April 2026 - Corpora

PROFE 2026 @ IberLEF 2026 - Call for Participation and release of development data
by ALVARO RODRIGO YUSTE 10 Apr '26

10 Apr '26

<Apologies for cross-postings> ------------------------------------------------ Call for Participation PROFE 2026: Language Proficiency Evaluation IberLEF 2026 Shared Task https://sites.google.com/view/profe2026 PROFE 2026 reuses the exams for Spanish proficiency evaluation developed by Instituto Cervantes along many years to evaluate human students. Therefore, automatic systems will be evaluated under the same conditions as humans were. Systems will receive a set of exercises with their corresponding instructions without specific training material. In this way we expect Transfer Learning approaches or the use of Generative Large Language Models. The previous edition proposed exams based only on text. In this new edition, we will include exams with images, which sometimes require interpretation to answer the exercise correctly. We propose evaluating systems on their ability to perform multimodal reasoning, moving beyond text-only comprehension. We will provide a limited set of new image-based exercises while retaining the dataset from the previous edition. This setup encourages participants to develop strategies for handling the scarcity of specific training data. Subtasks PROFE 2026 has three subtasks, one per exercise type. Teams can participate in any combination of them. Each subtask contains several exercises of the same type. The subtasks are: 1. Multiple choice subtask: each exercise includes a text and a set of multiple-choice questions about the text where only one answer is correct. Given a multiple-choice question, systems must select the correct answer among the candidates. 2. Matching subtask: each exercise contains two sets of texts. Systems must find the text in the second set that best matches the first set. There is only one possible matching per text, but the first set can contain extra unnecessary texts. 3. Filling the gap subtask: each exercise contains a text with several gaps corresponding to textual fragments that have been removed and presented disorderly as options. Systems must determine the correct position for each fragment. There is only one correct text per gap, but there could be more candidates than gaps. The different exercises open research on how to approach them, adapting different prompts when using generative models. As the main novelty in this edition, some exercises will contain images. While some of these images will be the candidate answers (rather than text excerpts), others might provide visual information needed to answer the exercise correctly. Conversely, some images will not provide essential information. Consequently, systems participating in this edition must adopt a multimodal approach, capable of discerning when to integrate visual cues and when to disregard them. This necessity to filter visual relevance introduces significant new challenges compared to the previous edition. Dataset We will use the IC-UNED-RC-ES dataset created from real examinations at Instituto Cervantes. These exams were created by human experts to assess language proficiency in Spanish. We have already collected the exams and converted them to a digital format, which is ready to be used in the task. The dataset contains exams at different levels (from A1 to C2). The description of the full dataset was published in the following paper: * Anselmo Peñas, Álvaro Rodrigo, Javier Fruns-Jiménez, Inés Soria-Pastor, Sergio Moreno-Álvarez, Alberto Pérez García-Plaza, and Julio Reyes-Montesinos. A Spanish Language Proficiency Dataset for AI Evaluation<https://www.mdpi.com/2078-2489/17/2/159>. Information 17, no. 2: 159. DOI: 10.3390/info17020159<https://doi.org/10.3390/info17020159>. 2026. The complete dataset contains 282 exams with 855 exercises. The total number of evaluation points are 6146 (among 16570 options) distributed by exercise type as: multiple-choice: 3544 responses matching: 2309 responses fill-the-gap: 293 responses In PROFE 2026, we plan to use around 50% of the exams; the other 50% was already used for the PROFE 2025 edition. We intend not to distribute the gold standard to prevent overfitting in post-campaign experiments and data contamination in LLMs. Evaluation measures and baseline We will use traditional accuracy (proportion of correct answers) as the main evaluation measure. Systems will receive evaluation scores from two different perspectives: * At the question level, where correct answers are counted individually without grouping them. * At the exam level, where scores for each exam are considered. Each exam contains several exercises of different types. An exam is considered to be passed if an accuracy score (accounted as the proportion of correct answers) above 0.5 is reached. Then, the proportion of passed exams is given as a global score. This perspective will only apply to those teams participating in the three subtasks. More in detail, the exact evaluation per subtask is as follows: * Multiple choice subtask: we will measure accuracy as the proportion of questions correctly answered * Matching subtask: we will measure accuracy as the proportion of correct texts matched. * Fill in the gap subtask: We will measure accuracy as the proportion of correctly filled gaps. We will use accuracy as the evaluation measure because there is only one correct option among candidates and because it is the measure applied to humans doing the same exams. Thus, we can compare the performance of automatic systems and humans under the same conditions A preliminary baseline using ChatGPT obtains the following results for each exercise type (provided that different prompting can produce slightly different results): * Multiple choice accuracy: 0.64 * Filling the gap accuracy: 0.43 * Matching accuracy: 0.51 Schedule April April 10, 2026 Development data released April 27, 2026 Test set release May May 11, 2026 Deadline for submitting runs May 18, 2026 Release of evaluation results June June 3, 2026 Paper submission deadline Organizers Alvaro Rodrigo<https://www.uned.es/universidad/docentes/informatica/alvaro-rodrigo-yuste.h…>, UNED NLP & IR Group (Universidad Nacional de Educación a Distancia) Anselmo Peñas<https://www.uned.es/universidad/docentes/informatica/anselmo-penas-padilla.…>, UNED NLP & IR Group (Universidad Nacional de Educación a Distancia) Alberto Pérez<https://www.uned.es/universidad/docentes/informatica/alberto-perez-garcia-p…>, UNED NLP & IR Group (Universidad Nacional de Educación a Distancia) Sergio Moreno<https://www.uned.es/universidad/docentes/en/informatica/sergio-moreno-alvar…>, UNED NLP & IR Group (Universidad Nacional de Educación a Distancia) Javier Fruns, Instituto Cervantes Inés Soria, Instituto Cervantes Rodrigo Agerri<https://ragerri.github.io/>, HiTz (Universidad del País Vasco, UPV/EHU) AVISO LEGAL. Este mensaje puede contener información reservada y confidencial. Si usted no es el destinatario no está autorizado a copiar, reproducir o distribuir este mensaje ni su contenido. Si ha recibido este mensaje por error, le rogamos que lo notifique al remitente. Le informamos de que sus datos personales, que puedan constar en este mensaje, serán tratados en calidad de responsable de tratamiento por la UNIVERSIDAD NACIONAL DE EDUCACIÓN A DISTANCIA (UNED) c/ Bravo Murillo, 38, 28015-MADRID-, con la finalidad de mantener el contacto con usted. La base jurídica que legitima este tratamiento, será su consentimiento, el interés legítimo o la necesidad para gestionar una relación contractual o similar. En cualquier momento podrá ejercer sus derechos de acceso, rectificación, supresión, oposición, limitación al tratamiento o portabilidad de los datos, ante la UNED, Oficina de Protección de datos<https://www.uned.es/dpj>, o a través de la Sede electrónica<https://uned.sede.gob.es/> de la Universidad. Para más información visite nuestra Política de Privacidad<https://descargas.uned.es/publico/pdf/Politica_privacidad_UNED.pdf>.

