederlandse Taal, 3Instituut voor de Nederlandse Taal

09:50 – 10:10 Resolution of morphosyntactic ambiguity in Russian with two-level linguistic analysis Uliana Petrunina University of Tromsø

10:10 – 10:30 Task-specific pretraining for German and Dutch dependency parsing Daniël de Kok and Tobias Pütz University of Tübingen

09:30 – 10:30 Sentiment Analysis – Drift 21 1.09 (chair: Kalliopi Zervanou)

09:30 – 09:50 An unsupervised aspect extraction method with an application to Dutch book reviews Stephan Tulkens1 and Andreas van Cranenburgh2 1CLiPS, University of Antwerp, 2University of Groningen

09:50 – 10:10 Improving Pattern.nl sentiment analysis Lorenzo Gatti and Judith van Stegeren Human Media Interaction, University of Twente

10:10 – 10:30 Dutch language polarity analysis on reviews and cognition description datasets Gerasimos Spanakis and Josephine Rutten Maastricht University

11:00 – 12:00 Keynote: Multilingual Dependency Parsing: From Universal Dependencies to Sesame Street – Drift 21 0.32 (chair: Jan Odijk)

While research on dependency parsing has always had a strong multilingual orientation, the lack of standardized annotations for a long time made it difficult both to meaningfully compare results across languages and to develop truly multilingual systems. The Universal Dependencies project has during the last five years tried to overcome this obstacle by developing cross-linguistically consistent morphosyntactic annotation for many languages. During the same period, dependency parsing (like the rest of NLP) has been transformed by the adoption of continuous vector representations and neural network techniques. In this talk, I will introduce the framework and resources of Universal Dependencies, and discuss advances in multilingual dependency parsing enabled by these resources in combination with deep learning techniques, ranging from traditional word and character embeddings to deep contextualized word representations like ELMo and BERT. Joakim Nivre

12:00 – 13:45 Poster – Drift 21 0.03

BLISS: A collection of Dutch spoken dialogue about what makes people happy Jelte van Waterschoot1, Iris Hendrickx2, Arif Khan2, Marcel de Korte3 1University of Twente, 2Radboud University Nijmegen, 3ReadSpeaker

Dutch Anaphora Resolution: A Neural Network Approach towards Automatic die/dat Prediction Liesbeth Allein1, Artuur Leeuwenberg2, Marie-Francine Moens1 1KU Leuven, 2Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht

Computational Model of Quantification Guanyi Chen and Kees van Deemter Utrecht University

Parallel corpus annotation and visualization with TimeAlign Martijn van der Klis and Ben Bonfil UiL OTS, Utrecht University

Towards a Dutch FrameNet lexicon and parser using the data-to-text method Gosse Minnema1 and Levi Remijnse2 1University of Groningen, 2VU University Amsterdam

The merits of Universal Language Model Fine-tuning for Small Datasets – a case with Dutch book reviews Benjamin van der Burgh and Suzan Verberne LIACS, Leiden University

Low-Resource Unsupervised Machine Translation using Dependency Parsing Lukas Edman, Gertjan van Noord, Antonio Toral University of Groningen

Relation extraction for images using the image captions as supervision Xue Wang1, Youtian Du1, Suzan Verberne2, Fons J. Verbeek2 1Xi’an Jiaotong University, 2LIACS, Leiden University

Evaluating and improving state-of-the-art named entity recognition and anonymisation methods Chaïm van Toledo and Marco Spruit Universiteit Utrecht

Automatic extraction of semantic roles in support verb constructions Ignazio Mauro Mirto Università di Palermo

Introducing CROATPAS: A digital semantic resource for Croatian verbs Costanza Marini and Elisabetta Ježek University of Pavia

SONNET: our Semantic Ontology Engineering Toolset Maaike de Boer, Jack Verhoosel, Roos Bakker TNO

Stylometric and Emotion-Based Features for Hate Speech Detection Ilia Markov and Walter Daelemans University of Antwerp, CLiPS

Evaluating an Acoustic-based Pronunciation Distance Measure Against Human Perceptual Data Martijn Bartelds and Martijn Wieling University of Groningen

