Göm menyn

Title:
NEAL Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland
Download:
Full text (pdf)
Editor(s):
Mareike Hartman: University of Copenhagen, Denmark Barbara Plank: ITU Copenhagen, Denmark
Year:
2019
No. of pages:
410
Language:
English
ISBN:
978-91-7929-995-8
Series:
Linköping Electronic Conference Proceedings
Issue:
167
ISSN (print):
1650-3686
ISSN (online):
1650-3740
Series:
NEALT Proceedings Series
Issue:
42
Published:
2019-10-02
Publisher:
Linköping University Electronic Press, Linköpings universitet



Welcome to the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa 2019) held at the University of Turku in the beautiful city of Turku in Finland, on September 30-October 2, 2019. The aim of NoDaLiDa is to bring together researchers in the Nordic countries interested in any aspect related to human language and speech technologies. It is a great honor for me to serve as the general chair of NoDaLiDa 2019.

NoDaLiDa has a very long tradition. It stems from a working group initiative led by Sture Allèn, Kolbjörn Heggstad, Baldur Jönsson, Viljo Kohonen and Bente Maegaard (as the preface of the oldest workshop proceedings in the ACL anthology reveals).1 They organized the first NoDaLiDa (“Nordiska datalingvistikdagar”) in Gothenburg on October 10-11, 1977. In 2006, NEALT, the Northern European Association for Language Technology was founded. We are very honored to bring this bi-annual conference after 42 years to Turku this fall.

We solicited three different types of papers (long, short, demo papers) and received 78 valid submissions. In total, we accepted 49 papers, which will be presented as 34 oral presentations, 10 posters and 5 demo papers. A total of 4 submissions were withdrawn in the process. Each paper was reviewed by three experts. We are extremely grateful to the Programme Committee members for their detailed and helpful reviews. Overall, there are 10 oral sessions with talks and one poster session organized into themes over the two days, starting each day with a keynote talk.

We would like to thank our two keynote speakers for travel to Turku and sharing their work. Marie-Catherine de Marneffe from Ohio State University will talk about "Do you know that there’s still a chance? Identifying speaker commitment for natural language understanding". Grzegorz Chrupala from Tilburg University will talk about "Investigating neural representations of speech and language". We are also very grateful to Fred Karlsson, who accepted to share his insights into the Finnish language in the traditional NoDaLiDa language tutorial.

The conference is preceded by 5 workshops on a diverse set of topics: deep learning for natural language processing, NLP for Computer-Assisted Language Learning, Constraint Grammar Methods, Tools and Applications, NLP and pseudonymisation and Financial Narrative Processing. This shows the breadth of topics that can be found in language technology these days, and we are extremely happy and grateful to the workshop organizers for complementing the main program this way.

There will be two social events. A reception which is sponsored by the City of Turku and held at the Old Town Hall in Turku. A conference dinner will be held in the Turku Castle in the King’s hall. Two fantastic evenings are awaiting.

I would like to thank the entire team that made NoDaLiDa 2019 possible in the first place. First of all, I would like to thank Beáta Megyesi for inviting me to take up this exciting (and admittedly at times demanding) role and all her valuable input regarding NEALT and previous editions of NoDaLiDa. Jörg Tiedemann, for the smooth transition from the previous NoDaLiDa edition and his input and work as program chair; the program chair committee Jurgita Kapo?ci¯ut?e-Dzikien?e, Hrafn Loftsson, Patrizia Paggio, and Erik Velldal, for working hard on putting the program together. I am particularly grateful to Jörg Tiedemann, Jurgita Kapo?ci¯ut?e-Dzikien?e, Kairit Sirts and Patrizia Paggio for leading the reviewing process. Special thanks goes to the workshop chairs Richard Johansson and Kairit Sirts, who have done an invaluable job with leading the workshop selection and organization. A big thanks also to Miryam de Lhoneux for her work as social media chair and Mareike Hartmann for leading the publication efforts that led to this volume, as well as the coordination of the workshop proceedings. Thank you! Finally, my ultimate thanks goes to the amazing local organization committee and team. Thank you, Filip Ginter and Jenna Kanerva. With your infinite support and pro-active engagement in organizing NoDaLiDa you are the ones that make NoDaLiDa possible and surely an unforgettable experience. Thanks also to the entire local team (with special thanks to Hans Moen for help with the program): Li-Hsin Chang, Rami Ilo, Suwisa Kaewphan, Kai Hakala, Roosa Kyllönen, Veronika Laippala, Akseli Leino, Juhani Luotolahti, Farrokh Mehryary, Hans Moen, Maria Pyykönen, Sampo Pyysalo, Samuel Rönnqvist, Antti Saloranta, Antti Virtanen, Sanna Volanen. NoDaLiDa 2019 has received financial support from our generous sponsors, which we would also like to thank here.

