- Corpora - ELRA lists

CNRS Research Associate Positions (Laboratoire de Linguistique Formelle)
by Olivier Bonami 10 Oct '25

10 Oct '25

The Laboratoire de Linguistique Formelle ([http://]www.llf.cnrs.fr, LLF) is seeking to support applications in linguistics and language sciences to Research Associate positions at the French Centre National de la Recherche Scientifique (cnrs.fr <http://cnrs.fr/>). CNRS Research Associate positions are full-time permanent positions intended for candidates in their early career. Applicants must hold a PhD by the application deadline. Knowledge of French is not required. Although CNRS recruits researchers by way of a national competition, applicants are encouraged to select one or more research labs to which they would like to be assigned, and support is crucial for a successful application. Located at Université Paris Cité (u-paris.fr <http://u-paris.fr/>), the LLF has about 70 members, including 33 permanent faculty members, working on every subfield of linguistics. In recent years, it has extended its focus from formal and theoretical linguistics to domains such as psycholinguistics, sociolinguistics, experimental linguistics, computational linguistics, dialogue, typology, and Sign language linguistics. The LLF is interested in supporting a limited number of applicants, with an excellent research record and willing to develop a project that would fit the lab's areas of inquiry. The official call for application will be published in early December, 2025 with an application deadline in early January, 2026 (https://carrieres.cnrs.fr/en/external-competitions-for-researchers-m-f/). Prospective applicants that wish to be supported by the LLF are invited to contact the lab by December 12, sending a CV (including a publication list) and a short description of their research profile to direction.llf(a)listes.u-paris.fr <mailto:direction.llf@listes.u-paris.fr>. Decisions on whether support is granted will be taken by December 19. Heather Burnett Directrice de recherches au CNRS Directrice du Laboratoire de Linguistique Formelle UMR 7110 - Université Paris Cité & CNRS Tel: +33 1 57 27 57 97 Olivier Bonami Professeur de linguistique Université Paris Cité & Laboratoire de Linguistique Formelle Bâtiment Olympe de Gouges 8 place Paul Ricoeur, 75013 Paris Bureau 640

1 0

International Multimodal Communication Symposium (MMSYM 2026) in Leuven
by Patrizia Paggio 10 Oct '25

10 Oct '25

We would like to draw your attention to the 3rd edition of the International Multimodal Communication Symposium (MMSYM 2026), which will be held in Leuven (Belgium) from 9-11 September 2026. http://www.mmsym.org/<http://www.mmsym.org/> The third edition of MMSYM continues the symposium series on multimodal communication previously held in Frankfurt am Main (2024) and Barcelona (2023). The symposium aims at gaining insights into the interaction and/or co-dependence of semiotic resources in spoken and signed language. To advance our understanding of communication, the symposium aims at further integrating multimodality as an integral part of linguistics and cognitive science. This overarching goal of the symposium is rooted in the conviction that investigating multimodality is key to understanding how language and communication work. For MMSYM 2026, we welcome contributions approaching multimodal communication from different methodological and disciplinary angles. The main topic of this edition of the symposium is “Embodied communication in (inter)action”. We particularly encourage submissions that approach the main theme from one of the following angles: (1) multimodal pragmatics and interaction analysis, (2) (generative) multimodal behavior modelling, (3) creating and sharing sustainable multimodal data, and (4) exploring the interface of gesture and signed language. For MMSYM 2026, we particularly encourage contributions relating to these conference themes but are open for all submissions related to multimodal communication. TOPICS INCLUDE BUT ARE NOT LIMITED TO - Gesture-speech interaction & integration - Prosody-Gesture-coordination - Multimodal language processing - Gesture & sign language interaction - Sequential organization of multimodal behavior in (face-to-face) interaction - Semantics-pragmatics interface & multimodal communication - Multimodal communication & spatial configurations - Kinematics of bodily movements - Multimodal corpus development - Annotation schemes and tools for multimodal data processing - Machine and deep learning techniques applied to multimodal data - Multimodal human-computer interaction and conversational agents - Intercultural aspects of embodied behavior - Multimodal aspects of language acquisition and learning (both L1 and L2) - Multimodal communication disorders and communication support - Multimodal health communication IMPORTANT DATES - Abstract submissions welcome from 15th November 2025 - Abstract submission deadline: 1st March 2026 - Notification of acceptance: 3rd April 2026 - Conference dates: 9-11th September 2026 KEYNOTE SPEAKERS We are delighted to announce four keynote speakers whose work relates to the main themes of the conference: - Pamela Perniss (Universität zu Köln) - Elisabeth Zima (Universität Zürich) - Stefan Kopp (Bielefeld University) - Wim Pouw (Tilburg University) ABSTRACT SUBMISSION DEADLINES We invite abstract submissions for 20-minute oral presentations (15 minutes for the presentation and 5 minutes for discussion) or posters of original, unpublished work on any aspect of multimodal communication. Abstracts should be written in English and should be submitted via OpenReview.net<http://openreview.net/> (submissions will be welcome starting from 15th November 2025). Please check the website (http://www.mmsym.org/<http://www.mmsym.org/>) with the call for papers, important deadlines and keynote speakers for more details. We hope to welcome you in Leuven for an exciting MMSYM conference! On behalf of the organizers Geert Brône, Bert Oben and Julie Janssens **** Patrizia Paggio Associate Professor University of Copenhagen Centre for Language Technology paggio(a)hum.ku.dk<mailto:paggio@hum.ku.dk> Professor (retired) University of Malta Institute of Linguistics and Language Technology patrizia.paggio(a)um.edu.mt<mailto:patrizia.paggio@um.edu.mt> Selected recent publications and upcoming projects: Paggio, P., Mitterer, H., Attard, G., & Vella, A. (2025). Do hand gestures increase perceived prominence in naturally produced utterances? Language and Cognition, 17, e54. doi:10.1017/langcog.2025.20 MultiplEYE DK - Enabling multilingual eye-tracking data collection - Funded by the Carlsberg Foundation https://www.carlsbergfondet.dk/det-har-vi-stoettet/cf24-2005/

