1 code implementation • COLING (LAW) 2020 • Marta Andersson, Murathan Kurfali, Robert Östling
This paper investigates the semantic prosody of three causal connectives: due to, owing to and because of in seven varieties of the English language.
no code implementations • COLING (MWE) 2020 • Murathan Kurfali, Robert Östling
The unsupervised classification, similarly, yields very impressive results, comparing favorably to the supervised classifier for the majority of the expressions.
no code implementations • ACL (unimplicit) 2021 • Murathan Kurfali, Robert Östling
We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem.
Classification Implicit Discourse Relation Classification +4
1 code implementation • 17 Aug 2023 • Robert Östling, Katarina Gillholm, Murathan Kurfali, Marie Mattson, Mats Wirén
We find that GPT-3 in a few-shot setting by far outperforms previous grammatical error correction systems for Swedish, a language comprising only 0. 11% of its training data.
1 code implementation • 19 Jan 2023 • Robert Östling, Murathan Kurfali
To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned?
no code implementations • ACL (RepL4NLP) 2021 • Murathan Kurfali, Robert Östling
Pre-trained multilingual language models have become an important building block in multilingual natural language processing.
no code implementations • 6 Jun 2021 • Murathan Kurfali, Robert Östling
We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem.
Classification Implicit Discourse Relation Classification +4
1 code implementation • 30 Jul 2019 • Murathan Kurfali, Robert Östling
Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation.
no code implementations • CL 2019 • Johannes Bjerva, Robert Östling, Maria Han Veiga, Jörg Tiedemann, Isabelle Augenstein
If the corpus is multilingual, the same model can be used to learn distributed representations of languages, such that similar languages end up with similar representations.
1 code implementation • WS 2017 • Robert Östling, Yves Scherrer, Jörg Tiedemann, Gongbo Tang, Tommi Nieminen
We also discuss our submissions for English--Latvian, English--Chinese and Chinese--English.
no code implementations • 18 Aug 2017 • Robert Östling, Jörg Tiedemann
Neural machine translation (NMT) approaches have improved the state of the art in many machine translation settings over the last couple of years, but they require large amounts of training data to produce sensible output.
no code implementations • CONLL 2017 • Robert Östling, Johannes Bjerva
This paper describes the Stockholm University/University of Groningen (SU-RUG) system for the SIGMORPHON 2017 shared task on morphological inflection.
no code implementations • 10 Jun 2017 • Johan Sjons, Thomas Hörberg, Robert Östling, Johannes Bjerva
In earlier work, we have shown that articulation rate in Swedish child-directed speech (CDS) increases as a function of the age of the child, even when utterance length and differences in articulation rate between subjects are controlled for.
no code implementations • 22 Dec 2016 • Robert Östling, Jörg Tiedemann
Most existing models for multilingual natural language processing (NLP) treat language as a discrete category, and make predictions for either one language or the other.
no code implementations • WS 2015 • Max Berggren, Jussi Karlgren, Robert Östling, Mikael Parkvall
This paper describes a series of experiments to determine how positionally annotated microblog posts can be used to learn location-indicating words which then can be used to locate blog texts and their authors.