| 9:00 – 9:30 | REGISTRATION | |||
|---|---|---|---|---|
| Session 1 9:30 – 10:50 | NER/WSD
Els Lefever |
Machine Translation
Wilker Aziz |
Neural Networks
Diego Marcheggiani |
SRL/Semantic Parsing
Orphee De Clercq |
|---|---|---|---|---|
| 9:30 | A look inside Babelfy: Examining the Bubble Minh Le and Filip Ilievski |
Machine translation-based language model adaptation for automatic speech recognition of spoken translations Joris Pelemans, Tom Vanallemeersch, Kris Demuynck, Lyan Verwimp, Hugo Van Hamme and Patrick Wambacq |
Recurrent neural networks for genre-specific language generation in Dutch Tim Van de Cruys |
Exploiting the existing: Towards a Dutch frame-semantic parser Chantal van Son |
| 9:50 | Inducing multi-sense word representations multilingually Simon Suster, Ivan Titov and Gertjan Van Noord |
UGENT-LT3 SCATE system for machine translation quality estimation Arda Tezcan, Veronique Hoste, Bart Desmet and Lieve Macken |
Tagging variation-rich languages using convolutional neural networks Mike Kestemont, Guy De Pauw, Walter Daelemans, Renske van Nie, Sander Dieleman and Gilles- Maurice de Schryver |
The effects of semantic role labeling on sub-sentential alignment in parallel treebanks Mathias Coeckelbergs |
| 10:10 | Word sense disambiguation in text-to-pictograph translation Gilles Jacobs, Leen Sevens, Vincent Vandenghinste, Ineke Schuurman, Frank Van Eynde |
Deep Machine Translation for Dutch: the QTLeap project. Dieke Oele, Gertjan Van Noord and Ondrej Dusek |
Towards learning domaingeneral representations for language from multi-modal data Ákos Kádár, Grzegorz Chrupała and Afra Alishahi |
Cross-lingual transfer of a semantic parser via parallel data Kilian Evang and Johan Bos |
| 10:30 | Enriching machine translation input using semantics-based fuzzy matches Tom Vanallemeersch and Leen Sevens |
A discourse-aware deep neural attention based model for machine reading and recognizing textual entailment Ehsan Khoddam |
Surfacing Dutch syntactic parses Erwin Komen |
| 10:50 – 11:20 | COFFEE BREAK | |||
|---|---|---|---|---|
| 11:20 – 12:30 | PLENARY SESSION | |||
|---|---|---|---|---|
| 11:20 | Welcome | |||
| 11:25 | STIL Thesis Award | |||
| 11:30 | Invited talk by Miriam Butt
The talk presents innovative visual analyses for text and speech data that allow linguists a comparative analysis of the underlying structure of languages by: a) processing vast amounts of data automatically; b) have a snap shot overview; c) drill down to individual data points; and d) interact dynamically with the visualizations. The visual analyses include pixel and sunburst visualizations as well as self-organizing maps.,The examples are drawn from language change, pragmatics and prosodic analysis. |
|||
| 12:30 – 14:20 | LUNCH and POSTER SESSION | |||
|---|---|---|---|---|
| POSTERS with DEMO
An editor to quickly produce age-specific texts for children. Thijs Westerveld Automatic writing assistance in multiple languages. Dennis de Vries BlackLab: advantages and disadvantages of using Lucene for a linguistic corpus search system. Jan Niestadt Breaking the glass ceiling: Semantic Approaches to Machine Translation. Paul Van Eecke, Miquel Cornudella and Remi van Trijp Extending Alpino with Multiword Expressions: an initial investigation. Jan Odijk Natural Language Generation from Pictographs. Leen Sevens, Vincent Vandeghinste, Ineke Schuurman and Frank Van Eynde Representing and Implementing Constructions in Fluid Construction Grammar. Paul Van Eecke, Luc Steels, Miquel Cornudella and Remi van Trijp SHEBANQ: Annotations based hub of research in the Hebrew Bible. Wido van Peursen, Dirk Roorda and Martijn Naaijer The CLARIN Concept Registry. Ineke Schuurman, Menzo Windhouwer and Olha Shkaravska Transcriptor: a transcription app for the Cyrillic script. Martin Reynaert, Pepijn Hendriks and Nicoline van der Sijs ==================================================================================================================================================================================== POSTERS A novel approach to aspect extraction taking into account linguistic structure. Stéphan Tulkens and Walter Daelemans Annotating Telugu corpus: Using the BIS-POS Tagset. Viswanatha Naidu Data Selection for SMT: Comparison of Various Methods. Amir Kamran and Khalil Sima’An DISCOSUMO: Summarizing forum threads. Sander Wubben, Suzan Verberne, Antal van Den Bosch and Emiel Krahmer Evaluation and analysis of term scoring methods for keyphrase extraction. Suzan Verberne, Maya Sappelli and Wessel Kraaij Initial steps towards building a large vocabulary automatic speech recognition system for the Frisian language. Emre Yilmaz, Maaike Andringa, Sigrid Kingma, Frits Van der Kuip, Hans Van de Velde, Frederik Kampstra, Jouke Algra, Henk Van den Heuvel and David Van Leeuwen Intricate Natural Language Processing made easier with Symbolic Computation software: Pattern Matching lessons from Bracmat. Bart Jongejan Learning metrical stress systems using finite-state machines. Cesko Voeten and Menno