- Corpora - ELRA lists

IWCS 2025: Call for Workshop Proposals
by Kilian Evang 13 Dec '24

13 Dec '24

Call for Workshop Proposals 16th International Conference on Computational Semantics (IWCS) Heinrich Heine University Düsseldorf, Germany 22-24 September 2025 https://iwcs2025.github.io/ IWCS is a biennial conference on computational semantics. This year's edition is organized by Heinrich Heine University Düsseldorf. The conference is endorsed by SIGSEM, the ACL Special Interest Group on Computational Semantics. The aim of IWCS is to bring together researchers interested in any aspects of the computation, annotation, extraction, representation, and learning of meaning in natural language, whether this is from a lexical or structural semantic perspective. IWCS embraces both symbolic and machine learning approaches to computational semantics, and everything in between. The conference and workshops will take place 22-24 September 2025. === WORKSHOP PROPOSALS === We invite proposals for workshops to be held in conjunction with IWCS 2025. Accepted workshops will have the option to publish their proceedings in the ACL Anthology. We solicit proposals in all areas of computational semantics, in other words all computational aspects of meaning of natural language within written, spoken, signed, or multi-modal communication. Workshops are invited on these closely related areas, including the following: * design of meaning representations * syntax-semantics interface * representing and resolving semantic ambiguity * shallow and deep semantic processing and reasoning * hybrid symbolic and statistical approaches to semantics * distributional semantics * alternative approaches to compositional semantics * inference methods for computational semantics * recognizing textual entailment * learning by reading * methodologies and practices for semantic annotation * machine learning of semantic structures * probabilistic computational semantics * neural semantic parsing * computing meaning with large language models * computational aspects of lexical semantics * semantics and ontologies * semantic web and natural language processing * semantic aspects of language generation * generating from meaning representations * semantic relations in discourse and dialogue * semantics and pragmatics of dialogue acts * multimodal and grounded approaches to computing meaning * semantics-pragmatics interface * applications of computational semantics === SUBMISSION INFORMATION === Proposals for workshops should contain: * A title and brief (max two pages) description of the workshop topic and content; * The names, affiliation and email addresses of the organisers; * An estimate of the expected audience size; * If the workshop has been held before, a note specifying where previous workshops were held, how many submissions the workshop received, how many papers were accepted and how many attendees the workshop attracted; * Whether you plan a half-day or full-day workshop; * Whether or not the workshop proceedings should be published in the ACL Anthology. Proposals should be submitted on OpenReview: https://openreview.net/group?id=aclweb.org/SIGSEM/IWCS/2025/Workshop_Propos… The person submitting the proposal will need an OpenReview account. Please note OpenReview's moderation policy, where newly created accounts with an institutional email address are approved automatically, but other email addresses can take up to two weeks to approve. === FINANCES === Workshops must cover their own costs for invited speakers as well as organizers' traveling costs. === IMPORTANT DATES === 31 January 2025 Workshop proposal submissions due 07 February 2025 Workshop proposal notification of acceptance 24 September 2025 Workshop date === CONTACT === For questions, contact: iwcs2025-program-chairs(a)uni-duesseldorf.de Kilian Evang, Laura Kallmeyer, Sylvain Pogodalla (the IWCS 2025 program chairs) -- Dr. Kilian Evang · Institut für Linguistik · Heinrich-Heine-Universität Düsseldorf Universitätsstr. 1 · 40225 Düsseldorf, Germany · https://kilian.evang.name

1 0

NLP4Ecology 2025 – Deadline Extension Announcement
by Valerio Basile 13 Dec '24

13 Dec '24

Great news—we’ve extended the paper submission deadline for our workshop to *December 30th, 2024*. Below is the Call for Papers. Please feel free to share it widely. ------------------------------------------------------------------------------------------------------------- *Call for Papers *for the *NLP4Ecology 2025 Workshop*, titled "The 1st Workshop on Ecology, Environment, and Natural Language Processing," The workshop will be co-located with *the Joint 25th Nordic Conference on Computational Linguistics and the 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)*. We are inviting submissions that explore how NLP and computational linguistics can help address ecological challenges. The workshop focuses on interdisciplinary approaches to tackle the environmental crises by leveraging NLP tools to, e.g., analyze harmful narratives, detect misinformation, and examine public discourse related to ecological issues. Topics of interest include sentiment analysis, bias detection, framing analysis, and more. We aim to attract a highly interdisciplinary audience and welcome contributions at the intersection of *linguistics*, *ecology*, and *computer science*, particularly from fields such as *AI*, *computational linguistics* , *digital humanities*, *ecolinguistics*, *ethics*, *philosophy*, and *environmental humanities, *with the goal of fostering collaboration between the NLP community and scholars from diverse disciplines to explore how language technology can help address climate change and environmental crises. More details on the Call for Papers are on the workshop website <https://econlpws2025.di.unito.it/>. Key dates: *Paper Submission Deadline*: December 16, 2024 *December 30, 2024* *Camera-Ready Deadline*: February 3, 2025 *Workshop Date*: March 2, 2025 (Tallinn, Estonia)

