Programme

Overall programme for CLIN20 on Friday February 5th.

Every registered attendee will also receive a personalized schedule at CLIN20 itself.

Room 0.03 Room 0.05 Room 0.06 Room 1.05 Room 1.09
09:00-09:30 Registration and coffee. Drift 21
09:30-09:50 Parallel identification of the spelling variants in OCR-ed, historical corpora.
M. Reynaert		 Using social media for ontology enrichment.
P. Monachesi, T. Markus		 Evaluation of a Dynamic Bayesian Network Framework for Transliteration Similarity Estimation.
P. Nabende		 Finding Constraints for Semantic Relations.
S. Katrenko		 A Chunk-Driven Bootstrapping Approach to Extracting Translation Patterns.
L. Macken, W. Daelemans
09:50-10:10 Acquiring Competence from Performance Data: Online learnability of OT and HG with simulated annealing.
T. Biro		 Checking the Official Dutch Wordlist for Gender Inconsistencies.
J. Korst, G. Geleijnse		 A context-based approach to minimize unknown words in user search queries.
R. Hielkema		 Acquiring a reference corpus for written Dutch.
O. De Clercq, M. Reynaert		 Detecting semantic similarity using syntactic tree alignment.
E. Marsi, E. Krahmer
10:10-10:30 Memory-based approaches to event extraction from biomedical texts.
R. Morante, V. Van Asch, W. Daelemans		 Monolingual translation for headline paraphrasing.
S. Wubben, A. van den Bosch, E. Krahmer		 Weigh your words: memory-based lemma retrieval for Middle Dutch literary texts.
M. Kestemont, W. Daelemans, G. De Pauw		 Improving Successor Variety for Unsupervised Morphological Segmentation.
Ç. Çöltekin		 Bottom-up vs. Top-down Transfer in Example-Based Machine Translation.
V. Vandeghinste, S. Martens
10:30-10:50 Cross-lingual Word Sense Disambiguation.
E. Lefever, V. Hoste		 Dutch dependency parser performance across domains.
B. Plank, G. van Noord		 Co-clustering varieties and linguistic features using bipartite spectral graph partitioning.
M. Wieling, J. Nerbonne		 A Practical Application of Language Technology.
D.N. de Vries		 Recent Advances in Temporal Processing of Text.
O. Kolomiyets, M. Moens
10:50-11:10 Coffee break.
Senaatszaal, Academiegebouw
11:10-11:15 Welcome by director UiL-OTS.
Martin Everaert
Aula, Academiegebouw
11:15-11:20 30 Years Nederlandse Taalunie.
Linde van den Bosch
Aula, Academiegebouw
11:20-11:30 CLARIN-NL.
Jan Odijk
Aula, Academiegebouw
11:30-11:40 STIL thesis prize.
Aula, Academiegebouw
11:40-12:40 Invited talk: Social attention in the age of the web.
Bernardo Huberman.
Aula, Academiegebouw
12:40-13:40 Lunch break.
Senaatszaal, Academiegebouw
13:40-14:00 Fluency Ranking for Dutch.
D. de Kok, G. van Noord		 A Probabilistic Language Model à la Tesnière.
F. Sangati		 Looking beyond the single link: towards improved semantic similarity recognition?
H. van Halteren		 Processing the scope of negation and hedge cues in biomedical texts: a comparative study.
R. Morante Vallejo, W. Daelemans		 An overview of Caliss: Open source treebank pattern miner.
S.A. Martens
14:00-14:20 Temporal Processing of Electronic Health Records.
M. Verhagen, A. Stubbs, J. Pustejovsky		 Syntax-based Automatic Segmentation of Dutch Text.
N. van der Vliet		 Age Predicting from Speech Production.
J. Geertzen		 Retrieving semantically similar words in Dutch. A comparison of type- and token-based distributional models.
K. Heylen, D. Speelman, D. Geeraerts		 MaxEnt syntax-based reordering model for statistical machine translation.
M. Khalilov, K. Sima’an
14:20-14:40 Automated Lexical Acquisition for Parsing.
K. Cholakov		 Domain Adaptation for Statistical MT using Models with Decaying Cache.
J. Tiedemann		 LASSY for Beginners.
E. Tjong Kim Sang, G. Bouma, G. van Noord		 Advances in Memory Based Language Modeling.
P. Berck, A. van den Bosch		 Supporting knowledge discovery in an eLearning environment having social components.
P. Monachesi, T. Markus, V. Posea, S. Trausan-Matu, P. Osenova, K. Simov
14:40-15:00 Class division as an alternative to downsampling.
M. van Zaanen		 A Hunter is a Jager is a Jäger. Translating Selectional Preferences with Bilingual Vector Spaces.
Y. Peirsman, S. Padó		 Modifying the granularity of automatically-defined word senses.
M. Apidianaki		 Dependency parsing and semantic role labeling: Variants of a single task.
A. van den Bosch, R. Morante		 Sustainable operability: Keeping complex linguistic resources alive.
M. Windhouwer, A. Dimitriadis
15:00-16:00 Poster session & coffee break.
Hall, Drift 21
16.00-16.20 Evaluation of pair HMMs and Trigram models for Transliteration Identification.
P. Nabende		 A DOP-inspired approach to syntactic category induction.
M. Smets		 Forward-backward tagging based on a hybrid model.
Y. Zhao, G. van Noord, J. Nerbonne		 Towards a balanced named entity corpus for Dutch.
B. Desmet, V. Hoste		 A quantitative evaluation of semantic word space models.
T. Van de Cruys
16.20-16.40 Mereological and Meronymic Relations for Learning Part-Whole Patterns.
A. Ittoo, G. Bouma		 Extending Memory-Based Machine Translation to Phrases.
M. van Gompel, A. van den Bosch, P. Berck		 Using suffix trees as language models: Scaling the n-gram.
H. Stehouwer, M. van Zaanen		 Modeling normal and impaired knowledge of semantic constraints on adjective order without explicit constraints.
B. Vandekerckhove, D. Sandra, W. Daelemans		 Emotion Classification in a Serious Game for Training Communication Skills.
F. Vaassen, W. Daelemans
16.40-17.00 Mining treebanks to make subtree matching during translation more efficient.
J. Van den Bogaert, S. Martens		 Automatic Extraction of Antonymous Verbs.
A. Lobanova, J. Spenader		 Dutch Parallel Corpus: a new parallel corpus with Dutch as central language.
O. De Clercq, L. Macken, H. Paulussen, M. Montero Perez, P. Desmet, W. Vandeweghe		 A mother- daughter machine.
C. Cremers, M. Hijzelendoorn, D. Shakouri		 A System for Large-Scale Bootstrapping of Synonyms in Taxonomies.
M. Spitters, R. Bonnema, M. Rotaru, J. Zavrel
17:00-19:00 Drinks & CLIN20 celebrations.
Senaatszaal, Academiegebouw