- Corpora - ELRA lists

Convocatoria premio RutaMdL al mejor artículo en Modelos de Lenguaje
by ANSELMO PEÑAS PADILLA 21 Apr '26

21 Apr '26

La Red de Investigación para la Asesoría sobre la Construcción, Evaluación y Uso de Modelos de Lenguaje convoca el Primer Premio RutaMdL al mejor artículo científico sobre la construcción o uso de Modelos de Lenguaje Para optar al premio, el primer autor del artículo debe haber estado afiliado a un centro español en el momento de su publicación. Se podrán presentar artículos publicados en abierto en los dos últimos años (2025 y 2026). Únicamente se podrá presentar un artículo con el mismo primer autor. Los artículos se enviarán mediante el siguiente formulario: https://forms.gle/R3hdCjxNKZkEjjeH8 El comité científico valorará tanto indicadores cuantitativos (citas, prestigio del congreso, impacto de la revista, etc.) como indicadores cualitativos (contribuciones del trabajo, resultados, etc.). El ganador del premio recibirá una bolsa de viaje (inscripción y dietas de alojamiento y manutención) para asistir al Congreso de la Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN), donde recogerá el premio en un acto oficial. El plazo para la presentación de artículos termina el día 30 de junio de 2026. El comité científico que evaluará los artículos candidatos está formado por: Eneko Agirre, Universidad del País Vasco / Euskal Herriko Unibertsitatea (UPV/EHU) Aitor González, Barcelona Supercomputing Center Nombre (BSC) Alfonso Ureña, Universidad de Jaén (UJA) Anselmo Peñas, Universidad Nacional de Educación a Distancia Nombre (UNED) Senén Barro, Universidade Santiago de Compostela (USC) Manuel Palomar, Universidad de Alicante (UA) David Camacho, Universidad Politécnica de Madrid (UPM) Mariona Taulé, Universitat de Barcelona (UB) Lluís Padró, Universitat Politécnica de Catalunya (UPC) Rafael Valencia, Universidad de Murcia (UM) Aitor Soroa, Universidad del País Vasco / Euskal Herriko Unibertsitatea (UPV/EHU) Julio Gonzalo, Universidad Nacional de Educación a Distancia Nombre (UNED) Rafael Muñoz, Universidad de Alicante (UA) [uned.png] Anselmo Peñas Catedrático de Universidad Director del departamento de Lenguajes y Sistemas Informáticos [separador-uned.png] ETSI Informática, UNED anselmo(a)lsi.uned.es nlp.uned.es/~anselmo @anselpp 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

[CfP] CLiC-it 2026 - Twelfth Italian Conference on Computational Linguistics | 14-16 September 2026 | Palermo, Italy
by Daniel Russo 21 Apr '26

