Program

Detailed Program

Monday September 30, 2019 Workshops

Time Session Room
08:00-09:00 Registration  
  Workshops  
09:00-17:00 NLPL Workshop on Deep Learning for Natural Language Processing PUB2
09:00-17:30 NLP for Computer-Assisted Language Learning (NLP4CALL) PUB5
09:00-15:30 Constraint Grammar - Methods, Tools and Applications PUB 209
14:00-17:00 Workshop on NLP and Pseudonymisation PUB4
09:00-15:30 Financial Narrative Processing Workshop (FNP 2019) PUB 126
10:00-10:30 Coffee break  
12:00-14:00 Lunch break Holiday Club Caribia
15:00-15:30 Coffee break  
19:00 Welcome Reception in the Turku City Hall  

Tuesday October 1, 2019

Time Session Room
09:00-09:15 Opening PUB1
09:15-10:05 Keynote by Marie-Catherine de Marneffe: Do you know that there’s still a chance? Identifying speaker commitment for natural language understanding
Chair: Joakim Nivre
PUB1
10:05-10:35 Coffee break  
10:35-12:15 Parallel session A: Multilinguality and Machine Translation
Chair: Jörg Tiedemann
PUB1
10:35-11:00 Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated Content.
José Carlos Rosales Nuñez, Djamé Seddah and Guillaume Wisniewski.
 
11:00-11:25 Bootstrapping UD treebanks for Delexicalized Parsing.
Prasanth Kolachina and Aarne Ranta.
 
11:25-11:50 Lexical Resources for Low-Resource PoS Tagging in Neural Times.
Barbara Plank and Sigrid Klerke.
 
11:50-12:15 Toward Multilingual Identification of Online Registers.
Veronika Laippala, Roosa Kyllönen, Jesse Egbert, Douglas Biber and Sampo Pyysalo.
 
10:35-12:15 Parallel session B: Embeddings, Biases and Language Change
Chair: Richard Johansson
PUB3
10:35-11:00 Gender Bias in Pretrained Swedish Embeddings.
Magnus Sahlgren and Fredrik Olsson.
 
11:00-11:25 A larger-scale evaluation resource of terms and their shift direction for diachronic lexical semantics.
Astrid van Aggelen, Antske Fokkens, Laura Hollink and Jacco van Ossenbruggen.
 
11:25-11:50 Some steps towards the generation of diachronic WordNets.
Yuri Bizzoni, Marius Mosbach, Deitrich Klakow and Stefania Degaetano-Ortlieb.
 
11:50-12:15 An evaluation of Czech word embeddings.
Karolína Hořeňovská.
 
12:15-13:45 Lunch break Holiday Club Caribia
13:45-15:00 Parallel session A: Semantics
Chair: Marianna Apidianaki
PUB1
13:45-14:10 Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions.
Adam Ek, Jean-Philippe Bernardy and Shalom Lappin.
 
14:10-14:35 Comparing linear and neural models for competitive MWE identification.
Hazem Al Saied, Marie Candito and Mathieu Constant.
 
14:35-15:00 A Wide-Coverage Symbolic Natural Language Inference System.
Stergios Chatzikyriakidis and Jean-Philippe Bernardy.
 
13:45-15:00 Parallel session B: Morphology and Syntax
Chair: Kairit Sirts
PUB3
13:45-14:10 Ensembles of Neural Morphological Inflection Models.
Ilmari Kylliäinen and Miikka Silfverberg.
 
14:10-14:35 Nefnir: A high accuracy lemmatizer for Icelandic.
Svanhvít Lilja Ingólfsdóttir, Hrafn Loftsson, Jón Friðrik Daðason and Kristín Bjarnadóttir.
 
14:35-15:00 Syntax-based identification of light-verb constructions.
Silvio Ricardo Cordeiro and Marie Candito.
 
15:00-15:30 Coffee Break  
15:30-16:45 Parallel session A: Machine Learning Applications, Text Classification
Chair: Jenna Kanerva
PUB1
15:30-15:55 Natural Language Processing in Policy Evaluation: Extracting Policy Conditions from IMF Loan Agreements.
Joakim Åkerström, Adel Daoud and Richard Johansson.
 
15:55-16:20 Comparing the Performance of Feature Representations for the Categorization of the Easy-to-Read Variety vs Standard Language.
Marina Santini, Benjamin Danielsson and Arne Jönsson.
 
16:20-16:45 Unsupervised Inference of Object Affordance from Text Corpora.
Michele Persiani and Thomas Hellström.
 
15:30-16:45 Parallel session B: Language Resources and Applications
Chair: Elena Volodina
PUB3
15:30-15:55 Annotating evaluative sentences for sentiment analysis: a dataset for Norwegian.
Petter Mæhlum, Jeremy Claude Barnes, Lilja Øvrelid and Erik Velldal.
 
15:55-16:20 Interconnecting lexical resources and word alignment: How do learners get on with particle verbs?
David Alfter and Johannes Graën.
 
16:20-16:45 An Unsupervised Query Rewriting Approach Using N-gram Co-occurrence Statistics to Find Similar Phrases in Large Text Corpora.
Hans Moen, Laura-Maria Peltonen, Henry Suhonen, Hanna-Maria Matinolli, Riitta Mieronkoski, Kirsi Telen, Kirsi Terho, Tapio Salakoski and Sanna Salanterä.
 
