Accepted papers
| ID | Authors | Title | Type |
|---|---|---|---|
| 2 | Mark Anderson and Carlos Gómez-Rodríguez | What Taggers Fail to Learn, Parsers Need the Most | Short |
| 5 | Amalie Brogaard Pauli, Maria Barrett, Ophélie Lacroix and Rasmus Hvingelby | DaNLP: An open-source toolkit for Danish Natural Language Processing | Demo |
| 6 | Mika Hämäläinen, Niko Partanen, Jack Rueter and Khalid Alnajjar | Neural Morphology Dataset and Models for Multiple Languages, from the Large to the Endangered | Long |
| 7 | Yuri Bizzoni and Ekaterina Lapshinova-Koltunski | Measuring Translationese across Levels of Expertise: Are Professionals more Surprising than Students? | Long |
| 9 | Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Paavo Alku and Mikko Kurimo | Spectral modification for recognition of children’s speech undermismatched conditions | Long |
| 10 | Tuomas Kaseva, Hemant Kumar Kathania, Aku Rouhe and Mikko Kurimo | Speaker Verification Experiments for Adults and Children using a shared embedding spaces | Long |
| 13 | Kristian Nørgaard Jensen, Mike Zhang and Barbara Plank | De-identification of Privacy-related Entities in Job Postings | Long |
| 14 | Lifeng Han, Gareth Jones, Alan Smeaton and Paolo Bolzoni | Chinese Character Decomposition for Neural MT with Multi-Word Expressions | Short |
| 17 | Katrin Ortmann | Chunking Historical German | Long |
| 21 | Chaojun Wang, Christian Hardmeier and Rico Sennrich | Exploring the Importance of Source Text in Automatic Post-Editing for Context-Aware Machine Translation | Short |
| 22 | Evelina Rennes and Arne Jönsson | Synonym Replacement based on a Study of Basic-level Nouns in Swedish Texts of Different Complexity | Long |
| 23 | Hanna Berg and Hercules Dalianis | HB Deid - HB De-identification tool demonstrator | Demo |
| 24 | Synnøve Bråthen, Wilhelm Wie and Hercules Dalianis | Creating and Evaluating a Synthetic Norwegian Clinical Corpus for De-Identification | Long |
| 25 | Mila Grancharova and Hercules Dalianis | Applying and Sharing pre-trained BERT-models for Named Entity Recognition and Classification in Swedish Electronic Patient Records | Long |
| 27 | Quan Duong, Mika Hämäläinen and Simon Hengchen | An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish | Long |
| 29 | Tobias Norlund and Agnes Stenbom | Building a Swedish Open-Domain Conversational Language Model | Short |
| 30 | Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis and Jörg Tiedemann |
NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance | Long |
| 32 | Timo Johner, Abhik Jana and Chris Biemann | Error Analysis of using BART for Multi-Document Summarization: A Study for English and German Language | Short |
| 35 | Magnus Sahlgren, Fredrik Carlsson, Fredrik Olsson and Love Börjeson | It’s Basically the Same Language Anyway: the Case for a Nordic Language Model | Short |
| 36 | Antonia Karamolegkou and Sara Stymne | Investigation of Transfer Languages for Parsing Latin: Italic Branch vs. Hellenic Branch | Short |
| 38 | Leon Strømberg-Derczynski, Manuel Ciosici, Rebekah Baglini, Morten H. Christiansen, Jacob Aarup Dalsgaard, Riccardo Fusaroli, Peter Juel Henrichsen, Rasmus Hvingelby, Andreas Kirkedal, Alex Speed Kjeldsen, Claus Ladefoged, Finn Årup Nielsen, Jens Madsen, Malte Lau Petersen, Jonathan Hvithamar Rystrøm and Daniel Varab |
The Danish Gigaword Corpus | Short |
| 40 | Steinþór Steingrímsson, Hrafn Loftsson and Andy Way | CombAlign: a Tool for Obtaining High-Quality Word Alignments | Long |
| 41 | Sampo Pyysalo, Jenna Kanerva, Antti Virtanen and Filip Ginter | WikiBERT Models: Deep Transfer Learning for Many Languages | Long |
| 42 | Per E Kummervold, Javier De la Rosa, Freddy Wetjen and Svein Arne Brygfjeld | Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model | Long |
| 43 | Jarkko Lagus and Arto Klami | Learning to Lemmatize in the Word Representation Space | Long |
| 44 | Yvonne Adesam and Aleksandrs Berdicevskis | Part-of-speech tagging of Swedish texts in the neural era | Long |