1 0

Call for Participation in iKAT 2026 as Part of SCAI@SIGIR 2026
by Marcel Ewald Gohsen 10 Apr '26

10 Apr '26

We invite participation to the 4th shared task on interactive (personalized) knowledge assistance (iKAT 2026), which will be hosted as part of the 10th Workshop on Search-Oriented Conversational AI (SCAI)<https://scai.info/scai-2026/> , colocated with SIGIR 2026 in Melbourne, Australia. * Name: Interactive Knowledge Assistance Track (iKAT) * Organizers: Marcel Gohsen<https://www.uni-weimar.de/en/media/chairs/computer-science-department/webis…>, Mohammad Aliannejadi<https://aliannejadi.com/>, Simon Lupart<https://simonlupart.github.io/>, Zahra Abbasiantaeb<https://zahraabbasiantaeb.github.io/>, Nailia Mirzakhmedova<https://www.uni-weimar.de/en/media/chairs/computer-science-department/webis…>, Johannes Kiesel<https://kiesels.de/johannes>, Jeff Dalton<https://www.dcs.gla.ac.uk/~jeff/> * Preliminary timeline (exact dates might still be subject of change): * Registration deadline: May 27, 2026 * System submission opens: May 27, 2026 * System submission deadline: June 10, 2026 * Report submission deadline: July 17, 2026 * SCAI Workshop: July 24, 2026 * Website: https://www.trecikat.com/ * Registration: https://form.jotform.com/260753949743066 Motivation While the conversational interaction paradigm becomes more and more prevalent for search, the challenge of adapting system responses to individual users (i.e., personalization) still remains a challenge for conversational retrieval systems. Since answer relevance is highly subjective, personalization is necessary to build effective user-centric retrieval systems. From the beginning, personalization of conversational search is the central goal of the Interactive Knowledge Assistance Track (iKAT). The iKAT shared task can look back on four years under former name, Conversational Assistance Track (CAsT), and three years under the current name, iKAT, hosted at TREC. In 2026, iKAT will be organized in collaboration with the SCAI workshop that will take place at SIGIR 2026 in Melbourne, Australia. Task Overview Participants of iKAT will receive the following resources to provide their run submissions. 1. Test dataset that contains the following information: a) Topics b) Example conversations c) Personal Text Knowledge Bases (PTKB) of the users 2. Passage collection (iKAT subset of ClueWeb22-B) 3. Access to the user simulation API (Sim.API<https://github.com/marcel-gohsen/user-simulation-api>) and documentation. Participants submit conversational search systems that, for each real-time simulated user turn, retrieves and ranks relevant passages from the passage collection. Then, the system use the ranked passages to generate a personalized response based on the user’s PTKB, utterance, and context. This response will be passed back to the simulated user, which again produces an utterance. This process will be repeated until the user terminates the conversation. The systems have to provide the generated text response, the ranked list of passages (citations), and the PTKB statements that were deemed relevant for each produced turn. Submission Participants submit their runs via an API and submit a report to describe their approaches. Every participating team will be invited to present their approaches during the SCAI workshop and the reports will be released as part of our proceedings. Further Details For more information and updates on the task please keep an eye on our guidelines and on our iKAT website<https://www.trecikat.com/>.