21 Apr '26

[Apologies for Cross Posting] ══════════════════════════════ *CLiC-it 2026 – Twelfth Italian Conference on Computational Linguistics* *14–16 September 2026 | Palermo, Italy* ══════════════════════════════ Conference Website: https://clic2026.unipa.it/ Contact Email: clicit2026(a)unipa.it We are pleased to invite submissions to *CLiC-it 2026*, the *Twelfth Italian Conference on Computational Linguistics*, to be held in *Palermo* from the *14th to the 16th of September 2026* and *organized by AILC* (http://www.ai-lc.it/ ). Over the years, CLiC-it has evolved into an *important forum* for the *Italian community* of researchers in *Computational Linguistics *(CL) and *Natural Language Processing* (NLP). The conference aims to promote and disseminate *high-quality, original research* covering different aspects of automatic language processing, involving both written and spoken language, and seeks to showcase cutting-edge theoretical findings, experimental methodologies, technologies, and application perspectives. CLiC-it has an inclusive spirit, bringing together researchers from Computational Linguistics, NLP, Linguistics, Cognitive Science, Machine Learning, Computer Science, Knowledge Representation, Information Retrieval, and Digital Humanities. Contributions on all languages are welcome, with a particular emphasis on Italian. *TOPICS* Topics include but are not limited to: - Machine Learning and Modeling for NLP - Large Language and Foundation Models - Interpretability, Analysis, and Explainability of NLP Models - Resources, Benchmarks, and Evaluation - Syntax, Morphology, and Phonology - Semantics, Discourse, and Pragmatics - Linguistic Theories, Cognitive Modeling, and Psycholinguistics - Natural Language Generation and Summarization - Dialogue Systems and Conversational AI - Question Answering and Reading Comprehension - Creativity, Style, and Narrative Generation - Information Extraction and Text Mining - Sentiment Analysis, Opinion Mining, and Argumentation - Multilingual and Cross-Lingual NLP - Low-Resource NLP and Linguistic Diversity - Computational Historical Linguistics, Social Science, and Cultural Analytics - Speech and Spoken Language Processing - Multimodal and Grounded Language - Applied NLP and NLP Systems - Ethics, Fairness, and Societal Impacts of NLP *SUBMISSIONS* *Regular Papers.* Original, complete, and unpublished work. Up to 11 pages of main content (with unlimited references/appendix). One additional page will be granted upon acceptance. Short vs. Regular paper classification will be upon publication based on paper length (short papers are typically 5-9 pages, regular papers are 10+ pages). Papers may be in English or Italian, with an English abstract. Accepted papers will be published in the proceedings and presented orally or as a poster during the conference. *Research Communications. *Outstanding papers accepted in 2025–2026 at major CL/NLP venues (A* CORE, Q1 SCImago, ANVUR Class A) may be submitted as a one-page abstract for presentation at the conference (not included in proceedings). All Submissions via START: https://softconf.com/p/clic-it2026 Select the "Papers and Research Communications" track. *Note*: All submissions must be compatible with CEUR (https://ceur-ws.org/) and include the CEUR Declaration on Generative AI section ( https://ceur-ws.org/GenAI/Policy.html). Papers missing this section will be desk rejected. *Templates:* - LaTeX: https://clic2026.unipa.it/wp-content/uploads/2026/02/CLiC_it_2026_CEURART_L… - ODT: https://clic2026.unipa.it/wp-content/uploads/2026/02/CLiC_it_2026_CEURART_O… - Overleaf (read-only): https://www.overleaf.com/read/qmhnsrbyqskw#96f442 *IMPORTANT DATES* *Submission deadline: **29 May 2026 *🚨 Notification to authors: 10 July 2026 Camera-ready due: 31 July 2026 Conference: 14–16 September 2026 *AWARDS* *Best Paper Award *— for papers with a Master's or PhD student as first author and presenter. Recipients of the award will be invited to submit an extended version of the paper to IJCoL. *"Emanuele Pianta" Prize* — for the best Master's Thesis (Tesi di Laurea Magistrale) in Computational Linguistics submitted at an Italian university and supervised by an AILC member. Prize: €500 + free AILC membership + free CLiC-it registration. *ORGANIZATION* *Conference Chairs:* Valerio Basile (University of Torino) Danilo Croce (University of Roma Tor Vergata) Lucia Passaro (University of Pisa) Roberto Pirrone (University of Palermo) *Senior Program Committee:* Pierpaolo Basile, Alessandro Bondielli, Cristina Bosco, Tommaso Caselli, Gloria Gagliardi, Gianluca E. Lebani, Elisa Leonardelli, Eleonora Litta, Marta Marchiori Manerba, Martina Miliani, Simonetta Montemagni, Giovanni Puccetti, Giulia Rambelli, Rachele Sprugnoli, Fabio Tamburini *Local Organizing Committee (University of Palermo):* Irene Siragusa (Lead), Germano Ammirata, Salvatore Contino, Luca Cruciata, Francesco Foderà *Publicity and Social Media Chairs:* Alessandro Bondielli (University of Pisa) Pierluigi Cassotti (University of Gothenburg) Daniel Russo (Fondazione Bruno Kessler) *Proceedings Chairs:* Francesca Grasso (University of Torino) Eliana Di Palma (University of Torino) *Web Chairs:* Salvatore Contino, Luca Cruciata, Irene Siragusa *CONTACTS * Website: https://clic2026.unipa.it/ Email: clicit2026(a)unipa.it We look forward to seeing you in Palermo! *The CLiC-it 2026 Organizing Committee* -- -- Le informazioni contenute nella presente comunicazione sono di natura privata e come tali sono da considerarsi riservate ed indirizzate esclusivamente ai destinatari indicati e per le finalità strettamente legate al relativo contenuto. Se avete ricevuto questo messaggio per errore, vi preghiamo di eliminarlo e di inviare una comunicazione all’indirizzo e-mail del mittente. -- The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you received this in error, please contact the sender and delete the material.