Van Zaanen Mapping Leiden: Automatically extracting street names from digitized newspaper articles. Kim Groeneveld and Menno van Zaanen Multimodal distributional semantic models and conceptual representations in sensory deprived subjects. Giovanni Cassani and Alessandro Lopopolo Querying Parallel Treebanks with GrETEL. Vincent Vandeghinste, Liesbeth Augustinus and Tom Vanallemeersch Reordering Grammar Induction. Milos Stanojevic and Khalil Simaan Semantic Relatedness and Textual Entailment via Corpus Patterns. Ngoc Phuoc An Vo and Octavian Popescu Skipping meals, skipping words, and how the latter can benefit you and the first just makes you hungry. Louis Onrust Sustainability report readability prediction: an NLP expansion on the tried-and-true formulae. Nils Smeuninx, Orphée Declercq, Véronique Hoste and Bernard De Clerck Task specific warping of word vector representations using limited labeled data. Paul Neculoiu, Chao Li, Carsten Lygteskov Hansen and Mihai Rotaru Unbiased Expectations for Statistical Machine Translation. Wilker Aziz |
||||
| Session 2 14:20 / 15:40 | Event/Relation Extraction
Tommaso Caselli |
Machine Translation
Vincent Vandeghinste |
Social Media
Suzan Verberne |
Distributional Semantics
Malvina Nissim |
|---|---|---|---|---|
| 14:20 | Details from a distance? A Dutch pipeline for event detection Chantal van Son, Marieke van Erp, Antske Fokkens, Paul Huygen, Ruben Izquierdo Bevia and Piek Vossen |
Wikification for Implicit MT evaluation Iris Hendrickx and Antal van Den Bosch |
Exploring the realization of irony in Twitter data Cynthia Van Hee, Els Lefever and Véronique Hoste |
Augmenting recurrent neural network language models with subword information Lyan Verwimp, Joris Pelemans, Hugo Van Hamme and Patrick Wambacq |
| 14:40 | The Event and Implied Situation Ontology (ESO) Roxane Segers and Piek Vossen |
Machine translation with source predicted target morphology Joachim Daiber and Khalil Simaan |
Detecting racism in Dutch social media posts Stéphan Tulkens, Lisa Hilte, Elise Lodewyckx, Ben Verhoeven and Walter Daelemans |
Leveraging psycholinguistic data to evaluate Dutch semantic models Emiel van Miltenburg |
| 15:00 | Discrete-State autoencoders for joint discovery and factorization of relations Diego Marcheggiani and Ivan Titov |
Modelling adjunction in hierarchical phrase-based SMT Sophie Arnoult and Khalil Sima’an |
Personality traits on Twitter for less-resourced languages Barbara Plank, Ben Verhoeven and Walter Daelemans |
Very quaffable and great fun: Applying NLP to wine reviews Els Lefever, Iris Hendrickx and Antal van den Bosch |
| 15:20 | Clause analysis: using syntactic information to identify who is attacking whom in political news Wouter Van Atteveldt, Tamir Sheafer, Shaul Shenhav and Yair Foger-Dror |
Text clustering for improved statistical machine translation Bushra Jawaid and Amir Kamran |
This concert was an anticipointment’: Automatically detecting emotion in open domain event reports on Twitter Florian Kunneman and Antal van den Bosch |
Topic-guided token cloud visualisation. Thomas Wielfaert, Kris Heylen, Dirk Geeraerts and Dirk Speelman |
| 15:40 – 16:10 | COFFEE BREAK | |||
|---|---|---|---|---|
| Session 3 16:10 – 17:10 | Corpus Analysis Linguistic IE
Sander Wubben |
Shared Task & STIL Presentation
Ruben Izquierdo |
Social Media
Isa Maks |
Human Language Learning
Grzegorz Chrupala
|
|---|---|---|---|---|
| 16:10 | Extracting present perfects from a multilingual corpus Martijn van der Klis, Bert Le Bruyn and Henriette de Swart |
Introduction Antske Fokkens Rule-Based Coreference Resolution for Dutch Rob van der Goot, Hessel Haagsma and Dieke Oele Running Frog on the CLIN26 NER task Iris Hendrickx, Ko van der Sloot, Maarten van Gompel and Antal van den Bosch |
Delving deeper into the (Dutch) Twitter tribal language hierarchy Hans Van Halteren and Nelleke Oostdijk |
Distributional bootstrapping with memory-based learning Giovanni Cassani, Robert Grimm, Steven Gillis and Walter Daelemans |
| 16:30 | A multi-agent model approach to resemanticization in pronominal agreement in Dutch Roxana Radulescu and Katrien Beuls |
Rule based classification of events and factuality Iris Monster and Iris Hendrickx-Dekkers Event detection and event factuality classification for shared task Oliver Louwaars and Chris Pool |
Character-level modeling of noisy microposts Fréderic Godin, Wesley De Neve and Rik Van de Walle |
Modeling the impact of contextual diversity on word learning Robert Grimm, Giovanni Cassani, Walter Daelemans and Steven Gillis |
| 16:50 | Lexical preferences in Dutch verbal cluster ordering Jelke Bloem, Arjen Versloot and Fred Weerman |
STIL winner presentation: Explaining relationships between entities Nikos Voskarides | Text-based age and gender prediction for online safety monitoring Janneke van de Loo, Guy De Pauw and Walter Daelemans |
Automatic detection and correction of preposition errors in learners’ Dutch Lennart Kloppenburg and Malvina Nissim |
| 17:10 – 18:10 | DRINKS | |||
|---|---|---|---|---|