1 0

[Jobs@ELDA] Offre de missions de traduction en anglais, français, allemand et russe (H/F) / English, French, German and Russian Translators (F/M)
by info＠elda.org 10 Apr '26

10 Apr '26

[Apologies for multiple postings] English, French, German and Russian translators (F/M) (English version below) Context: In order to create high-quality linguistic resources, ELDA (Evaluations and Language resources Distribution Agency) is hiring translators to work in the following language pairs: • French to English • German to French • English to German • Russian to English Mission details: • Document type: political newspaper articles (defense-oriented); • Volume: 15.000 words ; • Modality: full translation (target text to be created from scratch); • Technical terminology: journalistic discourse - may contain political, judicial or military jargon; • Start date: as soon as possible; • End date: May 22nd, 2026; • Location: ELDA main office (Paris, 13th district). Remote work allowed; • Contract type: freelance (possible fixed-term contract upon request); • Send estimate to: <menel(a)elda.org> Additional job specificities: • Knowledge of annotation softwares (Label Studio) is a great-to-have. • You are able to quickly understand and apply complex annotation guidelines. How to apply : • Send your resume to <menel(a)elda.org>. ------------------------------------------------------- Offre de missions de traduction - anglais, français, allemand et russe (H/F) Contexte : Dans le cadre de ses activités de production de ressources linguistiques, ELDA (Evaluations and Language resources Distribution Agency) recherche des traducteurs (F/H) amenés à travailler dans les paires de langues suivantes : • Français vers anglais • Allemand vers français • Anglais vers allemand • Russe vers anglais Détails de la mission : • Documents : articles politiques contemporains (axés défense) ; • Volume : 15 000 mots ; • Modalité : traduction complète (production du texte cible) ; • Langage technique : discours journalistique, avec jargons politique, juridique et/ou militaire occasionnels ; • Date d’embauche prévue : Dès que possible ; • Date de fin de mission : 22 mai 2026 ; • Lieu : Locaux d’ELDA (Paris 13ème arrondissement), télétravail possible ; • Type de contrat : freelance (CDD envisageable sur demande) ; • Envoi de devis : <menel(a)elda.org> Autres spécificités du poste : • La connaissance du logiciel d’annotation Label Studio est très appréciée. • Capacité à intégrer et appliquer rapidement des règles d’annotation complexes. Candidature : • Envoyer un CV à <menel(a)elda.org>

1 0

[Jobs@ELDA] Annotateurs (H/F) en allemand, anglais et russe / Annotators (M/F) in German, English and Russian
by info＠elda.org 10 Apr '26

10 Apr '26

[Apologies for multiple postings] Contexte : ELDA (Evaluations and Language resources Distribution Agency) recherche, dans le cadre de ses activités de production de ressources linguistiques, des annotateurs (F/H) pour une mission de deux semaines (renouvelable) à temps plein. Langues concernées : • Allemand • Anglais • Russe Mission : Dans le cadre d’un projet européen, nous constituons des corpus d’évaluation des technologies langagières. L’annotateur sera amené à travailler sur les tâches suivantes : • Entités nommées (NER), • Reconnaissance de la parole (ASR), • Reconnaissance automatique de caractères (OCR). La mission aura lieu dans les locaux d'ELDA (Paris 13e) et peut démarrer dès que possible. Profil recherché : • Locuteur natif (ou niveau C2 minimum) d’une des langues concernées ; • Connaissances dans le domaine des langues et/ou de la linguistique afin de comprendre et mobiliser des concepts fins (sémantique, phonétique) ; • Connaissances en traitement automatique des langues ou humanités numériques très appréciées ; • Capacité à travailler sur les types de textes suivants : presse politique, documentation technique en lien avec la défense, données de défense européenne ; • Capacité à travailler avec les formats de données suivants : images, audio, texte ; • Bonne maîtrise de l’outil informatique ; la connaissance de logiciels d'annotation (Label Studio, Praat en particulier) est très appréciée ; • Capacité à intégrer rapidement et suivre des règles d’annotation complexes ; • Curiosité, minutie, attention au détail, rigueur. Modalités du contrat : • Rémunération SMIC +20% soit 2162,16€ brut mensuel ; • Premiers jours de formation sur site, télétravail possible par la suite ; • CDD de 2 semaines renouvelable. Candidature : • Envoyer un CV à <menel(a)elda.org>. ------------------------------------------------------------------ Context: In order to create high-quality language resources, ELDA (Evaluations and Language resources Distribution Agency) is hiring full-time annotators. Targeted Languages: • German • English • Russian Mission : Currently taking part in a European-funded project, ELDA is developing evaluation datasets for language technologies. The annotators will work on the following tasks: • Named Entity Recognition (NER), • Automatic Speech Recognition (ASR), • Optical Character Recognition (OCR). The position will be based at the ELDA main office (Paris, 13th district) and can start as soon as possible. Requirements and qualifications : • You are a native (or at least C2 level) speaker in one of the targeted languages; • You have extensive knowledge in language sciences and/or linguistics. This will be necessary to discuss advanced concepts such as semantics or phonetics; • Ideally, you have knowledge in Natural Language Processing (NLP) or in Digital Humanities (DH); • You can handle the following textual types: political news, technical documentation on the defense domain, European defense data; • You can handle the following data types: image, audio and text; • You have solid computer skills; knowing annotation software (esp. Label Studio and Praat) is a great-to-have; • You are able to quickly understand and apply complex annotation guidelines; • You are curious, meticulous and detail-oriented. Contract specifications: • Compensation: French minimum wage (SMIC) +20%, amounting to €2162.16 (gross monthly salary); • Location: on-site for the first days of training, then remote work is allowed for the remaining days; • Duration: 2-week renewable fixed-term contract (CDD). How to apply : • Send your resume to <menel(a)elda.org>.