Examination on the Phonological Rules Processing of Korean TTS Hyeon-yeol Im Chung-ang University

12:00 – 13:45 Poster – Drift 21 0.06

How far is “man bites dog” from “dog bites man”? Investigating the structural sensitivity of distributional verb matrices Luka van der Plas Utrecht University

The Effect of Vocabulary Overlap on Linguistic Probing Tasks for Neural Language Models Prajit Dhar and Arianna Bisazza University of Groningen

Towards automation of language assessment procedures Sjoerd Eilander and Jan Odijk 1Utrecht University, UiL-OTS

A Collection of Side Effects and Coping Strategies in Patient Discussion Groups Anne Dirkson, Suzan Verberne, Wessel Kraaij Leiden University

A replication study for better application of text classification in political science. Hugo de Vos Leiden University

Article omission in Dutch newspaper headlines R. van Tuijl and Denis Paperno Utrecht University

Innovation Power of ESN Erwin Koens HU University of Applied Sciences Utrecht

Multi-label ICD Classification of Dutch Hospital Discharge Letters Ayoub Bagheri1, Arjan Sammani2, Daniel Oberski3, Folkert W. Asselbergs2 1Department of Methodology and Statistics, Utrecht University, 2Department of Cardiology, Division of Heart and Lungs, University Medical Center Utrecht, 3Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University

Political self-presentation on Twitter before, during, and after elections: A diachronic analysis with predictive models Harmjan Setz, Marcel Broersma, Malvina Nissim University of Groningen

Text Processing with Orange Erik Tjong Kim Sang1, Peter Kok1, Wouter Smink2, Bernard Veldkamp2, Gerben Westerhof2, Anneke Sools2 1Netherlands eScience Center, 2University of Twente

Whose this story? Investigating Factuality and Storylines Tommaso Caselli, Marcel Broersma, Blanca Calvo Figueras, Julia Meyer Rijksuniversiteit Groningen

Bootstrapping the extension of an Afrikaans treebank through gamification Peter Dirix1 and Liesbeth Augustinus2 1Cerence, KU Leuven, 2CCL, KU Leuven

Starting a treebank for Ughele Peter Dirix1 and Benedicte Haraldstad Frostad2 1Cerence, KU Leuven, 2Norwegian Language Council, Oslo

13:45 – 14:45 Semantics II – Drift 21 0.32 (chair: Malvina Nissim)

13:45 – 14:05 Comparing Frame Membership to WordNet-based and Distributional Similarity Esra Abdelkareem Debrecen University

14:05 – 14:25 Representing a concept by the distribution of names of its instances Matthijs Westera1, Gemma Boleda2, Sebastian Padó3 1Universitat Pompeu Fabra, 2ICREA / Universitat Pompeu Fabra, 3Universität Stuttgart

14:25 – 14:45 Semantic parsing with fuzzy meaning representations Pavlo Kapustin1 and Michael Kapustin2 1University of Bergen, 2Moscow Institute of Physics and Technology

13:45 – 14:45 Text Analytics II – Drift 25 1.02 (chair: Paola Monachesi)

13:45 – 14:05 Annotating sexism as hate speech: the influence of annotator bias Elizabeth Cappon1,2, Guy De Pauw1,2, Walter Daelemans2 1TEXTGAIN, 2University of Antwerp

14:05 – 14:25 Accurate Estimation of Class Distributions in Textual Data Erik Tjong Kim Sang1, Kim Smeenk2, Aysenur Bilgin3, Tom Klaver1, Laura Hollink3, Jacco van Ossenbruggen3,4, Frank Harbers2, Marcel Broersma2 1Netherlands eScience Center, 2University of Groningen, 3CWI, 4VU

14:25 – 14:45 Interpreting Dutch Tombstone Inscriptions Johan Bos University of Groningen

13:45 – 14:45 Medical NLP – Drift 21 1.05 (chair: Thierry Declerck)

13:45 – 14:05 Extracting Drug, Reason, and Duration Mentions from Clinical Text Data: A Comparison of Approaches Jens Lemmens, Simon Suster, Walter Daelemans University of Antwerp, CLiPS