1 0

Postdoc position: Text Simplification + Machine Translation for Horizon Europe project, Barcelona, Spain
by Horacio Saggion 10 Oct '25

10 Oct '25

We are hiring: Postdoctoral position to carry out research and development in the areas of (i) multilingual text simplification and (ii) multilingual and multicultural machine translation relying on state-of-the-art deep neural models and architectures (LLMs). The work is to be carried out in the context of the Horizon Europe project IDEAL (Inclusive Democratic Engagement and Language Technologies in Europe) which addresses several languages. TALN group, Department of Engineering, Pompeu Fabra University. Barcelona, Spain How to apply: https://lnkd.in/dpssFU7a TALN: https://lnkd.in/ePKttcZX Department: https://lnkd.in/dGEWbHsb UPF: https://www.upf.edu/ -- Horacio Saggion Full Professor / Chair in Computer Science and Artificial Intelligence Head of the Natural Language Processing Group - TALN Project Coordinator iDEM Project (HE) Co-PI of the AI-BOOST project (HE) Co-PI of the IDEAL project (HE) Universitat Pompeu Fabra https://twitter.com/h_saggion https://www.linkedin.com/in/horacio-saggion-1749b916 -- Horacio Saggion Full Professor / Chair in Computer Science and Artificial Intelligence Head of the Natural Language Processing Group - TALN Project Coordinator iDEM Project (HE) Co-PI of the AI-BOOST project (HE) Co-PI of the IDEAL project (HE) Universitat Pompeu Fabra https://twitter.com/h_saggion https://www.linkedin.com/in/horacio-saggion-1749b916

1 0

[Deadline Extension] 3rd Workshop on AI for Scientific Publications (WASP) at IJCNLP-AACL 2025
by Tirthankar Ghosal 09 Oct '25

09 Oct '25

****Call for Papers WASP @ IJCNLP-AACL 2025**** *https://ui.adsabs.harvard.edu/WIESP/2025/ <https://ui.adsabs.harvard.edu/WIESP/2025/>* Building on the success of the First Workshop on Information Extraction from Scientific Publications (WIESP) at AACL-IJCNLP 2022 and the Second WIESP at IJCNLP-AACL 2023, the Third Workshop on Artificial intelligence for Scientific Publications (WASP) at IJCNLP-AACL 2025 aims to establish itself as a pivotal platform for promoting discussions and research in the field of Natural Language Processing (NLP) and Artificial Intelligence (AI). This gathering will bring together esteemed experts and renowned organizations with students and early-career researchers who are interested and invested in efforts to extract and mine the world’s scientific knowledge from research papers. Their collaboration will be focused on developing advanced algorithms, models, and tools that will lay the foundation for future machine comprehension of scientific literature. The third iteration of WASP will specifically concentrate on various topics related to Artificial Intelligence research for scientific publications: ****Topics (not limited to)**** - *Scientific document parsing and structured information extraction* - *Scientific named-entity recognition and concept identification* - *Citation context/span extraction and citation-based knowledge mining* - *Argument extraction and scientific discourse analysis* - *Scientific article summarization and headline generation* - *Question-answering and fact retrieval from scientific literature* - *Prompt engineering and retrieval-augmented generation (RAG) for science Q&A* - *Chain-of-thought reasoning and scientific problem-solving with LLMs* - *LLM-powered information extraction from scientific texts* - *Pretraining and fine-tuning LLMs on scientific corpora* - *Evaluation and alignment of LLMs for scientific understanding* - *AI-assisted scientific discovery and hypothesis generation* - *Ethical and responsible use of LLMs in scientific publishing* - *Large Language Reasoning Models for Scientific Discovery* - *LLM hallucinations and impact on scientific knowledge, publications* - *Challenges, Future of AI in Scientific Publishing* - *AI, Peer Review, and Scientific Publishing* - *Impact of Generative AI on Scientific Publishing* *In addition to papers, WASP will also host a shared task. * ****Telescope Reference and Astronomy Categorization Shared (TRACS)**** https://ui.adsabs.harvard.edu/WIESP/2025/shared_task We will publish a separate CfP on the shared task. Shared task authors will be invited to write their system descriptions, which will then undergo light peer review. All accepted papers and shared task system papers will be published in the WASP proceedings as part of IJCNLP-AACL 2025 and indexed in the ACL Anthology. ****Important Dates**** - *NEW Paper submission deadline (WASP): October 13, 2025* - *ARR commitment deadline: October 27, 2025* - Notification of paper acceptance (WASP+TRACS): November 3, 2025 - Camera-ready submission deadline (WASP+TRACS): November 11, 2025 - Workshop: December 23, 2025 (hybrid) - All submission deadlines are 11.59 pm UTC -12h (“Anywhere on Earth”) ****Paper Submission Site**** *https://openreview.net/group?id=aclweb.org/AACL-IJCNLP/2025/Workshop/WASP <https://openreview.net/group?id=aclweb.org/AACL-IJCNLP/2025/Workshop/WASP>* Submission will be via OpenReview. Submissions should follow the ACLPUB formatting guidelines and use the provided template files. Paper formatting guidelines - ACLPUB <https://acl-org.github.io/ACLPUB/formatting.html> Submissions (Long and Short Papers) will be subject to a double-blind peer-review process. We follow the same policies as IJCNLP-AACL 2025 regarding anonymity, preprints, and double submissions. Please reach out to the organizers (cc'ed) for any queries. Thank you! -- +++++++++++++++++++++++++++++++++++ Dr. Tirthankar Ghosal <https://www.tirthankarghosal.com/> Scientist (NLP/AI and HPC) <https://www.ornl.gov/staff-profile/tirthankar-ghosal> National Center for Computational Sciences (NCCS) Oak Ridge National Laboratory, United States & Affiliate Faculty (NLP/AI) <https://bredesencenter.utk.edu/faculty/tirthankar-ghosal/> University of Tennessee Knoxville United States ++++++++++++++++++++++++++++++++++++