1 0

[IberLEF 2025] Second Call for Task Proposals
by Salud María Jiménez Zafra 11 Dec '24

11 Dec '24

================================= IberLEF 2025 -- Second Call for Task Proposals ================================= IberLEF (the Iberian Language Evaluation Forum) is a shared evaluation campaign of Natural Language Processing systems in Spanish and other Iberian languages, whose 2025 edition will be held as part of the 41th International Conference of the Spanish Society for Natural Language Processing (SEPLN). The 2025 edition of the SEPLN conference will take place in Zaragoza, Spain. The goal of IberLEF is to encourage the research community to organize competitive text processing, understanding and generation tasks, with the aim of defining new research challenges and advancing the state of the art in Natural Language Processing challenges involving at least one of the following Iberian languages: Spanish, Portuguese, Catalan, Basque or Galician. Researchers and practitioners from all areas of Natural Language Processing and related communities are invited to submit task proposals that fit IberLEF goals by December 22, 2024. Proposals must be submitted (as a pdf file) to iberlef(a)googlegroups.com, and should include the following fields: - Title of the task. - Description of the task, highlighting: - Relevance and novelty of the task, and the challenges involved. - Evaluation measures, and other relevant methodological aspects. - Expected target community, and actual or potential industrial takeup. - Related evaluation activities, if any. - Previous editions of the task, if any. If it has been organized previously, what the roadmap is and what the novelties for 2024 are. - Linguistic resources to be gathered, created and/or reused. Please include as many details on data gathering, selection and annotation procedures as possible: sources and representativity, training/validation/test sizes, harvesting procedures, profile of annotators (experts, linguists, crowdworkers, etc.), multiple annotation policy, IPR issues, baselines, etc. - Tentative schedule (note that camera-ready versions of the proceedings must be ready by July 3, 2025). - Organization committee: full name and affiliation of the organizers, with a succinct description of their research interests, areas of expertise and experience organizing similar events. - Funding, if available. - Contact person. - Any other relevant issues. Task organizers duties Note that organizers of accepted tasks are expected to: - Set up the evaluation exercise according to the submitted proposal. - Promote the task within the target research community. - Manage the submission and scientific evaluation of the system description papers of the corresponding systems submitted by the participants. The accepted papers will be published in the IberLEF proceedings. - Prepare and submit an overview of the evaluation exercise. - Present the results of the task at IberLEF 2025. Task selection procedure Each submitted proposal will be reviewed by members of the IberLEF steering and program committee, and decisions will be sent back to the task organizers by January 24, 2025. Proceedings IberLEF 2025 Proceedings including the description of the participating systems will be published at CEUR-WS.org. Task Overviews will be published in the SEPLN journal (http://www.sepln.org/en/journal, indexed in Clarivate ESCI (JCI: 0.21), CiteScore (Scopus): 2,9 and SJR: 0,421) in its September 2025 issue. Task Organizers are expected to notify participants the acceptance of their works by June 20, 2025, and send the camera ready task and system description papers for their task to IberLEF organizers by July 3, 2025. Important dates - Task proposals due: December 22, 2024. - Notification of acceptance: January 24, 2025. - Final date for sending paper acceptance to task participants: June 20, 2025. - Camera ready submissions due: July 3, 2025. - IberLEF Workshop: September 2025. IberLEF general chairs Salud María Jiménez Zafra, SINAI, Universidad de Jaén (Spain) Luis Chiruzzo, Universidad de la República (Uruguay) José Ángel González Barba, Symanto Research (Spain) Website https://sites.google.com/view/iberlef-2025 Contact E-mail: iberlef(a)googlegroups.com ================================= [image: Universidad de Jaén] <http://www.uja.es/> *Salud María Jiménez Zafra* sjzafra(a)ujaen.es Universidad de Jaén Grupo de Investigación SINAI <http://sinai.ujaen.es/> | Departamento de Informática EPS Jaén, Edificio A3, Despacho 326 Campus Las Lagunillas s/n 23071 - Jaén | +34 953212992 [image: Universidad de Jaén] <http://www.uja.es/>