14:05 – 14:25 Dialogue Summarization for Smart Reporting: the case of consultations in health care. Sabine Molenaar, Fabiano Dalpiaz, Sjaak Brinkkemper Utrecht University

14:25 – 14:45 Natural Language Processing and Machine Learning for Classification of Dutch Radiology Reports Prajakta Shouche1 and Ludo Cornelissen2 1University of Groningen, 2University Medical Center Groningen

13:45 – 14:45 Syntax & Parsing II – Drift 21 0.05 (chair: Gosse Bouma)

13:45 – 14:05 Frequency-tagged EEG responses to grammatical and ungrammatical phrases. Amelia Burroughs, Nina Kazanina, Conor Houghton University of Bristol

14:05 – 14:25 Detecting syntactic differences automatically using the minimum description length principle Martin Kroon1, Sjef Barbiers1, Jan Odijk2, Stéphanie van der Pas1 1Leiden University, 2Utrecht University

14:25 – 14:45 Complementizer Agreement Revisited: A Quantitative Approach Milan Valadou KU Leuven

14:45 – 16:15 Poster – Drift 21 0.03

Alpino for the masses Joachim Van den Bogaert K.U. Leuven

GrETEL @ INT: Querying Very Large Treebanks by Example Vincent Vandeghinste and Koen Mertens Instituut voor de Nederlandse Taal

Convergence in First and Second Language Acquisition Dialogues Arabella Sinclair and Raquel Fernández ILLC, University of Amsterdam

ExpReal: A Multilingual Expressive Realiser Ruud de Jong1, Nicolas Szilas2, Mariët Theune1 1University of Twente, 2University of Geneva

IVESS: Intelligent Vocabulary and Example Selection for Spanish vocabulary learning Jasper Degraeuwe and Patrick Goethals Ghent University

Interlinking the ANW Dictionary and the Open Dutch WordNet Thierry Declerck DFKI GmbH

Psycholinguistic Profiling of Contemporary Egyptian Colloquial Arabic Words Bacem Essam1 and Ameni Mejri2 1Peerwith, 2Debrecen University

BERT-NL: a set of language models pre-trained on the Dutch SoNaR corpus Alex Brandsen1, Anne Dirkson1, Suzan Verberne1, Maya Sappelli2, Dungh Manh Chu3, Kimberly Stoutjesdijk3 1Leiden University, 2FDMG / HAN, 3FD Mediagroep

Dialect-aware Tokenisation for Translating Arabic User Generated Gontent Pintu Lohar1, Haithem Afli2, Andy Way3 1Dublin City University, 2ADAPT Centre, Cork Institute of Technology, 3ADAPT Centre, Dublin City University

Literary MT under the magnifying glass: Assessing the quality of an NMT-translated Agatha Christie novel. Margot Fonteyne, Arda Tezcan, Lieve Macken LT3, Ghent University, Belgium

WordNet, occupations and natural gender Ineke Schuurman1, Vincent Vandeghinste2, Leen Sevens1 1KU Leuven, 2Instituut voor de Nederlandse Taal

Mark my Word: A Sequence-to-Sequence Approach to Definition Modeling Timothee Mickus1, Denis Paperno2, Mathieu Constant3 1Université de Lorraine, ATILF, 2Utrecht University, 3Université de Lorraine, CNRS, ATILF

Nederlab Word Embeddings Martin Reynaert KNAW Meertens Institute / Tilburg University

Neural Semantic Role Labeling Using Deep Syntax for French FrameNet Tatiana Bladier1 and Marie Candito2 1Heinrich Heine University of Düsseldorf, 2LLF (Univ Paris Diderot / CNRS)

14:45 – 16:15 Poster – Drift 21 0.06

Acoustic speech markers for psychosis Janna de Boer1, Alban Voppel2, Frank Wijnen3, Iris Sommer2 1UMC Utrecht, 2UMC Groningen, 3UiL OTS

Social media candidate generation as a psycholinguistic task Stephan Tulkens, Dominiek Sandra, Walter Daelemans University of Antwerp, CLiPS