1 0

[2nd CFP] NALOMA: Natural Language Meets Logic and Machine Learning
by Abzianidze, L. (Lasha) 09 Apr '26

09 Apr '26

[Apologies for cross-posting] TL;DR Time & place: 3-7 August, ESSLLI in Prague, Czech Republic Submission types: ACL Anthology archival (short/long/demo) and non-archival (extended abstract) Deadline: 30 April Website: https://naloma.github.io The 6th iteration of the NALOMA (Natural Language Meets Logic and Machine Learning) workshop invites submissions on any (theoretical or computational) aspect of hybrid methods concerning Natural Language Understanding and Reasoning (NLU&R). The topics include but are not limited to: - Hybrid NLU&R systems that integrate logic-based/symbolic methods with neural networks - Explainable NLU&R (with structured explanations) - Opening the black-box of deep learning in NLU&R - Downstream applications of hybrid NLU&R systems - Probabilistic semantics for NLU&R - Comparison and contrast between symbolic and deep learning work on NLU&R - Creation, criticism, refinement, and augmentation of NLU&R datasets - (Dis)Alignment of humans and machines on NLU&R tasks - Addressing inherent human disagreements in NLU&R tasks - Generalization of NLU&R systems - Fine-grained evaluation of NLU&R systems NALOMA accepts archival papers (long, short, and demo) to appear in the ACL anthology proceedings and non-archival extended abstracts. The workshop is co-located with ESSLLI (https://2026.esslli.eu), 3-7 August, Prague, Czech Republic. The submission deadline is 30 April. Please visit https://naloma.github.io for more details about the call. NALOMA PC chairs, Lasha Abzianidze and Hitomi Yanaka Lasha Abzianidze Assistant professor Institute for Language Sciences, Utrecht University