1 0

First Call for Papers : Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS’2026)
by Ranasinghe, Tharindu 09 Oct '25

09 Oct '25

𝗦𝗲𝗰𝗼𝗻𝗱 𝗜𝗻𝘁𝗲𝗿𝗻𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗼𝗻 𝗡𝗮𝘁𝘂𝗿𝗮𝗹 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 𝗮𝗻𝗱 𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝗳𝗼𝗿 𝗖𝘆𝗯𝗲𝗿 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 (𝗡𝗟𝗣𝗔𝗜𝗖𝗦’𝟮𝟬𝟮𝟲) University of Alicante, Alicante, Spain 11 and 12 June 2026 https://nlpaics2026.gplsi.es/ 𝗙𝗶𝗿𝘀𝘁 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀 Recent advances in Natural Language Processing (NLP), Deep Learning and Large Language Models (LLMs) have resulted in improved performance of applications. In particular, there has been a growing interest in employing AI methods in different Cyber Security applications. In today's digital world, Cyber Security has emerged as a heightened priority for both individual users and organisations. As the volume of online information grows exponentially, traditional security approaches often struggle to identify and prevent evolving security threats. The inadequacy of conventional security frameworks highlights the need for innovative solutions that can effectively navigate the complex digital landscape for ensuring robust security. NLP and AI in Cyber Security have vast potential to significantly enhance threat detection and mitigation by fostering the development of advanced security systems for autonomous identification, assessment, and response to security threats in real-time. Recognising this challenge and the capabilities of NLP and AI approaches to fortify Cyber Security systems, the Second International Conference on Natural Language Processing (NLP) and Artificial Intelligence (AI) for Cyber Security (NLPAICS’2026) continues the tradition from NLPAICS’2024 to be a gathering place for researchers in NLP and AI methods for Cyber Security. We invite contributions that present the latest NLP and AI solutions for mitigating risks in processing digital information. 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝘁𝗼𝗽𝗶𝗰𝘀 The conference invites submissions on a broad range of topics related to the employment of NLP and AI (and in general, language studies and models) for Cyber Security including but not limited to: - 𝘚𝘰𝘤𝘪𝘦𝘵𝘢𝘭 𝘢𝘯𝘥 𝘏𝘶𝘮𝘢𝘯 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 𝘢𝘯𝘥 𝘚𝘢𝘧𝘦𝘵𝘺 - Content Legitimacy and Quality - Detection and mitigation of hate speech and offensive language - Fake news, deepfakes, misinformation and disinformation - Detection of machine generated language in multimodal context (text, speech and gesture) - Trust and credibility of online information - User Security and Safety - Cyberbullying and identification of internet offenders - Monitoring extremist fora - Suicide prevention - Clickbait and scam detection - Fake profile detection in online social networks - Technical Measures and Solutions - Social engineering identification, phishing detection - NLP for risk assessment - Controlled languages for safe messages - Prevention of malicious use of ai models - Forensic linguistics - Human Factors in Cyber Security - 𝘚𝘱𝘦𝘦𝘤𝘩 𝘛𝘦𝘤𝘩𝘯𝘰𝘭𝘰𝘨𝘺 𝘢𝘯𝘥 𝘔𝘶𝘭𝘵𝘪𝘮𝘰𝘥𝘢𝘭 𝘐𝘯𝘷𝘦𝘴𝘵𝘪𝘨𝘢𝘵𝘪𝘰𝘯𝘴 𝘧𝘰𝘳 𝘊𝘺𝘣𝘦𝘳 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 - Voice-based security: Analysis of voice recordings or transcripts for security threats - Detection of machine generated language in multimodal context (text, speech and gesture) - NLP and biometrics in multimodal context - 𝘋𝘢𝘵𝘢 𝘢𝘯𝘥 𝘚𝘰𝘧𝘵𝘸𝘢𝘳𝘦 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 - Cryptography - Digital forensics - Malware detection, obfuscation - Models for documentation - NLP for data privacy and leakage prevention (DLP) - Addressing dataset “poisoning” attacks - 𝘏𝘶𝘮𝘢𝘯-𝘊𝘦𝘯𝘵𝘳𝘪𝘤 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 𝘢𝘯𝘥 𝘚𝘶𝘱𝘱𝘰𝘳𝘵 - Natural language understanding for chatbots: NLP-powered chatbots for user support and security incident reporting - User behaviour analysis: analysing user-generated text data (e.g., chat logs and emails) to detect insider threats or unusual behaviour - Human supervision of technology for Cyber Security - 𝘈𝘯𝘰𝘮𝘢𝘭𝘺 𝘋𝘦𝘵𝘦𝘤𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘛𝘩𝘳𝘦𝘢𝘵 𝘐𝘯𝘵𝘦𝘭𝘭𝘪𝘨𝘦𝘯𝘤𝘦 - Text-Based Anomaly Detection - Identification of unusual or suspicious patterns in logs, incident reports or other textual data - Detecting deviations from normal behaviour in system logs or network traffic - Threat Intelligence Analysis - Processing and analysing threat intelligence reports, news, articles and blogs on latest Cyber Security threats - Extracting key information and indicators of compromise (IoCs) from unstructured text - 𝘚𝘺𝘴𝘵𝘦𝘮𝘴 𝘢𝘯𝘥 𝘐𝘯𝘧𝘳𝘢𝘴𝘵𝘳𝘶𝘤𝘵𝘶𝘳𝘦 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 - Systems Security - Anti-reverse engineering for protecting privacy and anonymity - Identification and mitigation of side-channel attacks - Authentication and access control - Enterprise-level mitigation - NLP for software vulnerability detection - Malware Detection through Code Analysis - Analysing code and scripts for malware - Detection using NLP to identify patterns indicative of malicious code - 𝘍𝘪𝘯𝘢𝘯𝘤𝘪𝘢𝘭 𝘊𝘺𝘣𝘦𝘳 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 - Financial fraud detection - Financial risk detection - Algorithmic trading security - Secure online banking - Risk management in finance - Financial text analytics - 𝘌𝘵𝘩𝘪𝘤𝘴, 𝘉𝘪𝘢𝘴, 𝘢𝘯𝘥 𝘓𝘦𝘨𝘪𝘴𝘭𝘢𝘵𝘪𝘰𝘯 𝘪𝘯 𝘊𝘺𝘣𝘦𝘳 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 - Ethical and Legal Issues - Digital privacy and identity management - The ethics of NLP and speech technology - Explainability of NLP and speech technology tools - Legislation against malicious use of AI - Regulatory issues - Bias and Security - Bias in Large Language Models (LLMs) - Bias in security related datasets and annotations - 𝘋𝘢𝘵𝘢𝘴𝘦𝘵𝘴 𝘢𝘯𝘥 𝘙𝘦𝘴𝘰𝘶𝘳𝘤𝘦𝘴 𝘧𝘰𝘳 𝘊𝘺𝘣𝘦𝘳 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 𝘈𝘱𝘱𝘭𝘪𝘤𝘢𝘵𝘪𝘰𝘯𝘴 - 𝘚𝘱𝘦𝘤𝘪𝘢𝘭𝘪𝘴𝘦𝘥 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 𝘈𝘱𝘱𝘭𝘪𝘤𝘢𝘵𝘪𝘰𝘯𝘴 𝘢𝘯𝘥 𝘖𝘱𝘦𝘯 𝘛𝘰𝘱𝘪𝘤s - Intelligence applications - Emerging and innovative applications in Cyber Security 𝘚𝘱𝘦𝘤𝘪𝘢𝘭 𝘛𝘩𝘦𝘮𝘦 𝘛𝘳𝘢𝘤𝘬 - 𝘍𝘶𝘵𝘶𝘳𝘦 𝘰𝘧 𝘊𝘺𝘣𝘦𝘳 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘺 𝘪𝘯 𝘵𝘩𝘦 𝘌𝘳𝘢 𝘰𝘧 𝘓𝘓𝘔𝘴 𝘢𝘯𝘥 𝘎𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘷𝘦 𝘈𝘐 NLPAICS 2026 will feature a special theme track with the goal of stimulating discussion around Large Language Models (LLMs), Generative AI and ensuring their safety. The latest generation of LLMs, such as CHATGPT, Gemini, DeepSeek, LLAMA and open-source alternatives, has showcased remarkable advancements in text and image understanding and generation. However, as we navigate through uncharted territory, it becomes imperative to address the challenges associated with employing these models in everyday tasks, focusing on aspects such as fairness, ethics, and responsibility. The theme track invites studies on how to ensure the safety of LLMs in various tasks and applications and what this means for the future of the field. The possible topics of discussion include (but are not limited to) the