1 0

EURALEX Talks: ‘Pattern and Construction in Learner Dictionaries’ Susan Hunston (29 April 2026 at 12pm CET - online)
by REES, GERAINT PAUL 21 Apr '26

21 Apr '26

On 29 April 2026 at 12pm CET, Professor Susan Hunston will give a talk entitled ‘Pattern and Construction in Learner Dictionaries’ as part of the European Association for Lexicography (EURALEX) Talks series. This talk is based on a Leverhulme-funded project (EM-2022-022) seeking to unify three approaches to grammar and lexis in English: Pattern Grammar, Construction Grammar, and Systemic Functional Grammar. These represent three approaches to the description of grammar and lexis, from the point of view of observation, cognition, and social semiotic respectively. The talk first explores the relationship between patterns and constructions, with examples from the 50 verb complementation patterns analysed in the project. It discusses how a focus on construction might influence the format of learner dictionaries. The talk then considers the relationship between constructions and systemic networks, speculating on potential resources for learners based on meaning networks. Examples are taken from the 10 semantic fields discussed in the project. Further details can be found on the EURALEX talks page <https://euralex.org/euralex-talks/> We hope to see you there. Geraint Rees On behalf of the EURALEX Board

1 0

2 PhD positions at AI4DH European centre of Excellence
by Antoine Doucet 21 Apr '26

21 Apr '26

--------------------------------------------------------------------------------------------------------------------------- ------------ Doctoral positions - AI4DH - University of Ljubljana, Slovenia------------ --------------------------------------------------------------------------------------------------------------------------- The University of Ljubljana has 2* open PhD positions *in artificial intelligence for digital humanities (AI4DH) in the context of the *European centre of excellence in AI4DH*. These positions are associated with the ELEXAI (European Lexicographic Infrastructure for Artificial Intelligence) project, where newly admitted PhD students will research and develop large language models and agentic interfaces for multilingual knowledge management, using high-quality lexicographic resources. At the heart of the vibrant European capital city of Ljubljana, close to both the Alps and the Mediterranean, you will be part of an AI research group working, dedicated to AI research that can be applied to DH. You will benefit from *competitive salaries* and *top-notch infrastructure*, based in the faculty of computer and information science, yet in an *interdisciplinary context*. Full details are available here: - *Doctoral positions, for up to 3 years*: https://euraxess.ec.europa.eu/jobs/429925 *Important dates: * - *Information sessions:* 22 April at 10am CEST and 5 May at 3pm CEST (see registration details on Euraxess) - Application *deadline: 22 May* CEST (Ljubljana time)

1 0

[CFP] 3rd Workshop on Language Models for Underserved Communities (LM4UC)
by Fred PHILIPPY 21 Apr '26