1 0

Summer Corpus Intensive
by Daniel HENKEL 09 Apr '26

09 Apr '26

(Texte en français ci-dessous) Paris 8 University is pleased to announce their upcoming Summer Intensive Program "*Corpus Methods in Linguistics--compilation, annotation, and quantitative analysis*", to be held 26-29 May 2026. This will be a 30h week-long course consisting of: --morning sessions devoted to data collection, extraction and organization, as well as DIY corpus building --afternoon sessions focusing on statistical analysis of the data produced during the morning sessions --several half-day sessions on automatic annotation and manual annotation methods Participants will learn how to: --formulate advanced search queries in a concordancer (e.g. TextSTAT, AntConc) --compile a text corpus with BootCaT --automatically annotate a text corpus in TreeTagger --measure keyword specificity and collocation strength using AntConc --perform statistical analyses of categorical variables in R This program is intended primarily for researchers and upper-level students (Masters or Doctorate). Tuition will be 90€. To participate*, or request further information, please send an email to the organizers indicating name, status (e.g. Doctoral student, Post-doctoral researcher, Faculty) and 5 keywords describing your research interests using this link <mailto:daniel.henkel@univ-paris8.fr?subject=Summer%20Corpus%20Intensive&body=Name:%0D%0A%0D%0AStatus%2FAffiliation:%0D%0A%0D%0AKeywords:%0D%0A%0D%0AHow%2FWhere%20did%20you%20learn%20about%20the%20Paris%208%20Summer%20Corpus%20Intensive%3F:%0D%0A%0D%0AMessage:%0D%0A%0D%0A%0D%0ANB.%20Please%20leave%20the%20subject%20line%20%22Summer%20Corpus%20Intensive%22%20unchanged.%0D%0AVeuillez%20ne%20pas%20modifier%20la%20ligne%20objet%20%22Summer%20Corpus%20Intensive%22.&cc=dsg.up8@gmail.com,summer.school.paris8@gmail.com>. Please note that this is an international Summer School and that we will work with corpora in English, French and possibly other languages. Knowledge of French is thus an advantage but is not strictly necessary. /*Pending confirmation/ *** Nous avons le plaisir de vous annoncer l'ouverture prochaine du Séminaire Intensif « *Méthodes en Linguistique de Corpus--compilation, annotation et analyse quantitative* », de l'Université Paris 8 qui aura lieu du 26 au 29 mai 2026. Ce programme, d'une durée d'une semaine, comprend 30h de cours répartis de la manière suivante : --le matin, des séances consacrées à la récolte et à la préparation des données --l'après-midi, des cours dédiés à l'analyse statistique des données récoltées lors des séances du matin --plusieurs demi-journées d'entraînement à l'annotation automatique et manuelle. Les participants apprendront à : --concevoir des formules de recherche complexes dans un concordancier (p.ex. TextSTAT, AntConc) --rassembler un corpus thématique avec BootCaT --étiqueter un corpus de texte automatiquement avec TreeTagger --mesurer la spécificité des mots clefs et la force des collocations dans AntConc --réaliser des analyses statistiques de variables catégoriques dans R Ce programme s'adresse principalement à des enseignants-chercheurs et étudiants de deuxième ou troisième cycle (Master, Doctorat). Les frais de participation seront de 90€. Pour y participer*, ou pour tout complément d'information, envoyez un courriel aux organisateurs indiquant votre nom, statut (p.ex. Doctorant, Post-doc, Enseignant-chercheur) et 5 mots clefs décrivant vos intérêts de recherche en cliquant ici <mailto:daniel.henkel@univ-paris8.fr?subject=Summer%20Corpus%20Intensive&body=Name:%0D%0A%0D%0AStatus%2FAffiliation:%0D%0A%0D%0AKeywords:%0D%0A%0D%0AHow%2FWhere%20did%20you%20learn%20about%20the%20Paris%208%20Summer%20Corpus%20Intensive%3F:%0D%0A%0D%0AMessage:%0D%0A%0D%0A%0D%0ANB.%20Please%20leave%20the%20subject%20line%20%22Summer%20Corpus%20Intensive%22%20unchanged.%0D%0AVeuillez%20ne%20pas%20modifier%20la%20ligne%20objet%20%22Summer%20Corpus%20Intensive%22.&cc=dsg.up8@gmail.com,summer.school.paris8@gmail.com>. /*Sous réserve de confirmation/

1 0

ACM ICMI 2026 Call for Tutorials
by Gualtiero Volpe 09 Apr '26

09 Apr '26

ICMI 2026 CALL FOR TUTORIALS ============================================ 5-9 October 2026, Napoli - Italy https://icmi.acm.org/2026/ ============================================ ACM ICMI 2026 seeks half-day tutorial proposals addressing current and emerging topics within the scope of context and cultural awareness for multimodal interaction. Tutorials are designed to offer a high-quality learning experience to participants with diverse backgrounds. It is expected that tutorials are self-contained. Prospective organizers should submit a 4-page (maximum) proposal containing the following information: 1. Title. 2. Abstract, appropriate for possible Web promotion of the tutorial. 3. A short list of the distinctive topics to be addressed. 4. Learning objectives (specific and measurable objectives). 5. The targeted audience (student / early stage / advanced researchers, pre-requisite knowledge, field of study). 6. Detailed description of the tutorial and its relevance to multimodal interaction. 7. Outline of the tutorial content with a tentative schedule and its duration. 8. Description of the presentation format (number of presenters, interactive sessions, practical aspects). 9. Accompanying material (repository, references) and equipment, emphasizing any required material from the organization committee (subject to approval). 10. Short biography of the organizers (preferably from multiple institutions) together with their contact information and a list of 1-2 key publications related to the tutorial topic. 11. Previous editions: If the tutorial was given before, describe when and where it was delivered. Proposals will be evaluated using the following criteria: - Importance of the topic and the relevance to ACM ICMI 2026. - Presenters’ experience. - Adequacy of the presentation format to the topic. - Targeted audience interest and impact. - Accessibility and quality of accompanying materials (open access). Proposals that focus exclusively on the presenters’ own work or commercial presentations are not acceptable. However, we encourage non-academic researchers to propose tutorials. Contact Details Proposals should be emailed to the ICMI 2026 Tutorial Chairs, Prof. Marco Cristani and Prof. Tsvi Kuflik at: icmi2026-tutorials-chairs(a)acm.org Prospective organizers are also encouraged to contact the co-chairs if they have any questions. Important Dates Tutorial proposal deadline: April 30th, 2026 Tutorial acceptance notification: May 23th, 2026 Camera-ready version of the tutorial abstract: August 2nd, 2026 Tutorial date: October 5th or October 9th 2026 ICMI organization will provide rooms, coffee, and lunch for participants, and one free registration for a speaker or organizer for each tutorial.