1 0

Ukrainian NLP Workshop @ ACL 2025: First CFP
by Mariana Romanyshyn 11 Dec '24

11 Dec '24

*The Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025) <https://unlp.org.ua/>* *Call For Papers* UNLP 2025 <https://unlp.org.ua/> will be held *online* on July 31 or August 1, 2025, in conjunction with ACL 2025. The workshop will bring together leading professionals from academia and industry who develop language resources, tools, and NLP solutions for the Ukrainian language or do cross-lingual research that can be applied to the Ukrainian language. The workshop will facilitate developments in the processing of the Ukrainian language, as well as provide a platform for discussion and sharing of ideas, encourage collaboration between different research groups, and improve the visibility of the Ukrainian research community. Topics of interest lie in the area of Ukrainian NLP and Computational Linguistics and include, but are not limited to, the following tasks: - morphosyntactic tagging, - named-entity recognition, - syntactic and semantic parsing, - coreference resolution, - information extraction and text mining, - automated question answering and information retrieval, - language modelling and natural language generation, - grammatical error correction, - text summarization, - machine translation, - sentiment analysis, - argument mining, - disinformation detection and fact verification, - development of language resources and evaluation methods, - speech recognition and generation, - knowledge representation and computational pragmatics, - computational semantics, - computational methods for phonology, - cross-lingual models applicable to Ukrainian, - Ukrainian dialects, sociolects, and code-switching, - Ukrainian NLP in interaction with other artificial intelligence technologies. *Note: *The workshop will accept research papers for the Crimean Tatar language with the aim of supporting this severely endangered language of the indigenous people of Ukraine. The workshop will also accept papers with negative results. *Shared Task* UNLP 2025 organizes a Shared Task on Detecting Social Media Manipulation. This Shared Task aims to challenge and assess AI capabilities to detect and classify manipulation, laying the groundwork for progress in cybersecurity and the identification of disinformation within the context of Ukraine. Organized jointly with Texty.org.ua, the task will be based on 9,500 Telegram posts manually annotated for ten manipulation techniques by media experts. The shared task will have two tracks: techniques classification and detection of manipulative text spans. More details will follow soon. Check for updates at https://unlp.org.ua/. *Important dates* April 14, 2025 — Workshop paper due (direct submission) May 5, 2025 — Pre-reviewed ARR commitment deadline May 12, 2025 — Notification of acceptance June 2, 2025 — Camera-ready papers due June 30, 2025 — Pre-recorded video due July 31 or August 1, 2025 — Workshop *Submissions* UNLP invites submissions of completed and ongoing projects. Submissions describing resources or solutions that have been made available to the broader public are strongly encouraged. We invite two types of submissions: long and short papers. Long papers should describe original, unpublished, and completed work. The short papers may describe work in progress, small focused contributions, system demonstrations, new linguistic resources, or experiments based on existing software and resources. The paper submission link will be added soon. Check for updates at https://unlp.org.ua/. The workshop will provide Grammarly Premium to all authors. To request Grammarly Premium, please fill in this form <https://docs.google.com/forms/d/e/1FAIpQLSemG2fVh_KJo6JZF9pC4TNQ9gdMawd-TC_…> . *Workshop Organizers* *Main Organizers* Andrii Hlybovets, National University of Kyiv-Mohyla Academy, Ukraine Mariana Romanyshyn, Grammarly, Ukraine Olena Nahorna, Grammarly, Germany Oleksii Ignatenko, Ukrainian Catholic University, Ukraine *Shared Task Organizers* Nataliia Romanyshyn, Ukrainian Catholic University, Ukraine Oleksii Syvokon, Microsoft, Ukraine Roman Kyslyi, Igor Sikorsky Kyiv Polytechnic Institute, Ukraine Volodymyr Sydorskyi, Igor Sikorsky Kyiv Polytechnic Institute, Ukraine Find our program committee at https://unlp.org.ua/committees/. *Follow us* Website: https://unlp.org.ua/. X: https://x.com/UNLP_workshop. Telegram: https://t.me/UNLP_workshop. Facebook: https://www.facebook.com/UNLPworkshop. Email: info(a)unlp.org.ua.