| 45 | Jeppe Nørregaard and Leon Derczynski | DanFEVER: claim verification dataset for Danish | Short |
| 47 | Simon Hengchen and Nina Tahmasebi | SuperSim: a test set for word similarity and relatedness in Swedish | Long |
| 48 | Jenna Kanerva, Filip Ginter, Li-Hsin Chang, Iiro Rastas, Valtteri Skantsi, Hanna-Mari Kupari, Jemina Kilpeläinen, Jenna Saarni, Maija Sevón and Otto Tarkka |
Finnish Paraphrase Corpus | Long |
| 49 | Eetu Sjöblom, Mathias Creutz and Teemu Vahtola | Grammatical Error Generation Based on Translated Fragments | Short |
| 50 | Helga Svala Sigurðardóttir, Anna Björk Nikulásdóttir and Jón Guðnason | Creating Data in Icelandic for Text Normalization | Short |
| 52 | Hjalti Daníelsson, Jón Hilmar Jónsson, Þórður Arnar Árnason, Alec Shaw, Einar Freyr Sigurðsson and Steinþór Steingrímsson |
The Icelandic Word Web: A language technology-focused redesign of a lexicosemantic database | Short |
| 53 | Manfred Klenner and Anne Göhring | Getting Hold of Villains and other Rogues | Short |
| 55 | Lovisa Hagström and Richard Johansson | Knowledge Distillation for Swedish NER models: A Search for Performance and Efficiency | Long |
| 64 | Atli Sigurgeirsson, Þorsteinn Gunnarsson, Gunnar Örnólfsson, Eydís Magnúsdóttir, Ragnheiður Þórhallsdóttir, Stefán Jónsson and Jón Guðnason | Talrómur: A large Icelandic TTS corpus | Short |
| 67 | Abdul Aziz Alkathiri, Lodovico Giaretta, Sarunas Girdzijauskas and Magnus Sahlgren | Decentralized Word2Vec Using Gossip Learning | Short |
| 69 | Sidsel Boldsen and Fredrik Wahlberg | Survey and reproduction of computational approaches to dating of historical texts | Long |
| 70 | Juho Leinonen, Sami Virpioja and Mikko Kurimo | Grapheme-Based Cross-Language Forced Alignment: Results with Nordic Languages | Short |
| 71 | Hasan Tanvir, Claudia Kittask, Sandra Eiche and Kairit Sirts | EstBERT: A Pretrained Language-Specific BERT for Estonian | Long |
| 72 | Petter Mæhlum, Jeremy Barnes, Robin Kurtz, Lilja Øvrelid and Erik Velldal | Negation in Norwegian: an annotated dataset | Long |
| 74 | Vinit Ravishankar, Andrey Kutuzov, Lilja Øvrelid and Erik Velldal Multilingual | ELMo and the Effects of Corpus Sampling | Short |
| 76 | Jeremy Barnes, Petter Mæhlum and Samia Touileb | NorDial: A Preliminary Corpus of Written Norwegian Dialect Use | Short |
| 77 | Hinrik Hafsteinsson and Anton Karl Ingason | Towards cross-lingual application of language-specific PoS tagging schemes | Short |
| 78 | Andrey Kutuzov, Jeremy Barnes, Erik Velldal, Lilja Øvrelid and Stephan Oepen | Large-Scale Contextualised Language Modelling for Norwegian | Long |
| 79 | Saga Hansson, Konstantinos Mavromatakis, Yvonne Adesam, Gerlof Bouma and Dana Dannélls | The Swedish Winogender Dataset | Short |
| 80 | Tim Isbister, Fredrik Carlsson and Magnus Sahlgren | Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead? | Short |
| 81 | Leo Leppänen and Hannu Toivonen | A Baseline Document Planning Method for Automated Journalism | Long |
| 82 | Samuel Rönnqvist, Valtteri Skantsi, Miika Oinonen and Veronika Laippala | Multilingual and Zero-Shot is Closing in on Monolingual Web Register Classification | Long |
| 83 | Mikko Aulamo, Sami Virpioja, Yves Scherrer and Jörg Tiedemann | Boosting Neural Machine Translation from Finnish to Northern Sámi with Rule-Based Backtranslation | Short |
| 85 | Maali Tars, Andre Tättar and Mark Fišel | Extremely low-resource machine translation for closely related languages | Long |
| 88 | Prajit Dhar and Arianna Bisazza | Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks | Long |
| 89 | Arild Brandrud Næss, Joakim Olsen and Pierre Lison | Assessing the Quality of Human-Generated Summaries with Weakly Supervised Learning | Long |
| 91 | Jouni Luoma, Li-Hsin Chang, Filip Ginter and Sampo Pyysalo | Fine-grained Named Entity Annotation for Finnish | Long |
| 92 | Elena Volodina, Yousuf Ali Mohammed and Therese Lindström Tiedemann | CoDeRooMor: A new dataset for non-inflectional morphology studies of Swedish | Long |