following: • Detection of LLM-generated language in multimodal context (text, speech and gesture) • LLMs for forensic linguistics • Bias in LLMs • Safety benchmarks for LLMs • Legislation against malicious use of LLMs • Tools to evaluate safety in LLMs • Methods to enhance the robustness of language models 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻𝘀 𝗮𝗻𝗱 𝗣𝘂𝗯𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻 NLPAICS welcomes high-quality submissions in English, which can take two forms: • Regular long papers: These can be up to eight (8) pages long, presenting substantial, original, completed, and unpublished work. • Short (poster) papers: These can be up to four (4) pages long and are suitable for describing small, focused contributions, ongoing research, negative results, system demonstrations, etc. Short papers will be presented as part of a poster session. The conference will not consider and evaluate abstracts only. Accepted papers, including both long and short papers, will be published as e-proceedings with ISBN will available online on the conference website at the time of the conference and are expected to be uploaded into the ACL Anthology. Further details on the submission procedure will be made available in the Second Call for Papers due in October 2025. The conference will feature a student workshop and awards will be offered to the authors of best papers. 𝗜𝗺𝗽𝗼𝗿𝘁𝗮𝗻𝘁 𝗱𝗮𝘁𝗲𝘀 • Submissions due: 16 March 2026 • Reviewing process: 1 April – 30 April 2026 • Notification of acceptance: 5 May 2026 • Camera-ready due: 19 May 2026 • Conference camera-ready proceedings ready 1 June 2026 • Conference: 11-12 June 2026 𝗢𝗿𝗴𝗮𝗻𝗶𝘀𝗮𝘁𝗶𝗼𝗻 𝙲̲𝚘̲𝚗̲𝚏̲𝚎̲𝚛̲𝚎̲𝚗̲𝚌̲𝚎̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲𝚜̲ ̲ Ruslan Mitkov (University of Alicante) Rafael Muñoz (University of Alicante) 𝙿̲𝚛̲𝚘̲𝚐̲𝚛̲𝚊̲𝚖̲𝚖̲𝚎̲ ̲𝙲̲𝚘̲𝚖̲𝚖̲𝚒̲𝚝̲𝚝̲𝚎̲𝚎̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲𝚜̲ Elena Lloret (University of Alicante) Tharindu Ranasinghe (Lancaster University) 𝙿̲𝚞̲𝚋̲𝚕̲𝚒̲𝚌̲𝚊̲𝚝̲𝚒̲𝚘̲𝚗̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲ Ernesto Estevanell (University of Alicante) 𝚂̲𝚙̲𝚘̲𝚗̲𝚜̲𝚘̲𝚛̲𝚜̲𝚑̲𝚒̲𝚙̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲ Andres Montoyo (University of Alicante) 𝚂̲𝚝̲𝚞̲𝚍̲𝚎̲𝚗̲𝚝̲ ̲𝚆̲𝚘̲𝚛̲𝚔̲𝚜̲𝚑̲𝚘̲𝚙̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲ Salima Lamsiyah (University of Luxembourg) 𝙱̲𝚎̲𝚜̲𝚝̲ ̲𝙿̲𝚊̲𝚙̲𝚎̲𝚛̲ ̲𝙰̲𝚠̲𝚊̲𝚛̲𝚍̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲ Saad Ezzini (King Fahd University of Petroleum & Minerals) 𝙿̲𝚞̲𝚋̲𝚕̲𝚒̲𝚌̲𝚒̲𝚝̲𝚢̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲ Beatriz Botella (University of Alicante) 𝚂̲𝚘̲𝚌̲𝚒̲𝚊̲𝚕̲ ̲𝙿̲𝚛̲𝚘̲𝚐̲𝚛̲𝚊̲𝚖̲𝚖̲𝚎̲ ̲𝙲̲𝚑̲𝚊̲𝚒̲𝚛̲ Alba Bonet (University of Alicante) 𝗩𝗲𝗻𝘂𝗲 The Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS’2026) will take place at the University of Alicante and is organised by the University of Alicante GPLSI research group. Further information and contact details The follow-up calls will list keynote speakers and members of the programme committee once confirmed. The conference website is https://nlpaics2026.gplsi.es/ and will be updated on a regular basis. For further information, please email nlpaics2026(a)dlsi.ua.es Registration will open in February 2026. Best Regards Tharindu Ranasinghe Dr Tharindu Ranasinghe | Lecturer in Security and Protection Science School of Computing and Communications | Lancaster University Contact me on Teams<https://teams.microsoft.com/l/chat/0/0?users=t.ranasinghe@lancaster.ac.uk> www.lancaster.ac.uk<https://www.lancaster.ac.uk/>