21 Apr '26

We are excited to announce the 3rd Language Models for Underserved Communities (LM4UC) workshop, co-located with IJCAI 2026. The workshop will take place in person and virtually between August 15-17, 2026, in Bremen. LM4UC invites researchers, practitioners, and policymakers to address challenges and propose innovative solutions for building and deploying language models (LMs) for underserved languages and communities. Underserved communities often lack adequate access to advanced NLP technologies due to limited linguistic data, insufficient computational resources, or inadequate AI governance frameworks. This gap hinders equitable access to NLP advancements, exacerbating the digital divide. Our workshop aims to address this by fostering a multidisciplinary dialogue around the development of LMs that prioritize cultural sensitivity, resource efficiency, and sustainable AI practices. Topics of Interest We invite submissions of full papers, ongoing work, position papers, and survey papers on topics including, but not limited to: 1. Evaluation Design: Evaluations are no longer passive datasets. They are mechanisms that shape model development. We invite research that focuses on principled, technically grounded benchmark design. 2. Cultural Alignment & Safety: Most alignment research assumes Western norms. We invite papers that focus on technically grounded alignment methods that generalize across cultures and languages. 3. Agentic Systems in Global Environments: As LLMs become agents, we need formal evaluation and control in multilingual, multi-cultural environments. Submission Guidelines We welcome long papers (8 pages) and short papers (4 pages), excluding references. Submissions must follow the IJCAI 2026 style guidelines. Important Dates * Submission deadline: May 24, 2026 * Notification of acceptance: June 7, 2026 * Camera-ready paper due: August 1, 2026 * Workshop dates: August 15/16/17, 2026 Submit your paper via OpenReview: https://openreview.net/group?id=ijcai.org/IJCAI/2026/Workshop/LM4UC Contact Us: For inquiries, please contact the workshop organizer: lm4uc.organizers(a)gmail.com<mailto:lm4uc.organizers@gmail.com> <mailto:lm4uc.organizers@gmail.com>

1 0

[RetroEval 2026] Deadline Extension
by Saad Mahamood 20 Apr '26

20 Apr '26

RetroEval 2026: Symposium on Natural Language Generation Evaluations ============================================ 1-2 June 2026, Aberdeen, Scotland, United Kingdom https://retroeval.github.io/ ============================================ Evaluation in the field of Natural Language Generation (NLG) has changed considerably over the past several decades. This special symposium in honour of Prof. Ehud Reiter’s retirement provides a forum for academic and industry researchers to look back on the topic of how evaluations in the field of NLG have changed and to explore unaddressed challenges. The two day symposium will be held in-person at the Sir Duncan Rice Library in the historic University of Aberdeen, June 1-2, 2026. For this symposium, we welcome submissions of long papers, short papers, and extended abstracts. *** Workshop Theme *** Ehud Reiter has been a leading light in Natural Language Generation (NLG) research throughout the four decades he worked in this area, in both academia (Aberdeen) and industry (CoGenTech; Arria NLG). Ehud’s influence extends to all aspects of NLG, but the areas in which it has arguably been the strongest is evaluation of NLG systems. On the occasion of his retirement, this workshop, which is held in his honour, will therefore focus on evaluation of NLG systems, highlighting in particular some of the topics that Ehud has tended to emphasize (see below) such as the importance of reproducibility and the risks of data contamination. *** Topics of Interest *** Topics of interest include (but are not limited to) the following: -- The aims of NLG and NLG evaluation -- Intrinsic versus extrinsic NLG evaluation -- Evaluation of NLG systems in the real world -- Impact assessment of NLG systems and LLMs -- New evaluation challenges arising from the use of LLMs -- Hallucination annotation and its role in NLG evaluation -- Statistical analysis for NLG evaluations -- Data contamination in NLG evaluation -- LLMs as evaluators: opportunities and pitfalls -- The role of LLMs in the development of evaluation metrics -- Reproduction and reproducibility of human evaluation experiments -- Publication bias: What to do with negative results? -- Pre-publication of research hypotheses in NLG evaluation -- NLG evaluation versus psycholinguistic experimentation: what can we learn from each other? -- Disciplinary cultures and evaluation methods -- Evaluating NLG systems/LLMs for assistive technology *** Submission Types *** The workshop accepts the following submission types: • Long Papers (archival) • Short Papers (archival) • Extended Abstracts (non-archival) Accepted contributions will be presented as oral or poster presentations. *** Archival Submissions *** • Long papers: • Up to 8 pages (excluding references) • Unlimited references • Up to 2 appendix pages • 1 additional page in the final version to address reviewer comments • Short papers: • Up to 4 pages (excluding references) • Unlimited references • Up to 1 appendix page • 1 additional page in the final version for reviewer comments *** Non-Archival Submissions *** • Extended abstracts: • Up to 2 pages including references • 1 additional appendix page for tables/figures • Selection based on the symposium fit *** Submission Format *** • Two-column ACL 2026 format • LaTeX template only • PDF submissions only • Submissions via OpenReview *** Important Dates *** Note: All deadlines are 23:59 UTC-12. • ARR commitment deadline (archival): 16 March, 2026 * Direct paper submission deadline (non-archival): 17 April, 2026 • Extended Direct paper submission deadline (archival): 28 April, 2026 (was 24 April, 2026) • New Notification of acceptance: 11 May, 2026 (was 8 May, 2026) • Camera-ready deadline: 22 May, 2026 • Symposium dates: 1-2 June, 2026 *** Review Policy *** Long and short papers will follow ACL double-blind review policies. Submissions must be anonymized, including self-references and links. Papers violating anonymity requirements will be rejected without review. Demo descriptions are exempt from anonymization. Contact and Information • Website: https://retroeval.github.io/ • Email: retroeval(a)googlegroups.com <mailto:retroeval@googlegroups.com> Workshop Organisers: Saad Mahamood (Shopware), David Howcroft (University of Aberdeen), Kees van Deemter (Utrecht University), Albert Gatt (Utrecht University), Simone Balloccu (TU Darmstadt), Margaret Mitchell (Hugging Face), Alberto Bugarín Diz (CiTIUS & University of Santiago de Compostela), Jose María Alonso-Moral (CiTIUS & University of Santiago de Compostela), Adarsa Sivaprasad (University of Aberdeen), Chenghua Lin (Manchester University), and Alexandra Johnstone (University of Aberdeen).