16:45-17:45 Poster and demo session Entrance hall
16:45-17:45 Posters:  
  Compiling and Filtering ParIce: An English-Icelandic Parallel Corpus.
Starkaður Barkarson and Steinþór Steingrímsson.
 
  May I Check Again? — A simple but efficient way to generate and use contextual dictionaries for Named Entity Recognition. Application to French Legal Texts.
Valentin Barriere and Amaury Fouret.
 
  Predicates as Boxes in Bayesian Semantics for Natural Language.
Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin and Aleksandre Maskharashvili.
 
  DIM: The Database of Icelandic Morphology.
Kristín Bjarnadóttir, Kristín Ingibjörg Hlynsdóttir and Steinþór Steingrímsson.
 
  Bornholmsk Natural Language Processing: Resources and Tools.
Leon Derczynski and Alex Speed Kjeldsen.
 
  Morphosyntactic Disambiguation in an Endangered Language Setting.
Jeff Ens, Mika Hämäläinen, Jack Rueter and Philippe Pasquier.
 
  Tagging a Norwegian Dialect Corpus.
Andre Kåsen, Anders Nøklestad, Kristin Hagen and Joel Priestley.
 
  The Lacunae of Danish Natural Language Processing.
Andreas Kirkedal, Barbara Plank, Leon Derczynski and Natalie Schluter.
 
  Tools for supporting language learning for Sakha.
Sardana Ivanova, Anisia Katinskaia and Roman Yangarber.
 
  Inferring morphological rules from small examples using 0/1 linear programming.
Ann Lillieström, Koen Claessen and Nicholas Smallbone.
 
16:45-17:45 Demos:  
  LEGATO: A flexible lexicographic annotation tool.
David Alfter, Therese Lindström Tiedemann and Elena Volodina.
 
  The OPUS Resource Repository: An Open Package for Creating Parallel Corpora and Machine Translation Services.
Mikko Aulamo and Jörg Tiedemann.
 
  Garnishing a phonetic dictionary for ASR intake.
Iben Nyholm Debess, Sandra Saxov Lamhauge and Peter Juel Henrichsen.
 
  Docria: Processing and Storing Linguistic Data with Wikipedia.
Marcus Klang and Pierre Nugues.
 
  UniParse: A universal graph-based parsing toolkit.
Daniel Varab and Natalie Schluter.
 
19:30-23:00 Conference Dinner in the Turku Castle  

Wednesday October 2, 2019

Time Session Room
09:00-09:50 Keynote by Grzegorz Chrupała: Investigating Neural Representations of Speech and Language
Chair: Lilja Øvrelid
PUB1
09:50-10:20 Coffee break  
10:20-12:00 Parallel session A: Sentiment Analysis and Stance
Chair: Mathias Creutz
PUB1
10:20-10:45 Lexicon information in neural sentiment analysis: a multi-task learning approach.
Jeremy Claude Barnes, Samia Touileb, Lilja Øvrelid and Erik Velldal.
 
10:45-11:10 Aspect-Based Sentiment Analysis using BERT.
Mickel Hoang, Oskar Alija Bihorac and Jacobo Rouces.
 
11:10-11:35 Political Stance Detection for Danish.
Rasmus Lehmann and Leon Derczynski.
 
11:35-12:00 Joint Rumour Stance and Veracity Prediction.
Anders Edelbo Lillie, Emil Refsgaard Middelboe and Leon Derczynski.
 
10:20-12:00 Parallel session B: Named Entity Recognition
Chair: Manex Agirrezabal
PUB3
10:20-10:45 Towards High Accuracy Named Entity Recognition for Icelandic.
Svanhvít Lilja Ingólfsdóttir, Sigurjón Þorsteinsson and Hrafn Loftsson.
 
10:45-11:10 Named-Entity Recognition for Norwegian.
Bjarte Johansen.
 
11:10-11:35 Neural Cross-Lingual Transfer and Limited Annotated Data for Named Entity Recognition in Danish.
Barbara Plank.
 
11:35-12:00 Projecting named entity recognizers without annotated or parallel corpora.
Jue Hou, Maximilian Koppatz, José María Hoya Quecedo and Roman Yangarber.
 
12:00-13:00 Lunch break Holiday Club Caribia
13:00-14:00 NEALT business meeting PUB1
14:00-15:15 Parallel session A: Text Generation and Language Model Applications
Chair: Leon Derczynski
PUB1
14:00-14:25 Template-free Data-to-Text Generation of Finnish Sports News.
Jenna Kanerva, Samuel Rönnqvist, Riina Kekki, Tapio Salakoski and Filip Ginter.
 
14:25-14:50 Matching Keys and Encrypted Manuscripts.
Eva Pettersson and Beata Megyesi.
 
14:50-15:15 The Seemingly (Un)systematic Linking Element in Danish.
Sidsel Boldsen and Manex Agirrezabal.
 
14:00-15:15 Parallel session B: Speech
Chair: Grzegorz Chrupała
PUB3
14:00-14:25 Perceptual and acoustic analysis of voice similarities between parents and young children.
Evgeniia Rykova and Stefan Werner.
 
14:25-14:50 Enhancing Natural Language Understanding through Cross-Modal Interaction: Meaning Recovery from Acoustically Noisy Speech.
Ozge Alacam.
 
14:50-15:15 Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations.
Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann and Martti Vainio.
 
15:15-15:45 Coffee Break  
15:45-16:25 Tutorial on Finnish by Fred Karlsson
Chair: Filip Ginter
PUB1
16:25-16:35 Closing and announcement of NoDaLiDa’21 PUB1