1 0

Two public online talks in October (16th, 23rd) on Large Language Models, for accessibility or evaluation (NLPV seminars, Exeter)
by h.dong2＠exeter.ac.uk 09 Oct '25

09 Oct '25

We welcome you to the next Natural Language Processing and Vision (NLPV) seminars at the University of Exeter. Talk 1 Scheduled: Thursday 16 Oct 2025 at 13:00 to 14:00, GMT+1 Location: https://Universityofexeter.zoom.us/j/94505914598?pwd=eXonSrKHuxUNnMCAmiZHic… (Meeting ID: 945 0591 4598 Password: 903478) Title: This One or That One? A Bilingual Study on Accessibility via Demonstratives with Multimodal Large Language Models Abstract: Accessibility describes how easily a speaker can obtain or interact with an object, and it is often conveyed through demonstrative pronouns like “this" and “that" in English or “这” (zhè) and “那” (nà) in Chinese, indicating proximal or distal objects. The proximal vs. distal distinction is not absolute, since it depends on the speaker's viewpoint. Are Multimodal Large Language Models (MLLMs) able to solve accessibility problems based on demonstratives? In this talk, I would like to present some preliminary results on a referent identification task based on a bilingual (English and Chinese), multimodal dataset. In our experiments, all models show significant struggles, and particularly when perspective shifts are introduced. Speaker's bio: Emmanuele Chersoni got a joint PhD in Language Sciences from Aix-Marseille University and the University of Pisa in 2018, under the supervision of Philippe Blache and Alessandro Lenci. Since 2021, he is an Assistant Professor in Computational Linguistics at the Department of Language Science and Technology of The Hong Kong Polytechnic University. His main research interests include classical distributional semantic models, thematic fit modeling, semantic relations and natural language processing for specialized domains. He has also served as a co-organizer of the *ACL workshop series on Cognitive Modeling and Computational Linguistics from 2019 to 2022. Talk 2 Scheduled: Thursday 23 Oct 2025 at 15:00 to 16:00, GMT+1 Location: https://Universityofexeter.zoom.us/j/92868830537?pwd=0yvSNEwhIeC3x2Mxn76zOr… (Meeting ID: 928 6883 0537 Password: 100657) Title: Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts Abstract: Evaluating natural language generation (NLG) systems is inherently challenging. While human evaluation remains the gold standard, it is difficult to scale and often suffers from inconsistencies and demographic biases. LLM-based evaluation offers a scalable alternative but is highly sensitive to prompt design, where small variations can lead to significant discrepancies. In this talk, I will introduce an inversion learning method that learns effective reverse mappings from model outputs back to their input instructions, enabling the automatic generation of highly effective, model-specific evaluation prompts. This method is simple, requires only a single evaluation sample, and eliminates the need for manual prompt engineering, thereby improving both the efficiency and robustness of LLM-based evaluation. Speaker's bio: Chenghua Lin is a Full Professor and Chair in Natural Language Processing in the Department of Computer Science at The University of Manchester. His research lies at the intersection of machine learning and natural language processing, with a focus on language generation, multimodal LLMs, and evaluation methods. He currently serves as Chair of the ACL SIGGEN Board, a member of the IEEE Speech and Language Processing Technical Committee, and Associate Editor for Computer Speech and Language. He has received several prizes and awards for his research and academic leadership, including the CIKM Test-of-Time Award, the INLG Best Paper Runner-up Award, and an Honourable Mention for the Scottish Informatics and Computer Science Alliance (SICSA) Supervisor of the Year Award. He has also held numerous program and chairing roles for *ACL conferences, including Documentation Chair for ACL’25, Publication Chair for ACL’23, Workshop Chair for AACL-IJCNLP’22, Program Chair for INLG’19, and Senior Area Chair for EMNLP’20, ACL’22–’23, EACL’23, NAACL’25, and AACL’25. We will update future talks on the website: https://sites.google.com/view/neurocognit-lang-viz-group/seminars Joining our *Google group* for future seminar and research information: https://groups.google.com/g/neurocognition-language-and-vision-processing-g…

1 0

3rd call, training data ready: UniDive shared tasks on idiomaticity and multiword expressions
by Agata Savary 09 Oct '25