This is the usual place for the greetings from the local organizers, but as we set out to write it, it turns out that Barbara already said it all. So we really only need to add one thing: huge thanks to Barbara for all the hard work she put into NoDaLiDa. We can only wonder where you found the time for all this. We hope the Turku edition of NoDaLiDa will be a success, at least we tried our best to make it so. In two weeks we will know. — Filip, Jenna, and the local team

Danke - kiitos!

We very much hope that you will have an enjoyable and inspiring time at NoDaLiDa 2019 in Turku.

Barbara Plank

København

September 2019



NEAL Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland

167:001
José Carlos Rosales Nuñez, Djamé Seddah, Guillaume Wisniewski
Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated Content
[Abstract and Fulltext]

167:002
Prasanth Kolachina, Aarne Ranta
Bootstrapping UD treebanks for Delexicalized Parsing
[Abstract and Fulltext]

167:003
Barbara Plank, Sigrid Klerke
Lexical Resources for Low-Resource PoS Tagging in Neural Times
[Abstract and Fulltext]

167:004
Magnus Sahlgren, Fredrik Olsson
Gender Bias in Pretrained Swedish Embeddings
[Abstract and Fulltext]

167:005
Astrid van Aggelen, Antske Fokkens, Laura Hollink, Jacco van Ossenbruggen
A larger-scale evaluation resource of terms and their shift direction for diachronic lexical semantics
[Abstract and Fulltext]

167:006
Yuri Bizzoni, Marius Mosbach, Dietrich Klakow, Stefania Degaetano-Ortlieb
Some steps towards the generation of diachronic WordNets
[Abstract and Fulltext]

167:007
Karolína Horenovská
An evaluation of Czech word embeddings
[Abstract and Fulltext]

167:008
Adam Ek, Jean-Phillipe Bernardy, Shalom Lappin
Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions
[Abstract and Fulltext]

167:009
Hazem Al Saied, Marie Candito, Mathieu Constant
Comparing linear and neural models for competitive MWE identification
[Abstract and Fulltext]

167:010
Silvio Ricardo Cordeiro, Marie Candito
Syntax-based identification of light-verb constructions
[Abstract and Fulltext]

167:011
Marina Santini, Benjamin Danielsson, Arne Jönsson
Comparing the Performance of Feature Representations for the Categorization of the Easy-to-Read Variety vs Standard Language
[Abstract and Fulltext]

167:012
Michele Persiani, Thomas Hellström
Unsupervised Inference of Object Affordance from Text Corpora
[Abstract and Fulltext]

167:013
Petter Mæhlum, Jeremy Barnes, Lilja Øvrelid, Erik Velldal
Annotating evaluative sentences for sentiment analysis: a dataset for Norwegian
[Abstract and Fulltext]

167:014
Hans Moen, Laura-Maria Peltonen, Henry Suhonen, Hanna-Maria Matinolli, Riitta Mieronkoski, Kirsi Telen, Kirsi Terho, Tapio Salakoski, Sanna Salanterä
An Unsupervised Query Rewriting Approach Using N-gram Co-occurrence Statistics to Find Similar Phrases in Large Text Corpora
[Abstract and Fulltext]

167:015
Starkaður Barkarson, Steinþór Steingrímsson
Compiling and Filtering ParIce: An English-Icelandic Parallel Corpus
[Abstract and Fulltext]

167:016
Kristín Bjarnadóttir, Kristín Ingibjörg Hlynsdóttir, Steinþór Steingrímsson
DIM: The Database of Icelandic Morphology
[Abstract and Fulltext]

167:017
Sardana Ivanova, Anisia Katinskaia, Roman Roman
Tools for supporting language learning for Sakha
[Abstract and Fulltext]

167:018
Ann Lillieström, Koen Claessen, Nicholas Smallbone
Inferring morphological rules from small examples using 0/1 linear programming
[Abstract and Fulltext]

167:019
Jeremy Barnes, Samia Touileb, Lilja Øvrelid, Erik Velldal
Lexicon information in neural sentiment analysis: a multi-task learning approach
[Abstract and Fulltext]

167:020
Mickel Hoang, Oskar Alija Bihorac, Jacobo Rouces
Aspect-Based Sentiment Analysis using BERT
[Abstract and Fulltext]

167:021
Rasmus Lehmann, Leon Derczynski
Political Stance in Danish
[Abstract and Fulltext]

167:022
Anders Edelbo Lillie, Emil Refsgaard Middelboe, Leon Derczynski
Joint Rumour Stance and Veracity Prediction
[Abstract and Fulltext]

167:023
Bjarte Johansen
Named-Entity Recognition for Norwegian
[Abstract and Fulltext]