1 0

12th Workshop on Argument Mining @ACL2025: Call for Shared Task Proposals
by Gabriella Lapesa 11 Dec '24

11 Dec '24

12th Workshop on Argument Mining - Call for Shared Task Proposals (Deadline: January 7th) We cordially invite submissions of shared task proposals, as part of ArgMining 2025, the “12th Workshop on Argument Mining”. The workshop will be co-located with ACL 2025 (to be held in Vienna, Austria). The call for papers will be circulated separately, in the next days Argument mining (also known as “argumentation mining”) is a gradually maturing research area within computational linguistics. It involves the automatic identification of argumentative structures in free text, as well as argument quality assessment, argument persuasiveness, and the synthesis of argumentative texts. To advance research on specific aspects of argument mining, previous editions of the ArgMining workshop series have promoted shared tasks, including key point analysis for quantitative summarization of arguments (see Argmining 2021), the validity and novelty of arguments (see Argmining 2022), multimodal argument mining and pragmatic tagging of peer reviews (see Argmining 2023), and argument mining considering perspective and dialogical aspects (see Argmining 2024). Following the success of previous workshops, ArgMining 2025 plans to share one or more unsolved problems to be investigated by the community. Proposals for shared tasks should include: • a title and a brief description of the task • a description of the datasets that will be used in the task and their readiness, and a proposed plan for data collection and annotation • previous work on the datasets, including publications (if any) • a few lines regarding evaluation of the submitted systems • a brief introduction of the task organizers Shared task organizers will have the opportunity to publish a task overview paper in the workshop proceedings. Please submit your shared task proposal via email to argmining.org2025 [at] gmail.com. The submission deadline is January 7th, 2025, and task organizers will be notified of proposal acceptance on January 19th. While exact dates are not yet available, we assume the following tentative schedule: • End of February - Training data release • Mid of April - Test data release, evaluation start • End of April - Evaluation end • Mid of May - Results announcement • End of May - Paper submission due • Mid of June - Camera-ready version due • July 31st or August 1st 2025 - ArgMining 2025 workshop (ACL) The timeline will be finalized with the shared task organizers. Organizers: Elena Chistova, Philipp Cimiano, Gabriella Lapesa, Shoreh Haddadan, Ramon Ruiz-Doiz

1 0

KONVENS 2025: Call for Tutorials and Workshop Proposals
by Christian Wartena 11 Dec '24

11 Dec '24

We cordially invite proposals for workshops and tutorials as part of KONVENS 2025 in Hildesheim, Germany (September 9-12). KONVENS is an annual conference series on computational linguistics that started in 1992 and that is organized under the auspices of the German Society for Computational Linguistics and Language Technology, the Special Interest Group on Computational Linguistics of the German Linguistic Society, the Austrian Society for Artificial Intelligence and SwissText. Past conferences are listed here: https://konvens.org. See https://konvens-2025.hs-hannover.de/ for more information! Workshop Proposals Workshop proposals should contain: * a title and a brief description (at most 4 pages in ACL format) of the workshop topic * the desired workshop length (half-day or full-day) * the names and email addresses of the organizers, with one-paragraph statements of their research interests and areas of expertise * a list of potential members of the program committee, with an indication of which members have already agreed to serve Workshop proposals should be submitted by email to info.konvens2025(a)gscl.org<mailto:info.konvens2025@gscl.org> no later than February 14, 2025. Notifications will be sent out by February 21, 2025. Organizers of accepted proposals will be responsible for publicizing and running the workshop, including reviewing submissions and producing the camera-ready workshop proceedings. The time schedule for workshops is: Workshop Proposal Deadline February 14, 2025 Workshop Proposal Notification February 21, 2025 Suggested Workshop Paper Deadline July 2, 2025 Suggested Workshop Paper Notification August 4, 2025 Mandatory Camera Ready Deadline August 15, 2025 Proceedings Camera Ready Deadline August 22, 2025 Tutorials Tutorials are intended to either provide a comprehensive introduction to core techniques/areas of interest or address advanced topics relevant for the KONVENS community. We invite half-day tutorials on established or emerging research topics in these areas but we also welcome tutorials from related research fields or applications. Tutorials may be explicitly introductory, targeting experienced researchers or attracting a wide audience by addressing basic as well as advanced topics. Tutorial proposals should contain: * a title and abstract of the tutorial * the language in which the tutorial will be held (English/German) * a brief description of the tutorial content and its relevance to the KONVENS community * a brief outline of the tutorial structure showing that the tutorial's core content can be covered in half a day * the names and email addresses of the tutorial instructors, including one-paragraph statements of their research interests and areas of expertise * a list of previous venues and approximate audience sizes, if the same or a similar tutorial has been given elsewhere Tutorial proposals should be submitted by email to info.konvens2025(a)gscl.org<mailto:info.konvens2025@gscl.org> no later than February 14, 2025. Notifications will be sent out by February 21, 2025. Proceedings Peer-reviewed workshop papers can be published in the KONVENS 2025 Proceedings. A camera-ready version of all accepted papers should be available at latest on August 22, 2025. Prof. Dr. Christian Wartena Hochschule Hannover Fakultät III - Medien, Information und Design Abt. Information und Kommunikation Lehrgebiet Sprach- und Wissensverarbeitung Expo Plaza 12 30539 Hannover e-mail: christian.wartena(a)hs-hannover.de<mailto:christian.wartena@hs-hannover.de> [DATA-H-Logo_RGB_Unterzeile_klein]