1 0

Deadline extension: BriGap-3, Bridges and Gaps between Formal and Computational Linguistics
by Timothée Bernard 20 Apr '26

20 Apr '26

*Deadline extension: BriGap-3, Bridges and Gaps between Formal and Computational Linguistics* Venue: Université Paris Cité, campus des Grands moulins, *Paris, France* Event date: *July 11th, 2026* Event website: https://brigap-workshop.github.io/ *BriGap-3 is a venue for formal linguists, computational linguists, and NLP scientists to meet: what fruitful interactions can we have? How do we build upon each other’s work?* ** Context ** Due to the groundbreaking achievements of the last decade, the ongoing discourse in NLP has shifted more to what can be achieved through language than studying language for its own sake, and traditional conferences are increasingly dominated by engineering-oriented work. It could thus appear that computational and formal linguistics are more than ever separate domains. Yet, we are also witnessing a growing interest in linguistics in both explaining the successes of neural models and uncovering their limitations. Conversely, all kinds of computational methods have proven their usefulness for linguistics time and again. To what extent are these traditions truly divorced, and what fruitful bridges can be (re)built? To answer these questions, the third iteration of the workshop on Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) intends to provide a space for formal linguists, computational linguists, and NLP scientists to exchange their perspectives on how their different domains of research can build upon one another. ** Event topics ** - investigation of the linguistic properties of machine learning models, - linguistic representations, vector space semantics, and their relations with theoretical concepts such as compositionality, - use of computational and information-theoretical methods for linguistic inquiry, - formal distributional semantics and neural-symbolic integration for NLP, - formal grammars, symbolic structures and their applications for computational linguistics and NLP, - trends in the history of computational linguistics and NLP, - … ** Invited speakers ** - *Raquel FERNÁNDEZ*, Universiteit van Amsterdam - *Tal LINZEN*, New York University (online) ** Submission details ** The event is designed with a widely inclusive submission policy so as to foster as vibrant a discussion as possible. In particular, we will accept: - Archival submissions, corresponding to novel and unpublished research, to be included in the event proceedings, - Non-archival submissions, corresponding to work in progress, early results, and articles presented in other venues that engage with the topics of the event. The event accepts both archival (original and unpublished research) submissions in either short (up to 4 pages) or long (up to 8 pages) format, and non-archival (work-in-progress, dissemination of research published or accepted elsewhere, etc.) submissions in short (up to 4 pages) format. Camera-ready versions of papers will be given one additional page of content so that reviewers’ comments can be taken into account. Each submission should mention whether it targets archival or non-archival status. Archival papers accepted at BriGap-3 will be indexed in the ACL Anthology. Please use the ACL style templates available here: https://github.com/acl-org/acl-style-files Submission link: https://openreview.net/group?id=BriGap/2026/Workshop Please be aware that to submit on OpenReview, you need an OpenReview profile, and that the activation process might take up to two weeks (in case you do not use an institutional email). While it is often syntactically correct and coherent to some extent, the text produced by current generative AI systems falls below our expectations in terms of depth, clarity, and precision. Conceptual clarity and argumentation will be key criteria in the evaluation of submissions. We therefore *strongly* discourage the use of AI systems. In addition, the detection of any hallucinations in a submission (whether in the bibliography or elsewhere) will lead to rejection, regardless of the other qualities of the text. ** Important dates *- Extended submission deadline: Sunday, May 3rd, 2026* (23:59 AoE) - Notification of acceptance: Monday, May 11th 2026 - Event: Saturday, July 11th, 2026 ** Contact ** For questions, please send an email to brigapworkshop(a)gmail.com or contact one of the event chairs: - Timothée Bernard, Université Paris Cité - Emmanuele Chersoni, Hong Kong Polytechnic University - Giulia Rambelli, Università di Bologna

