no code implementations • COLING (WANLP) 2020 • Samia Touileb
This paper presents our results for the Nuanced Arabic Dialect Identification (NADI) shared task of the Fifth Workshop for Arabic Natural Language Processing (WANLP 2020).
no code implementations • ACL (GeBNLP) 2021 • Samia Touileb, Lilja Øvrelid, Erik Velldal
More specifically, we add information about the gender of critics and book authors when classifying the polarity of book reviews, and the polarity of the reviews when classifying the genders of authors and critics.
1 code implementation • GeBNLP (COLING) 2020 • Samia Touileb, Lilja Øvrelid, Erik Velldal
We also explore the differences in how this is done by male and female critics.
1 code implementation • NAACL (GeBNLP) 2022 • Samia Touileb, Lilja Øvrelid, Erik Velldal
In this paper we explore how a demographic distribution of occupations, along gender dimensions, is reflected in pre-trained language models.
2 code implementations • WS (NoDaLiDa) 2019 • Jeremy Barnes, Samia Touileb, Lilja Øvrelid, Erik Velldal
This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models.
1 code implementation • 26 Jun 2023 • Huiling You, Samia Touileb, Lilja Øvrelid
We propose a graph-based event extraction framework JSEEGraph that approaches the task of event extraction as general graph parsing in the tradition of Meaning Representation Parsing.
no code implementations • 20 May 2023 • Sophie Blum, Raoul Koudijs, Ana Ozaki, Samia Touileb
We propose a new algorithm that aims at extracting the "tightest Horn approximation" of the target theory and that is guaranteed to terminate in exponential time (in the worst case) and in polynomial time if the target has polynomially many non-Horn examples.
1 code implementation • 6 May 2023 • David Samuel, Andrey Kutuzov, Samia Touileb, Erik Velldal, Lilja Øvrelid, Egil Rønningstad, Elina Sigdel, Anna Palatkina
We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation metrics.
no code implementations • 12 Apr 2023 • Samia Touileb, Lilja Øvrelid, Erik Velldal
We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models.
1 code implementation • 21 Nov 2022 • Samia Touileb, Debora Nozza
Scandinavian countries are perceived as role-models when it comes to gender equality.
1 code implementation • 18 Oct 2022 • Huiling You, David Samuel, Samia Touileb, Lilja Øvrelid
This paper presents our submission to the 2022 edition of the CASE 2021 shared task 1, subtask 4.
1 code implementation • 16 Oct 2022 • Huiling You, David Samuel, Samia Touileb, Lilja Øvrelid
Event extraction therefore becomes a graph parsing problem, which provides the following advantages: 1) performing event detection and argument extraction jointly; 2) detecting and extracting multiple events from a piece of text; and 3) capturing the complicated interaction between event arguments and triggers.
no code implementations • VarDial (COLING) 2022 • Petter Mæhlum, Andre Kåsen, Samia Touileb, Jeremy Barnes
We show that models trained on Universal Dependency (UD) data perform worse when evaluated against this dataset, and that models trained on Bokm{\aa}l generally perform better than those trained on Nynorsk.
1 code implementation • LREC 2022 • Andrey Kutuzov, Samia Touileb, Petter Mæhlum, Tita Ranveig Enstad, Alexandra Wittemann
We describe NorDiaChange: the first diachronic semantic change dataset for Norwegian.
1 code implementation • Findings (ACL) 2021 • Samia Touileb, Jeremy Barnes
However, the interplay between language similarity and difference in script on cross-lingual transfer is a less studied problem.
1 code implementation • NoDaLiDa 2021 • Jeremy Barnes, Petter Mæhlum, Samia Touileb
Norway has a large amount of dialectal variation, as well as a general tolerance to its use in the public sphere.
no code implementations • LREC 2020 • Wafia Adouane, Samia Touileb, Jean-Philippe Bernardy
We present in this paper our work on Algerian language, an under-resourced North African colloquial Arabic variety, for which we built a comparably large corpus of more than 36, 000 code-switched user-generated comments annotated for sentiments.
1 code implementation • ACL 2020 • Pierre Lison, Aliaksandr Hubin, Jeremy Barnes, Samia Touileb
When in-domain labelled data is available, transfer learning techniques can be used to adapt existing NER models to the target domain.
no code implementations • WS 2019 • Julia Rodina, Baksh, Daria aeva, Vadim Fomin, Andrey Kutuzov, Samia Touileb, Erik Velldal
We measure the intensity of diachronic semantic shifts in adjectives in English, Norwegian and Russian across 5 decades.
no code implementations • COLING 2018 • Samia Touileb, Truls Pedersen, Helle Sj{\o}vaag
Automatically identifying persons in a particular role within a large corpus can be a difficult task, especially if you don{'}t know who you are actually looking for.
1 code implementation • LREC 2018 • Erik Velldal, Lilja Øvrelid, Eivind Alexander Bergem, Cathrine Stadsnes, Samia Touileb, Fredrik Jørgensen
As resources for sentiment analysis have so far been unavailable for Norwegian, NoReC represents a highly valuable and sought-after addition to Norwegian language technology.