Search Results - "Touileb, Samia"

Learning Horn envelopes via queries from language models by Blum, Sophie, Koudijs, Raoul, Ozaki, Ana, Touileb, Samia

“…We present an approach for systematically probing a trained neural network to extract a symbolic abstraction of it, represented as a Boolean formula. We…”
Get full text

Measuring Harmful Representations in Scandinavian Language Models by Touileb, Samia, Nozza, Debora

“…Scandinavian countries are perceived as role-models when it comes to gender equality. With the advent of pre-trained language models and their widespread…”
Get full text

The interplay between language similarity and script on a novel multi-layer Algerian dialect corpus by Touileb, Samia, Barnes, Jeremy

“…Recent years have seen a rise in interest for cross-lingual transfer between languages with similar typology, and between languages of various scripts…”
Get full text

JSEEGraph: Joint Structured Event Extraction as Graph Parsing by You, Huiling, Touileb, Samia, Øvrelid, Lilja

“…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…”
Get full text

Measuring Normative and Descriptive Biases in Language Models Using Census Data by Touileb, Samia, Øvrelid, Lilja, Velldal, Erik

“…We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models. Such distributions are not…”
Get full text

Learning Horn Envelopes via Queries from Large Language Models by Blum, Sophie, Koudijs, Raoul, Ozaki, Ana, Touileb, Samia

“…We investigate an approach for extracting knowledge from trained neural networks based on Angluin's exact learning model with membership and equivalence…”
Get full text

NorDial: A Preliminary Corpus of Written Norwegian Dialect Use by Barnes, Jeremy, Mæhlum, Petter, Touileb, Samia

“…Norway has a large amount of dialectal variation, as well as a general tolerance to its use in the public sphere. There are, however, few available resources…”
Get full text

EventGraph at CASE 2021 Task 1: A General Graph-based Approach to Protest Event Extraction by You, Huiling, Samuel, David, Touileb, Samia, Øvrelid, Lilja

“…This paper presents our submission to the 2022 edition of the CASE 2021 shared task 1, subtask 4. The EventGraph system adapts an end-to-end, graph-based…”
Get full text

EventGraph: Event Extraction as Semantic Graph Parsing by You, Huiling, Samuel, David, Touileb, Samia, Øvrelid, Lilja

“…Event extraction involves the detection and extraction of both the event triggers and corresponding event arguments. Existing systems often decompose event…”
Get full text

Annotating Norwegian Language Varieties on Twitter for Part-of-Speech by Mæhlum, Petter, Kåsen, Andre, Touileb, Samia, Barnes, Jeremy

“…Norwegian Twitter data poses an interesting challenge for Natural Language Processing (NLP) tasks. These texts are difficult for models trained on standardized…”
Get full text

NorBench -- A Benchmark for Norwegian Language Models by Samuel, David, Kutuzov, Andrey, Touileb, Samia, Velldal, Erik, Øvrelid, Lilja, Rønningstad, Egil, Sigdel, Elina, Palatkina, Anna

“…We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation…”
Get full text

Named Entity Recognition without Labelled Data: A Weak Supervision Approach by Lison, Pierre, Hubin, Aliaksandr, Barnes, Jeremy, Touileb, Samia

“…Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When…”
Get full text

NorDiaChange: Diachronic Semantic Change Dataset for Norwegian by Kutuzov, Andrey, Touileb, Samia, Mæhlum, Petter, Enstad, Tita Ranveig, Wittemann, Alexandra

“…We describe NorDiaChange: the first diachronic semantic change dataset for Norwegian. NorDiaChange comprises two novel subsets, covering about 80 Norwegian…”
Get full text

NoReC: The Norwegian Review Corpus by Velldal, Erik, Øvrelid, Lilja, Bergem, Eivind Alexander, Stadsnes, Cathrine, Touileb, Samia, Jørgensen, Fredrik

“…This paper presents the Norwegian Review Corpus (NoReC), created for training and evaluating models for document-level sentiment analysis. The full-text…”
Get full text