no code implementations • LREC 2022 • Matej Martinc, Syrielle Montariol, Lidia Pivovarova, Elaine Zosa
We tackle the problem of neural headline generation in a low-resource setting, where only limited amount of data is available to train a model.
1 code implementation • LChange (ACL) 2022 • Clémentine Fourrier, Syrielle Montariol
Cognates and borrowings carry different aspects of etymological evolution.
no code implementations • JEP/TALN/RECITAL 2021 • Syrielle Montariol, Alexandre Allauzen
Plusieurs méthodes de détection des changements sémantiques utilisant des plongements lexicaux contextualisés sont apparues récemment.
no code implementations • JEP/TALN/RECITAL 2022 • Arij Riabi, Syrielle Montariol, Djamé Seddah
La tâche de détection de contenus haineux est ardue, car elle nécessite des connaissances culturelles et contextuelles approfondies ; les connaissances nécessaires varient, entre autres, selon la langue du locateur ou la cible du contenu.
no code implementations • CONSTRAINT (ACL) 2022 • Syrielle Montariol, Étienne Simon, Arij Riabi, Djamé Seddah
We propose our solution to the multimodal semantic role labeling task from the CONSTRAINT’22 workshop.
1 code implementation • 16 Apr 2024 • Jibril Frej, Anna Dai, Syrielle Montariol, Antoine Bosselut, Tanja Käser
In light of the job market's rapid changes and the current state of research in course recommender systems, we outline essential properties for course recommender systems to address these demands effectively, including explainable, sequential, unsupervised, and aligned with the job market and user's goals.
2 code implementations • 8 Apr 2024 • Syrielle Montariol, Matej Martinc, Andraž Pelicon, Senja Pollak, Boshko Koloski, Igor Lončarski, Aljoša Valentinčič
For assessing various performance indicators of companies, the focus is shifting from strictly financial (quantitative) publicly disclosed information to qualitative (textual) information.
no code implementations • 20 Mar 2024 • Li Mi, Chang Xu, Javiera Castillo-Navarro, Syrielle Montariol, Wen Yang, Antoine Bosselut, Devis Tuia
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view.
no code implementations • 29 Feb 2024 • Karina Halevy, Anna Sotnikova, Badr AlKhamissi, Syrielle Montariol, Antoine Bosselut
We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and conduct the first in-depth investigation of how different weight-editing methods impact model bias.
no code implementations • 20 Feb 2024 • Li Mi, Syrielle Montariol, Javiera Castillo-Navarro, Xianjie Dai, Antoine Bosselut, Devis Tuia
However, generating focused questions using textual constraints while enforcing a high relevance to the image content remains a challenge, as VQG systems often ignore one or both forms of grounding.
no code implementations • 6 Feb 2024 • Khanh Cao Nguyen, Mike Zhang, Syrielle Montariol, Antoine Bosselut
Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes.
1 code implementation • 5 Feb 2024 • Antoine Magron, Anna Dai, Mike Zhang, Syrielle Montariol, Antoine Bosselut
Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-consuming and expensive annotations.
no code implementations • 1 Dec 2023 • Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf, Antoine Bosselut
To identify the factors underlying LLM-brain alignment, we compute correlations between the brain alignment of LLMs and various model properties, such as model size, various problem-solving abilities, and performance on tasks requiring world knowledge spanning various domains.
1 code implementation • 27 Nov 2023 • Zeming Chen, Alejandro Hernández Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne Hartley, Martin Jaggi, Antoine Bosselut
Large language models (LLMs) can potentially democratize access to medical knowledge.
Ranked #1 on Multiple Choice Question Answering (MCQA) on MedMCQA (Dev Set (Acc-%) metric)
1 code implementation • 7 Nov 2023 • Angelika Romanou, Syrielle Montariol, Debjit Paul, Leo Laugier, Karl Aberer, Antoine Bosselut
In this work, we present CRAB, a new Causal Reasoning Assessment Benchmark designed to evaluate causal understanding of events in real-world narratives.
1 code implementation • 23 Oct 2023 • Mete Ismayilzada, Debjit Paul, Syrielle Montariol, Mor Geva, Antoine Bosselut
Recent efforts in natural language processing (NLP) commonsense reasoning research have yielded a considerable number of new datasets and benchmarks.
no code implementations • 24 Oct 2022 • Syrielle Montariol, Arij Riabi, Djamé Seddah
Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between languages, such as in hate speech detection.
no code implementations • ACL 2021 • Syrielle Montariol, Alexandre Allauzen
We propose a set of scenarios to characterize semantic divergence across two languages, along with a setup to differentiate them in a bilingual corpus.
1 code implementation • NAACL 2021 • Syrielle Montariol, Matej Martinc, Lidia Pivovarova
We propose a novel scalable method for word usage-change detection that offers large gains in processing time and significant memory savings while offering the same interpretability and better performance than unscalable methods.
no code implementations • SEMEVAL 2020 • Matej Martinc, Syrielle Montariol, Elaine Zosa, Lidia Pivovarova
This paper describes the approaches used by the Discovery Team to solve SemEval-2020 Task 1 - Unsupervised Lexical Semantic Change Detection.
no code implementations • JEPTALNRECITAL 2020 • Syrielle Montariol, Alex Allauzen, re
Nous exp{\'e}rimentons sur un corpus de rapports financiers d{'}entreprises fran{\c{c}}aises, pour appr{\'e}hender les enjeux et pr{\'e}occupations propres {\`a} certaines p{\'e}riodes, acteurs et secteurs d{'}activit{\'e}s.
no code implementations • 18 Jan 2020 • Matej Martinc, Syrielle Montariol, Elaine Zosa, Lidia Pivovarova
The way the words are used evolves through time, mirroring cultural or technological evolution of society.
no code implementations • RANLP 2019 • Syrielle Montariol, Alexandre Allauzen
Word meaning change can be inferred from drifts of time-varying word embeddings.
no code implementations • 22 Jul 2019 • Syrielle Montariol, Alexandre Allauzen
Word usage, meaning and connotation change throughout time.
no code implementations • JEPTALNRECITAL 2019 • Syrielle Montariol, Aina Garí Soler, Alexandre Allauzen
This study is a preliminary exploration of the concept of informativeness -how much information a sentence gives about a word it contains- and its potential benefits to building quality word representations from scarce data.
no code implementations • JEPTALNRECITAL 2019 • Syrielle Montariol, Alex Allauzen, re
L{'}usage, le sens et la connotation des mots peuvent changer au cours du temps.