The University of Helsinki Language Technology group has a number of papers at The 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19). Here’s where you can find us. See you in Turku!

Monday September 30:

NLP4CALL workshop:

• 13:15. Mathias Creutz, Eetu Sjöblom: “Toward automatic improvement of language produced by non-native language learners”

Constraint Grammar – Methods, Tools, and Applications workshop:

• 14:15. Anssi Yli-Jyrä: “Constraint Grammar Is a Hand-Crafted Transformer”

Tuesday 01 October:

Oral presentations:
Parallel session B: Morphology and Syntax.

• 13:45. Ilmari Kylliäinen and Miikka Silfverberg: “Ensembles of Neural Morphological Inflection Models”

Posters:

• 16:45. Jeff Ens, Mika Hämäläinen, Jack Rueter and Philippe Pasquier: “Morphosyntactic Disambiguation in an Endangered Language Setting”

Demos:

• 16:45. Mikko Aulamo and Jörg Tiedemann: “The OPUS Resource Repository: An Open Package for Creating Parallel Corpora and Machine Translation Services”

Wednesday 02 October

Oral presentations:
Parallel session B: Speech.

• 14:50. Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann and Martti Vainio: “Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations”

Professor Jörg Tiedemann gave a talk at the Charles University in Czech Republic on the 18th June as part of their Fred Jelinek Seminar Series.

Abstract:

Found in Translation – Learning to understand languages with cross-lingual grounding

Translated texts are semantic mirrors of the original text and the significant variations that we can observe across languages can be used to disambiguate the meaning of a given expression using the linguistic signal that is grounded in translation. We are interested in massively parallel corpora consisting of hundreds up to a thousand different languages and how they can be applied as implicit supervision to learn abstractions that could lead to significant improvements in natural language understanding. As a side-effect, we can also see how multilingual models can pick up essential relationships between languages building a continuous space with reasonable language clusters. I will talk about some initial results and plans for the future and I would like to get your feedback about those ideas.