Evaluating Language-Specific Adaptations of Multilingual Language Models for Universal Dependency Parsing Ahmet Üstün, Arianna Bisazza, Gosse Bouma, Gertjan van Noord University of Groningen

SPOD: Syntactic Profiler of Dutch Gertjan van Noord, Jack Hoeksema, Peter Kleiweg, Gosse Bouma University of Groningen

HAMLET: Hybrid Adaptable Machine Learning approach to Extract Terminology Ayla Rigouts Terryn, Veronique Hoste, Els Lefever LT3, Ghent University

How Similar are Poodles in the Microwave? Classification of Urban Legend Types Myrthe Reuver Radboud University Nijmegen

Identifying Predictors of Decisions for Pending Cases of the European Court of Human Rights Masha Medvedeva, Michel Vols, Martijn Wieling University of Groningen

Rightwing Extremism Online Vernacular: Empirical Data Collection and Investigation through Machine Learning Techniques Pierre Voué Textgain

SnelSLiM: a webtool for quick stable lexical marker analysis Bert Van de Poel KU Leuven

Syntactic, semantic and phonological features of speech in schizophrenia spectrum disorders; a combinatory classification approach. Alban Voppel1,2, Janna de Boer1,2, Hugo Schnack2,3, Iris Sommer1 1UMC Groningen, 2UMC Utrecht, 3Universiteit Utrecht

Tracing thoughts – application of “ngram tracing” on schizophrenia data Lisa Becker1 and Walter Daelemans2 1University of Potsdam, 2Universiteit Antwerpen

Spanish ‘se’ and ‘que’ in Universal Dependencies (UD) parsing: a critical review Patrick Goethals and Jasper Degraeuwe Ghent University

16:15 – 17:15 Language Generation – Drift 21 0.05 (chair: Mariët Theune)

16:15 – 16:35 Generating relative clauses from logic Crit Cremers LUCL, Leiden University

16:35 – 16:55 Elastic words in English and Chinese: are they the same phenomenon? Lin Li, Kees van Deemter, Denis Paperno Utrecht University

16:55 – 17:15 Generation of Image Captions Based on Deep Neural Networks Shima Javanmardi1, Ali Mohammad Latif1, Fons Verbeek2, Mohammad Taghi Sadeghi Sadeghi1 1Yazd University, 2Leiden University

16:15 – 17:15 Semantics III – Drift 21 0.32 (chair: Suzan Verberne)

16:15 – 16:35 AETHEL: typed supertags and semantic parses for Dutch Konstantinos Kogkalidis1, Michael Moortgat1, Richard Moot2 1Utrecht University, 2CNRS

16:35 – 16:55 Evaluating character-level models in neural semantic parsing Rik van Noord, Antonio Toral, Johan Bos University of Groningen

16:55 – 17:15 Testing Abstract Meaning Representation for Recognizing Textual Entailment Lasha Abzianidze CLCG, University of Groningen

16:15 – 17:15 Text & Speech Analytics – Drift 25 1.02 (chair: Erik Tjong Kim Sang)

16:15 – 16:35 Towards Dutch Automated Writing Evaluation Orphee De Clercq LT3, Ghent University

16:35 – 16:55 Automatic Analysis of Dutch speech prosody Aoju Chen, Na Hu, Berit Janssen Utrecht University

16:55 – 17:15 Hyphenation: from transformer models and word embeddings to a new linguistic rule-set Francois REMY UGent/IDLAB

16:15 – 17:15 Translation – Drift 21 1.05 (chair: Vincent Vandeghinste)

16:15 – 16:35 Translation mining in the domain of conditionals: first results Jos Tellings Utrecht University

16:35 – 16:55 Automatic Detection of English-Dutch and French-Dutch Cognates on the basis of Orthographic Information and Cross-Lingual Word Embeddings Sofie Labat, Els Lefever, Pranaydeep Singh LT3, Ghent University

16:55 – 17:15 On the difficulty of modelling fixed-order languages versus case marking languages in Neural Machine Translation Stephan Sportel and Arianna Bisazza University of Groningen

16:15 – 17:15 Shared Task – Drift 21 1.09 (chair: Marijn Schraagen)