09 Oct '25

**3rd CALL FOR PARTICIPATION** Two peas in a pod:PARSEME 2.0 and AdMiRe 2.0 multilingual UniDive shared tasks on idiomaticity and multiword expressions https://unidive.lisn.upsaclay.fr/doku.php?id=other-events:parseme-admire-st… <https://unidive.lisn.upsaclay.fr/doku.php?id=other-events:parseme-admire-st…> Expression of interest: https://forms.gle/rwSfUmNR1sTsHDfx6 <https://forms.gle/rwSfUmNR1sTsHDfx6> ==================================================================== The UniDive COST Action <https://unidive.lisn.upsaclay.fr/>is happy to announce ADMIRE 2 and the PARSEME 2.0 shared tasks dedicated to detecting and interpreting idiomaticity and multiword expressions(MWEs). MWEs are groups of words that have non-compositional semantics, i.e. their meanings cannot be straightforwardly deduced from the meanings of their components. For instance, a bad appleis a person who has a bad influence on others. Both shared tasks will take place together and we hope to co-organise the workshop with SIGLEX-MWE section <https://multiword.org/>and co-locate it with EACL 2026 in Morocco(24-29 March 2026). The participating teams are to submit the results of their systems on CodaBench <https://www.codabench.org/>. The submission links will be published at the same time as the test data. We are delighted to confirm that UniDive <https://unidive.lisn.upsaclay.fr/>will provide funding <https://unidive.lisn.upsaclay.fr/doku.php?id=other-events:parseme-admire-st…>for selected system presenters. Important dates ----------------- * [1 OCTOBER] Training data and baseline systems released * [3 DECEMBER] Publication of test blind data * [8 DECEMBER] Submission of system predictions * [19 DECEMBER] Systems evaluated * [5 JANUARY] Submission deadline for system description papers * [9-23 JANUARY] Reviewing period (system teams will participate as reviewers) * [3 FEBRUARY] Submission deadline for camera-ready papers * [24-29 MARCH 2026] EACL, including the MWE workshop(to confirm) PARSEME 2.0is a shared task whose main objective is to identify and paraphrase multiword expressions (MWEs) in written text. We propose two subtasks: the first corresponds to the classical identification task in running text. The second consists in paraphrasing a sentence containing a MWE, so as to remove idiomaticity. Data annotation is finished and 17 languages are covered: Dutch, Egyptian (ca. 2700-2000 BC), French, Georgian, Greek (Ancient), Greek (Modern), Hebrew, Japanese, Latvian, Persian, Polish, Portuguese (Brazilian), Romanian, Serbian, Slovene, Swedish, and Ukrainian. Subtask 1 is on MWEs identification and Subtask 2 on paraphrasing MWEs. AdMIRe 2.0 (Advancing Multimodal Idiomaticity Representation) addresses the challenge of multilingual and multimodal idiomatic language understanding by evaluating how well models interpret potentially idiomatic expressions (PIEs) across languages and across modalities using both text and images. This new edition extends the AdMIRe 1 task <https://arxiv.org/pdf/2503.15358>adding more languages from the UNIDIVE network and beyond. Given a context sentence containing a PIE and a set of five images, the task is to rank the images based on how accurately they depict the meaning of the PIE used in that sentence. The task will be zero-shot for newly introduced languages. While the task is designed to encourage participation from teams working on multilingual and multimodal technologies, it also accommodates approaches focused only on a subset of the languages and on a single modality (text) with automatically generated descriptive captions for each image, allowing models to rely exclusively on text input if desired. Data ----------------- * Training data for AdMiRe 2.0: https://semeval2025-task1.github.io/data/training/training_data.html <https://semeval2025-task1.github.io/data/training/training_data.html> * Training data for PARSEME 2.0: https://gitlab.com/parseme/sharedtask-data/-/tree/master/2.0 <https://gitlab.com/parseme/sharedtask-data/-/tree/master/2.0> Organizing team --------------- PARSEME 2.0: * Manon Scholivet, Université Paris Saclay, LISN, FR * Takuya Nakamura, Université Paris Saclay, LISN, FR * Agata Savary, Université Paris Saclay, LISN, FR * Éric Bilinski, Université Paris Saclay, LISN, FR * Carlos Ramisch, Aix-Marseille Université, LIS, FR ADMIRE 2 : * Adriana Pagano <https://secure-web.cisco.com/1YAGKjWKddhtqiA-9wwpTzBrRHqMWqraLLDCi63yoSQPHp…>, Universidade Federal de Minas Gerais, BR * Aline Villavicencio <https://secure-web.cisco.com/17hRYtc48CxUTuQ_Lm5LvtIDhREp6JpTTNFu3smb4Yyjp1…>, University of Exeter, UK * Dilara Torunoğlu Selamet <https://secure-web.cisco.com/1U3Kz5oRS8032U7C3ikqTwLrLuHnRujaiXILauGPxfilqd…>, Istanbul Technical University, TR * Doğukan Arslan <https://secure-web.cisco.com/1iCwzaJ-FPO1KSa7r0luNlHcUTrCy6K9Wm8I3pk9d_-iG8…>, Istanbul Technical University, TR * Gülşen Eryiğit <https://secure-web.cisco.com/1nP_yCeZKo55vzyCSp6J79GtmP_8EODYLoOnic4AHIQmdV…>, Istanbul Technical University, TR * Rodrigo Wilkens <https://secure-web.cisco.com/1zTIs9aO7VfKy_Sg1CYj8xiCPOZhZHkSPR2xYyMQE456pF…>, University of Exeter, UK * Tom Pickard <https://secure-web.cisco.com/1AbiBJ6cGhN9SrjpkIlBYQeo08-8YJIDUds7Qfs3H5_KpL…>, University of Sheffield, UK * Wei He <https://secure-web.cisco.com/1HrUa3BUU6pl9p4Ia2mMqmEqrPU834VAhFFDUvAV6PbjrP…>, University of Exeter, UK