1 0

HealTAC 2026 – Early Bird Deadline Approaching
by Jaya Chaturvedi 20 Apr '26

20 Apr '26

-------------------------------------------- HealTAC 2026 June 8-10th, 2026, Brighton (UK) https://healtac2026.github.io/ -------------------------------------------- Following the notification of decisions, we’re excited to share the next steps as we look ahead to HealTAC 2026 in Brighton this June. -------------------------------------------- Register Early & Plan Your Stay -------------------------------------------- Registration is open, and we encourage you to secure your place ahead of the early-bird deadline (May 4, 2026). Discounted hotel rates are also available for a limited time, so we recommend booking soon to take advantage of these offers. Please book your accommodation before 11 May, when the discount will be removed. Full details on registration<https://healtac2026.github.io/registration/> and accommodation are available on the conference<https://healtac2026.github.io/accommodation/> website. -------------------------------------------- Keynote Speakers -------------------------------------------- We are delighted to welcome our keynote speakers: * Professor Aline Villavicencio (University of Exeter) * Dr Martin Krallinger (Barcelona Supercomputing Center) Their talks will provide inspiring perspectives on this year’s theme: Human-Centered AI & NLP: Bridging Research and Real-World Practice. ------------------------------------------------------ Pre-Conference Workshops (June 8, 2026) ------------------------------------------------------ Workshop 1 Focused on the safe and responsible use of free-text healthcare data within Trusted Research Environments (TREs), this session will showcase DARE UK–funded projects (STAR-TRE, FORTRESS, TRExt, SAFETEXT), highlighting emerging tools and best practices for secure, privacy-preserving text analytics. Workshop 2 From patient narratives to insights: applying text analytics to scalable lived experience data for new discoveries An interactive two-hour workshop exploring how text analytics can be applied to patient-reported narratives and lived experience data at scale, bringing together perspectives from NLP, behavioural science, qualitative research, PPIE, and policy communities. ------------------ Key Dates ------------------ * Early-bird registration deadline: May 4, 2026 * Discounted hotel bookings deadline: May 11, 2026 * Pre-conference workshops: June 8, 2026 * Conference: June 9–10, 2026 --------------------------------------------- Registration Fees -------------------------------------------- Early registration fees (by 4th May, 2026): Full registration: £240 Student registration: £140 Presenting student registration: £40 Late registration fees (after 4th May, 2026): Full registration: £340 Student registration: £190 The fee includes participation for three days (including the pre-conference workshop day). All fees include a conference dinner on 9 June 2026. Follow the conference announcements on social media at #HEALTAC2026 We are looking forward to welcoming you to HealTAC 2026 in Brighton! Jaya Chaturvedi BDS MSc PhD Research Associate in Health Related Natural Language Processing Department of Biostatistics and Health Informatics C3.15, Social Genetic and Developmental Psychiatry Centre Institute of Psychiatry, Psychology & Neuroscience King’s College London PO Box 80, De Crespigny Park London SE5 8AF Pronunciation: Jah-yah Pronouns: she/her GitHub: https://github.com/jayachaturvedi Bluesky: @Jayachatur.bsky.social LinkedIn: https://www.linkedin.com/in/jayachaturvedi/ [cid:image001.png@01DAF499.ADF8D370] If you receive an email from me outside of normal working hours, please do not feel the need to respond outside of your own working hours.