1 0

2nd CFP: Second Workshop on Patient-Oriented Language Processing (CL4Health) @ NAACL 2025
by Paul Thompson 11 Dec '24

11 Dec '24

Second Workshop on Patient-Oriented Language Processing (CL4Health) @ NAACL 2025 https://bionlp.nlm.nih.gov/cl4health2025/ Albuquerque, New Mexico, USA SCOPE CL4Health fills the gap among the different biomedical language processing workshops by providing a general venue for a broad spectrum of patient-oriented language processing research. The second workshop on patient-oriented language processing follows the successful inaugural CL4Health workshop (co-located with LREC-COLING 2024), which clearly demonstrated the need for a computational linguistics venue that focuses on language related to health of the public. CL4Health is concerned with the resources, computational approaches, and behavioral and socio-economic aspects of the public interactions with digital resources in search of health-related information that satisfies their information needs and guides their actions. The workshop invites papers concerning all areas of language processing focused on patients' health and health-related issues concerning the public. The issues include, but are not limited to accessibility and trustworthiness of health information provided to the public; explainable and evidence-supported answers to consumer-health questions; accurate summarization of patients' health records at their health-literacy level; understanding patients' non-informational needs through their language, and accurate and accessible interpretations of biomedical research. The topics of interest for the workshop include but are not limited to the following: * Health-related information needs and online behaviors of the public; * Quality assurance and ethics considerations in language technologies and approaches applied to text and other modalities for public consumption; * Summarization of data from electronic health records for patients; * Detection of misinformation in consumer health-related resources and mitigation of potential harms; * Consumer health question answering (Community Question Answering)(CQA); * Biomedical text simplification/adaptation; * Dialogue systems to support patients' interactions with clinicians, healthcare systems, and online resources; * Linguistic resources, data and tools for language technologies focusing on consumer health; * Infrastructures and pre-trained language models for consumer health; SHARED TASK Perspective-aware Healthcare Answer Summarization (PerAnsSumm) will be co-located with the workshop. In community / consumer health question answering, several aspects, such as question understanding and answer generation, have been studied for over a decade. A new and important question posed by this task is the different perspectives provided in the answers to questions posted to online forums. The responses to the questions offer different answer perspectives, e.g., personal experiences, factual information, and suggestions. Traditionally, the CQA answer summarization task has focused on a single best-voted answer as a reference summary. A single answer does not capture all the perspectives. Moreover, a structured presentation of the information in the form of perspective-specific summaries may be more useful for the end-users. To address these gaps, this challenge introduces a novel perspective-specific answer summarization task within a CQA setup. The task will use the Perspective-aware healthcare Answer SuMmarizAtion (PUMA) dataset, a corpus of medical question-answer pairs created by the task organizers. The PUMA dataset consists of 3,167 CQA threads with approximately 10K answers filtered from the Yahoo! L6 corpus. Each answer in PUMA is annotated with five perspective spans: ‘cause’, ‘suggestion’, ‘experience’, ‘question’, and ‘information’. Further details are about the shared task are available at: https://peranssumm.github.io/ IMPORTANT DATES (Tentative) January 30, 2025 -Workshop Paper Due Date️ March 1, 2025 - Notification of acceptance March 10, 2025 - Camera-ready papers due April 8, 2025 - Pre-recorded video due (hard deadline) May 3 OR 4, 2025 - Workshop SUBMISSIONS Two types of submissions are invited: - Full papers: should not exceed eight (8) pages of text, plus unlimited references. These are intended to be reports of original research. - Short papers: may consist of up to four (4) pages of content, plus unlimited references. Appropriate short paper topics include preliminary results, application notes, descriptions of work in progress, etc. Electronic Submission: Submissions must be electronic and in PDF format, using the Softconf START conference management system. Submissions need to be anonymous. Submission site: https://softconf.com/naacl2025/cl4health2025 Dual submission policy: papers may NOT be submitted to the workshop if they are or will be concurrently submitted to another meeting or publication. MEETING The workshop will be hybrid. Virtual attendees must be registered for the workshop to access the online environment. Accepted papers will be presented as posters or oral presentations based on the reviewers’ recommendations. ORGANIZERS - Dina Demner-Fushman, US National Library of Medicine - Sophia Ananiadou, National Centre for Text Mining and University of Manchester, UK - Paul Thompson, National Centre for Text Mining and University of Manchester, UK - Deepak Gupta, US National Library of Medicine -- Paul Thompson Research Fellow Department of Computer Science National Centre for Text Mining Manchester Institute of Biotechnology University of Manchester 131 Princess Street Manchester M1 7DN UK http://personalpages.manchester.ac.uk/staff/Paul.Thompson/