1 0

Shared task for spontaneous speech ASR
by Robert Pugh 08 Oct '25

08 Oct '25

Mozilla Data Collective (the new platform where Mozilla Common Voice datasets, among other datasets, are hosted) just kicked off a Shared Task on Spontaneous Speech ASR. It targets 21 underrepresented languages (from Africa, the Americas, Europe, and Asia), brand-new datasets, and prizes for the best systems in each task. For more information, visit https://community.mozilladatacollective.com/shared-task-mozilla-common-voic… Robert Pugh Senior Community Manager mozillafoundation.org (UTC-7)

1 0

Monthly online ILFC Seminar: interactions between formal and computational linguistics
by Timothée Bernard 08 Oct '25

08 Oct '25

Monthly online ILFC Seminar: interactions between formal and computational linguistics https://gdr-lift.loria.fr/monthy-online-ilfc-seminar/ The LIFT 2 research group is happy to announce the forthcoming sessions of the ILFC seminar on the interactions between formal and computational linguistics. The seminar is held on Zoom. To attend the seminar and get updates, please subscribe to our mailing list (we now only rarely communicate through other mailing lists): https://sympa.inria.fr/sympa/subscribe/seminaire_ilfc - 2025/10/15 16:30-17:30 UTC+2: *Noga Zaslavsky* (New York University) Title: *Cultural evolution of efficient semantic systems in humans and AI* Abstract: *Human languages efficiently compress meanings into words, but how did our semantic systems evolve to be that way? Are AI systems capable of evolving efficient semantic systems and representing meaning as we do? In this talk, I address these open questions from cognitive, cultural, and computational perspectives. First, I show that individual human learners favor efficiently compressed semantic representations. This inductive learning bias, when amplified via cultural transmission, drives the evolution of near-optimally efficient semantic systems. Second, I consider large language models (LLMs) and show that while they vary widely in their semantic alignment with humans, they nevertheless exhibit a similar tendency toward efficient compression: when simulating cultural evolution with LLMs, they iteratively restructure initially random semantic systems towards greater efficiency. Finally, I show that introducing an explicit pressure for efficient compression, grounded in the information bottleneck principle, enables multi-agent reinforcement learning systems to evolve efficient, human-like semantic systems without any human supervision. Taken together, these results demonstrate how humans and AI can evolve efficient semantic systems through social interaction and cultural transmission, and more broadly, they suggest that efficient compression may be a fundamental principle of intelligence.* - 2025/11/26 16:30-17:30 UTC+1: *Ece Takmaz* (Utrecht University) Title: [TBA] Abstract: [TBA] - 2025/12/17 16:30-17:30 UTC+1: *Ethan Wilcox* (Georgetown University) Title: [TBA] Abstract: [TBA] - 2026/01/21 16:30-17:30 UTC+1: *Gemma Boleda* (Universitat Pompeu Fabra) Title: [TBA] Abstract: [TBA] - 2026/03/18 16:30-17:30 UTC+1: *Adele Goldberg* (Princeton University) Title: [TBA] Abstract: [TBA]

1 0

Deadline Extension – International Workshop on Spoken Dialogue (IWSDS) 2026 (Trento, Italy)
by Giuseppe Riccardi 08 Oct '25

08 Oct '25

Dear all, We are pleased to announce that the submission deadline for the 16th International Workshop on Spoken Dialogue Systems (IWSDS 2026) has been extended: 📅 Important Dates (Extended): 📝 Paper Submission Deadline: October 12 → October 22, 2025 🔄 Paper Update Deadline: October 18 → October 28, 2025 ✅ Acceptance Notification: December 10, 2025 🎤 Workshop Dates: February 26 – March 1, 2026 We invite submissions of long papers, short papers, position papers, industry track papers, and demonstrations on a broad range of topics related to the Theoretical Foundations, Systems and Methods, and Applications of spoken and multimodal dialogue systems. Accepted papers will be included in the ACL Anthology. This year’s theme is: 🎯“Human-Machine Dialogue in the Era of Multimodal Foundation Models” Location: Trento, Italy – the gateway to the Dolomites, right after the Milano Cortina 2026 Winter Olympics Website & CfP: https://sites.google.com/unitn.it/iwsds26/ Twitter/X: https://x.com/iwsdsmeeting Bluesky: https://bsky.app/profile/iwsdsmeeting.bsky.social --- Prof. Dr.-Ing. Giuseppe Riccardi Founder and Director of the Signals and Interactive Systems Lab Department of Computer Science and Information Engineering University of Trento Room D206, via Sommarive 5 38123 Povo di Trento, Italy Home Page: http://disi.unitn.it/~riccardi/

1 0