1 0

Post-doc position in archive digital valorization (computer science & digital humanities)
by Antonin Descampe 09 Apr '26

09 Apr '26

[Version française ci-dessous, apologies for cross-posting, mes excuses en cas d’envoi multiple] Job offer summary In the context of the BELSPO FED-tWIN<https://www.belspo.be/belspo/research/FEDtWIN_en.stm> research program (ARKEY funded proposal), the MiiL<https://uclouvain.be/en/research-institutes/ilc/miil> (Media Innovation and Intelligibility Lab from UCLouvain<https://uclouvain.be/en/index.html>, Belgium) and the States Archives of Belgium<https://www.arch.be/index.php?l=en> (SAB) are looking for a post-doc researcher in computer science or digital humanities, with a significant experience in the automatic processing of digital documents involving both text and images. The proposed contract is an open-ended FTE contract (50% UCLouvain, 50% SAB). The funding is guaranteed over a period of 7.5 years, with the intention of securing the position. The main objective of this ARKEY research profile will be to improve the digital valorization of archive collections through long-term tools and recent advances in artificial intelligence. It involves (1) the research and development of an enhanced access key to digitized content (through text and layout recognition, and enriched digital archival representation), and (2) the improvement of the navigation experience within archive collections, through semantic search and conversational interfaces. It builds on the expertise of a multidisciplinary team from SAB and from several research groups within UCLouvain (MiiL<https://uclouvain.be/en/research-institutes/ilc/miil>, Cental<https://uclouvain.be/fr/instituts-recherche/ilc/cental>, ARCH<https://uclouvain.be/fr/decouvrir/archives>, and GEMCA<https://uclouvain.be/fr/instituts-recherche/incal/gemca>). ARKEY aims to bring added value for society and public service, by improving the accessibility and intelligibility of archives: a priority for many researchers and a foundation of democratic states. The complete offer is available here<https://www.uclouvain.be/en/research-institutes/ilc/miil/jobs>. Application should be sent to Antonin Descampe (antonin.descampe(a)uclouvain.be<mailto:antonin.descampe@uclouvain.be>) and Johan Van Der Eycken (johan.vandereycken(a)arch.be<mailto:johan.vandereycken@arch.be>) as soon as possible and no later than May 10, 2026. Résumé de l’offre Dans le cadre du programme de recherche BELSPO FED-tWIN<https://www.belspo.be/belspo/research/FEDtWIN_fr.stm> (proposition financée « ARKEY »), le MiiL<https://uclouvain.be/fr/instituts-recherche/ilc/miil> (Media Innovation and Intelligibility Lab de l'UCLouvain<https://uclouvain.be/fr/index.html>, Belgique) et les Archives de l’Etat en Belgique<https://www.arch.be/index.php?l=fr> (AGR) recherchent un post-doctorant en informatique ou en humanités numériques, avec une expérience importante dans le le traitement automatique de documents numériques impliquant à la fois du texte et des images. Le contrat proposé est un contrat à temps plein à durée indéterminée (50% UCLouvain, 50% AGR). Le financement est garanti sur 7,5 ans, avec une intention de pérennisation du poste. L'objectif principal de ce profil de recherche ARKEY sera d’optimiser la valorisation numérique des collections d'archives grâce à des outils informatiques pérennes et aux avancées récentes en intelligence artificielle. Il propose (1) la recherche et le développement de moyens d'accès enrichis au contenu numérisé (grâce à la reconnaissance de texte et de structure, ainsi qu’à une représentation enrichie des archives), et (2) l'amélioration de l'expérience de navigation au sein des collections d’archives, notamment via des interfaces de recherche sémantique et conversationnelle. Il s'appuie sur l'expertise d'une équipe pluridisciplinaire des AGR et de plusieurs groupes de recherche au sein de l'UCLouvain (MiiL<https://uclouvain.be/fr/instituts-recherche/ilc/miil>, Cental<https://uclouvain.be/fr/instituts-recherche/ilc/cental>, ARCH<https://uclouvain.be/fr/decouvrir/archives> et GEMCA<https://uclouvain.be/fr/instituts-recherche/incal/gemca>). ARKEY vise à apporter une valeur ajoutée pour la société et le service public en améliorant l'accessibilité et l'intelligibilité des archives : une priorité pour de nombreux chercheurs et chercheuses, et un fondement des États démocratiques. L'offre complète est également disponible ici<https://uclouvain.be/fr/instituts-recherche/ilc/miil/offres-d-emploi.html>. Les candidatures doivent être envoyées à Antonin Descampe (antonin.descampe(a)uclouvain.be<mailto:antonin.descampe@uclouvain.be>) et Johan Van Der Eycken (johan.vandereycken(a)arch.be<mailto:johan.vandereycken@arch.be>) dès que possible et au plus tard le 10 mai 2026. Antonin Descampe - PhD Assistant Professor @ UCLouvain<https://www.uclouvain.be/> (personal page<https://www.uclouvain.be/people/antonin.descampe>) Teacher @ Louvain School of Communication and Journalism (COMU<https://www.uclouvain.be/fr/facultes/espo/comu>/EjL<https://uclouvain.be/fr/facultes/espo/comu/master-en-journalisme.html>) Researcher @ Observatory for Research on Media and journalism (ILC<https://www.uclouvain.be/fr/instituts-recherche/ilc>/ORM<https://www.uclouvain.be/orm>) Academic Supervisor @ Media Innovation and Intelligibility Lab (MiiL<https://www.uclouvain.be/miil>) Special Advisor to the Rector for Digital Communication Place de l'Université, 16, bur. b.405 1348 Louvain-la-Neuve (Belgium) Tel. +32 (0)10 47 27 87 antonin.descampe(a)uclouvain.be<mailto:antonin.descampe@uclouvain.be>