1 0

CfP: RAGE-KG Workshop at ISWC 2026
by a.graciotti＠rug.nl 20 Apr '26

20 Apr '26

Dear subscribers of Corpora, We are happy to share the Call for Papers for the 3rd Retrieval-Augmented Generation Enabled by Knowledge Graphs (RAGE-KG) workshop, which will be co-hosted with the International Semantic Web Conference (ISWC) 2026 in Bari, Italy, October 25-29, 2026. We share all the details below. On behalf of the Organizing Committee, Arianna Graciotti —-- RAGE-KG 2026: Retrieval-Augmented Generation Enabled by Knowledge Graphs - International Semantic Web Conference - Bari, Italy, October 25-29, 2026 - Conference website: https://2026.rage-kg.org/ - Submission link: https://easychair.org/conferences/?conf=ragekg2026 - Abstract registration deadline: July 17, 2026 - Submission deadline: July 24, 2026 RAGE-KG explores the state of the art and goes beyond in integrating Retrieval-Augmented Generation (RAG) with Knowledge Graphs as well as the synergies between Large Language Models and the Linked Open Data ecosystem. We aim to foster innovative RAG architectures relying on Semantic Web standards and new approaches to make Linked Open Data usable by LLMs, enhancing their ability to generate reliable, verifiable and context-aware responses based on structured, decentralized and authoritative data sources. Submission Guidelines - Short papers describing novel research contributions and preliminary results. Related to workshop topics. 4-6 pages excluding references. - Full papers describing novel research contributions of extended length. Related to workshop topics. 8-12 pages excluding references. The papers will be peer-reviewed (single-blind) by multiple researchers. Upon acceptance, one author must register at the conference and present at the workshop. List of Topics: - RAG Architectures - RAG and KAG (Knowledge-Augmented Generation) architectures leveraging Knowledge Graphs, Semantic Web standards and Linked Data - RAG and KAG design patterns, including GraphRAG and AI Agents - Evaluating RAG and KAG architectures with structured data - LLMs and Structured Data - Training and fine-tuning LLMs with structured data - Prompting Language Models with structured data - Language Model-supported and ontology-supported SPARQL query generation Innovative Approaches: - Neurosymbolic approaches for integrating Language Models with Linked Open Data, Semantic Web and Knowledge Graphs - Use Cases, Work-In-Progress and, especially, Bold Proposals for RAG systems Special track on RAG-systems for Human-AI Value Alignment: - RAG-based approaches for content moderation and harm reduction; - Designing RAG systems to deal with human subjectivity Committees: - Organizing committee: - Daniel Dobriy - Marco Antonio Stranisci - Arianna Graciotti - Blerina Spahiu - Sahar Vahdati Publication: Papers will be submitted to be published with CEUR (https://ceur-ws.org/) and must follow the 1-column CEUR format: - Overleaf template (https://www.overleaf.com/latex/templates/template-for-submissions-to-ceur-w…) - Latex template (http://ceur-ws.org/Vol-XXX/CEURART.zip) Venue - Where: ISWC 2026 | Bari, Italy - When: October 25–26, 2026 Contact - All questions about submissions should be emailed to daniel.dobriy(a)wu.ac.at