167:024
Jue Hou, Maximilian W. Koppatz, José María Hoya Quecedo, Roman Yangarber
Projecting named entity recognizers without annotated or parallel corpora
[Abstract and Fulltext]

167:025
Jenna Kanerva, Samuel Rönnqvist, Riina Kekki, Tapio Salakoski, Filip Ginter
Template-free Data-to-Text Generation of Finnish Sports News
[Abstract and Fulltext]

167:026
Eva Pettersson, Beáta Megyesi
Matching Keys and Encrypted Manuscripts
[Abstract and Fulltext]

167:027
Evgeniia Rykova, Stefan Werner
Perceptual and acoustic analysis of voice similarities between parents and young children
[Abstract and Fulltext]

167:028
Özge Alaçam
Enhancing Natural Language Understanding through Cross-Modal Interaction: Meaning Recovery from Acoustically Noisy Speech
[Abstract and Fulltext]

167:029
Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann, Martti Vainio
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
[Abstract and Fulltext]

167:030
Veronika Laippala, Roosa Kyllönen, Jesse Egbert, Douglas Biber, Sampo Pyysalo
Toward Multilingual Identification of Online Registers
[Abstract and Fulltext]

167:031
Jean-Philippe Bernardy, Stergios Chatzikyriakidis
A Wide-Coverage Symbolic Natural Language Inference System
[Abstract and Fulltext]

167:032
Ilmari Kylliäinen, Miikka Silfverberg
Ensembles of Neural Morphological Inflection Models
[Abstract and Fulltext]

167:033
Svanhvít Ingólfsdóttir, Hrafn Loftsson, Jón Daðason, Kristín Bjarnadóttir
Nefnir: A high accuracy lemmatizer for Icelandic
[Abstract and Fulltext]

167:034
Joakim Åkerström, Adel Daoud, Adel Daoud
Natural Language Processing in Policy Evaluation: Extracting Policy Conditions from IMF Loan Agreements
[Abstract and Fulltext]

167:035
David Alfter, Johannes Graën
Interconnecting lexical resources and word alignment: How do learners get on with particle verbs?
[Abstract and Fulltext]

167:036
Valentin Barriere, Amaury Fouret
May I Check Again? — A simple but efficient way to generate and use contextual dictionaries for Named Entity Recognition. Application to French Legal Texts
[Abstract and Fulltext]

167:037
Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin, Aleksandre Maskharashvili
Predicates as Boxes in Bayesian Semantics for Natural Language
[Abstract and Fulltext]

167:038
Leon Strømberg Derczynski, Alex Speed Kjeldsen
Bornholmsk Natural Language Processing: Resources and Tools
[Abstract and Fulltext]

167:039
Jeff Ens, Mika Hämäläinen, Jack Rueter, Philippe Pasquier
Morphosyntactic Disambiguation in an Endangered Language Setting
[Abstract and Fulltext]

167:040
Andre Kåsen, Kristin Hagen, Anders Nøklestad, Joel Priestley
Tagging a Norwegian Dialect Corpus
[Abstract and Fulltext]

167:041
Andreas Kirkedal, Barbara Plank, Leon Derczynski, Natalie Schluter
The Lacunae of Danish Natural Language Processing
[Abstract and Fulltext]

167:042
Svanhvít Ingólfsdóttir, Sigurjó Þorsteinsson, Hrafn Loftsson
Towards High Accuracy Named Entity Recognition for Icelandic
[Abstract and Fulltext]

167:043
Barbara Plank
Neural Cross-Lingual Transfer and Limited Annotated Data for Named Entity Recognition in Danish
[Abstract and Fulltext]

167:044
Sidsel Boldsen, Manex Agirrezabal
The Seemingly (Un)systematic Linking Element in Danish
[Abstract and Fulltext]

167:045
David Alfter, Therese Lindström Tiedemann, Elena Volodina
LEGATO: A flexible lexicographic annotation tool
[Abstract and Fulltext]

167:046
Mikko Aulamo, Jörg Tiedemann
The OPUS Resource Repository: An Open Package for Creating Parallel Corpora and Machine Translation Services
[Abstract and Fulltext]

167:047
Iben Nyholm Debess, Sandra Saxov Lamhauge, Peter Juel Juel Henrichsen
Garnishing a phonetic dictionary for ASR intake
[Abstract and Fulltext]

167:048
Marcus Klang, Pierre Nugues
Docria: Processing and Storing Linguistic Data with Wikipedia
[Abstract and Fulltext]

167:049
Daniel Varab, Natalie Schluter
UniParse: A universal graph-based parsing toolkit
[Abstract and Fulltext]

NEAL Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland

Author:
Mareike Hartman, Barbara Plank
Title:
NEAL Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland
Note: the following are taken directly from CrossRef
Citations:
No citations available at the moment


Responsible for this page: Peter Berkesand
Last updated: 2019-11-06