1 0

Call for Participation in Touché @ CLEF 2026: Shared Tasks on Argumentation Systems (Fallacies, Causality, Generalizability, RAG Advertisements)
by Johannes.Kiesel＠gesis.org 08 Apr '26

08 Apr '26

We invite you to participate in the following shared tasks at Touché 2026 held in conjunction with the CLEF conference. 1. Fallacy Detection. Given an argument, determine whether it is fallacious and what type of fallacy it is. https://touche.webis.de/clef26/touche26-web/fallacy-detection.html 2. Causality Extraction. Given a text, determine whether it contains causal information, identify the information in the text, and classify the expressed relationship. https://touche.webis.de/clef26/touche26-web/causality-extraction.html 3. Generalizability of Argument Identification in Context. Given a sentence from some argumentation dataset, determine whether the sentence was annotated as argument (using annotator guidelines etc.). https://touche.webis.de/clef26/touche26-web/generalizable-argument-mining.h… 4. Advertisement in Retrieval-Augmented Generation (RAG). Given a query and response of an RAG system, determine whether the response contains an ad, identify the ad in the response, and remove the ad. https://touche.webis.de/clef25/touche25-web/advertisement-detection.html Find out more at https://touche.webis.de/clef26/touche26-web/ and join our mailing list at https://groups.google.com/g/touche-lab for staying up to date. Awards -------------------------- The best submission for each task will receive an award. In addition, our partners at Methods Hub (https://methodshub.gesis.org/) have agreed to provide priority support to the award-winning teams in developing their submissions into fully reusable software packages to maximize your impact. Important Dates -------------------------- 2026-05-07: Approaches submission deadline 2026-05-28: Participant paper submission 2026-06-30: Peer review notification 2026-07-06: Camera-ready participant papers submission 2026-09 21-24: CLEF Conference in Jena and Touché Workshop Links -------------------------- Touché: https://touche.webis.de Contact: touche(a)webis.de We are looking forward to your submission! The Touché team

1 0

7th Call for Papers – LaTeLL 2026 (Low-Resource Languages)
by ernesto.estevanell＠ua.es 08 Apr '26