1 0

Stellenausschreibung bei der Universität Hildesheim
by Gertrud Faaß 20 Apr '26

20 Apr '26

Am Institut für Informationswissenschaft und Sprachtechnologie der Universität Hildesheim ist eine 100%-Stelle für wissenschaftliche Mitarbeiterinnen oder Mitarbeiter zu besetzen. Die Besetzung erfolgt baldmöglichst, bis 31.10.2029, mit evtl. Verlängerung um 6 Monate (TV-L E 13), Bewerbungsschluss ist der 7. Mai 2026. Im Verbundprojekt EDIKILEX, 'Interdisziplinäre Zugänge und digitale Methoden im Umgang mit frühneuhochdeutschen Texten', werden KI-Verfahren entwickelt, die die Lemmatisierung und Semantisierung frühneuhochdeutscher Wörter und Wortverbindungen erlauben. Die Ergebnisse sollen für Editionsarbeiten und für die Weiterentwicklung des 'Frühneuhochdeutschen Wörterbuchs' der AdW Göttingen nutzbar gemacht werden können. Dafür sollen in Hildesheim eine modulare Architektur des Gesamtsystems und Schnittstellen für unterschiedliche Zielgruppen entwickelt werden. Aufgaben: * Mitwirkung am Design und der Implementierung einer modularen Architektur des EDIKILEX-Systems; * Mitwirkung am Design und der Implementierung von Nutzerschnittstellen für verschiedene Nutzergruppen des EDIKILEX-Systems; * Dokumentation und Publikation der eigenen Projektarbeiten innerhalb des Projekts und auf wissenschaftlichen Tagungen; * Mitwirkung am Forschungsdatenmanagement. Voraussetzungen: * Abgeschlossenes wissenschaftliches Hochschulstudium in Computerlinguistik, Informatik, Informationswissenschaft, Digital Humanities, Software Engineering oder in einem Studiengang mit vergleichbaren Inhalten; * Kompetenz des Deutschen auf Niveau C1 des Europäischen Referenzrahmens und gute Englischkenntnisse; * Programmiererfahrung (Skript- und Auszeichnungssprachen); * Erfahrung im Aufbau kollaborativ entwickelter Softwaresysteme (Architekturen, Modularisierung, Schnittstellen, Datenaustausch, ...) und/oder in der Gestaltung von Nutzerschnittstellen (Methoden des user-centered design, agile Erstellung von Prototypen, ...). Wünschenswert: * Erfahrungen in der Entwicklung von Datenbanken; * Interesse an früheren Sprachstufen (speziell Frühneuhochdeutsch). Weitere Infos: Stellenausschreibung i.A. Prof Ulrich Heid (ulrich.heid(a)uni-hildesheim.de), Gertrud Faaß -- Gertrud Faaß, PhD/University of Pretoria Universität Hildesheim Institut für Informationswissenschaft und Sprachtechnologie Arbeitsgruppe Computerlinguistik (IwiSt-CL) Orcid-ID Email: gertrud.faass(a)uni-hildesheim.de Büro: Bühler Campus, LN129 Tel. 05121 883 30314 Fax. 05121 883 30315 Mein Pronomen: sie | Gerne können Sie mir mitteilen, wie Sie angesprochen werden möchten.

1 0

2026

2025

2024

2023

2022

Corpora