08 Apr '26

International Conference 'LAnguage TEchnologies for Low-resource Languages' (LaTeLL '2026) Fes, Morocco 30 September, 1 and 2 October 2026 www.latell.org/2026/ [1] 7th Call for Papers The conference Natural Language Processing (NLP) has witnessed remarkable progress in recent years, largely driven by the emergence of deep learning architectures and, more recently, large language models (LLMs). Nevertheless, these advances have disproportionately benefited high-resource languages that possess abundant data for model training. By contrast, low-resource languages which account for at least 85% of the world's linguistic diversity and are often spoken by smaller or marginalised communities, have not yet reaped the full benefits of contemporary NLP technologies. This imbalance can be attributed to several interrelated factors, including the scarcity of high-quality training data, limited computational and financial resources, and insufficient community engagement in data collection and model development. Developing NLP applications for low-resource languages poses major challenges, particularly the need for large, well-annotated datasets, standardised tools, and robust linguistic resources. Although several workshops have previously addressed NLP for low-resource languages, _LaTeLL_ represents the first international conference dedicated specifically to the automatic processing of such languages. The event aims to provide a forum for researchers to present and discuss their latest work in NLP in general, and in the development and evaluation of language models for low-resource languages in particular. Conference topics We invite submissions on a broad range of themes concerning linguistic and computational studies focusing on low-resource languages, including but not limited to the following topics: Language resources for low-resource languages * Dataset creation and annotation * Evaluation methodologies and benchmarks for low-resource settings * Lexical resources, corpora, and linguistic databases * Crowdsourcing and community-driven data collection * Tools and frameworks for low-resource language processing Core language technologies for low-resource languages * Language modelling and pre-training for low-resource languages * Speech recognition, text-to-speech, and spoken language understanding * Phonology, morphology, word segmentation, and tokenisation * Syntax: tagging, chunking, and parsing * Semantics: lexical and sentence-level representation NLP Applications for low-resource languages * Information extraction and named entity recognition * Question answering systems * Dialogue and interactive systems * Summarisation * Machine translation * Sentiment analysis, stylistic analysis, and argument mining * Content moderation * Information retrieval and text mining Multimodality and Grounding for low-resource languages * Vision and language for low-resource contexts * Speech and text multimodal systems * Low-resource sign language processing Ethics, Equity, and Social Impact for low-resource languages * Bias and fairness in low-resource language technologies * Sociolinguistic considerations in technology development * Cultural appropriateness and sensitivity Human-Centred Approaches in low-resource languages * Usability and accessibility of low-resource language technologies * Educational applications and language learning * Community needs assessment and technology adoption * User experience research in low-resource contexts Multilinguality and Cross-Lingual Methods for low-resource languages * Multilingual language models and their adaptation * Code-switching and code-mixing * Cross-lingual transfer learning in low-resource languages. Special Theme Track 1 -- Building Applications Based on Large Language Models for Low-Resource Languages _LaTeLL'2026_ will feature a Special Theme Track dedicated to the development of applications based on Large Language Models (LLMs) for low-resource languages. This track aims to explore innovative methodologies, architectures, and tools that leverage the power of LLMs to enhance linguistic processing, accessibility, and inclusivity for underrepresented languages. Contributions are encouraged on topics such as model adaptation and fine-tuning, multilingual and cross-lingual transfer, ethical and fairness considerations, and the creation of datasets and benchmarks that facilitate the integration of LLM-based solutions in low-resource settings. Special Theme Track 2 -- Modern Standard Arabic (MSA) and Arabic Dialects This special track addresses the unique challenges and opportunities in processing Modern Standard Arabic (MSA) and the rich landscape of Arabic dialects. The diglossic nature of Arabic, where the formal MSA coexists with numerous, widely used spoken dialects, presents a significant hurdle for NLP. While MSA is relatively well-resourced, Arabic dialects are quintessential examples of low-resource languages, often lacking standardised orthographies, annotated corpora, and dedicated processing tools. This track invites submissions on novel research and resources aimed at bridging this gap and advancing the state of the art in Arabic language technology. Topics of interest include, but are not limited to: * Dialect identification and classification * Creation of corpora and lexical resources for Arabic dialects * Machine translation between MSA and dialects, and across different dialects * Speech recognition and synthesis for dialectal Arabic * Computational modelling of morphology, syntax, and semantics for dialects * NLP applications (e.g., sentiment analysis, NER) for dialectal user-generated content * Code-switching between Arabic dialects, MSA, and other languages Submissions and Publication _LaTeLL'2026_ welcomes high-quality submissions in English, which may take one of the following two forms: * Regular (long) papers: Up to eight (8) pages in length, presenting substantial, original, completed, and unpublished research. * Short (poster) papers: Up to four (4) pages in length, suitable for concise or focused contributions, ongoing research, negative results, system demonstrations, and similar work. Short papers will be presented during a dedicated poster session. The conference will not consider submissions consisting of abstracts only. All accepted papers (both long and short) will be published as electronic proceedings (with ISBN) and made available on the conference website at the time of the event. The organisers intend to submit the proceedings for inclusion in the ACL Anthology. To prepare your submission, please make sure to use the LaTeLL'2026 style files available here: LaTeX: https://drive.google.com/file/d/1RceWyUqjFLEbv_oNto-x2Quop7qT4-wf/view?usp=… [2] Word: https://docs.google.com/document/d/1m6VeC9jtMpe-Ku2QREgrPlE2-NTDvJvZ/edit?u… [3] Overleaf: https://www.overleaf.com/read/ttzzfcnjrgvw#e82bef [4] Papers should be submitted through Softconf/START using the following link: https://softconf.com/p/latell2026 Authors of papers receiving exceptionally positive reviews will be invited to prepare extended and substantially revised versions for submission to a leading journal in the field of Natural Language Processing (NLP). The conference will also feature a Student Workshop, and awards will be presented to the authors of outstanding papers. Important dates * Submissions due: 1 June 2026 * Notification of acceptance: 21 July 2026 * Camera-ready due: 31 July 2026 * Conference: 30 September, 1 October and 2 October 2026 Keynote speaker Nizar Habash (New York University Abu Dhabi) Organisation Conference Chair Ruslan Mitkov (Lancaster University and University of Alicante) Programme Committee Chairs Saad Ezzini (King Fahd University of Petroleum & Minerals) Salima Lamsiyah (University of Luxembourg) Tharindu Ranasinghe (Lancaster University) Organising Committee Maram Alharbi (Lancaster University) Salmane Chafik (Mohammed VI Polytechnic University) Ernesto Estevanell (University of Alicante) Milica Ikonić Nešić (University of Belgrade) Further information and contact details The follow-up calls will provide more details on the conference venue and registration. The conference website is www.latell.org/2026/ [1] and will be updated on a regular basis. For further information, please email 2026(a)latell.org Registration will open before the end of April 2026. Links: ------ [1] http://www.latell.org/2026/ [2] https://drive.google.com/file/d/1RceWyUqjFLEbv_oNto-x2Quop7qT4-wf/view?usp=… [3] https://docs.google.com/document/d/1m6VeC9jtMpe-Ku2QREgrPlE2-NTDvJvZ/edit?u… [4] https://www.overleaf.com/latex/templates/latell-26-template/kfcvbgxmccvb

1 0

2026

2025

2024

2023

2022

Corpora April 2026