1 0

PhD and PostDoc positions in human-centered NLP at University of Göttingen
by Beinborn, Lisa 09 Dec '24

09 Dec '24

Dear fellow NLPers, we are looking for a PhD candidate and a PostDoc to join our group at the University of Göttingen. We take a human-centered perspective on natural language processing research and focus on the following topics: - the cognitive plausibility, interpretability and generalization capabilities of language processing models - cross-lingual transfer and typological diversity in multilingual models - exploring how language processing differences between humans and computers can guide the development of more efficient models - language technology for education (e.g., readability and simplification, exercise generation, learner modeling) PhD Candidate (E13): https://www.uni-goettingen.de/en/644546.html?&details=74728 PostDoc (E14, up to 5 years): https://www.uni-goettingen.de/en/644546.html?&details=74732 If the timing of the position is not right for you but everything else is, please reach out! We will have more positions coming up in the next few months. If you like our topics but already have a job, consider coming to the third edition of our HumanCLAIM workshop<https://clap-lab.github.io/workshop> (March 26th/27th, Göttingen). We bring together language researchers from computer science, linguistics, and cognitive science to exchange our ideas about “The Human Perspective on Cross-Lingual AI Models”. Best regards, Lisa Beinborn ------------------------------------------------- Prof. Dr. Lisa Beinborn Human-Centered Data Science https://www.uni-goettingen.de/huds Institute for Computer Science University of Göttingen -------------------------------------------------

1 0

SwissText 2025: 2ND CALL FOR SHARED TASK, WORKSHOP AND TUTORIAL PROPOSALS
by Tuggener Don (tuge) 08 Dec '24

08 Dec '24

Dear colleagues, We cordially invite submissions of proposals for shared tasks, workshops, and tutorials to be held at the SwissText 2025 conference (https://www.swisstext.org/). SwissText will take place on 14th and 15th of May, 2025 at ZHAW in Winterthur. ABOUT SwissText SwissText is an annual conference that brings together text analytics experts from industry and academia. It is organized by the Swiss Association for Natural Language Processing (SwissNLP) in collaboration with the Zurich University of Applied Sciences (ZHAW). SPECIAL EDITION This edition of SwissText will be special, since we celebrate its 10th anniversary! This is a great opportunity to look back. Hence, in addition to novel ideas for shared tasks, we also invite previous organizers of shared tasks to re-submit their ideas: What has changed since the last run of the shared task? Is the task still relevant? Do LLMs solve everything now? This offers us to see what progress has been made over the years. To give you some ideas, here is a list of previous shared tasks: * NLP for Sustainable Development Goals Monitoring * Swissdox Hackathon * Detecting greenwashing signals through a comparison of ESG reports and public media * Swiss German Speech to Standard German Text Shared Task * Low-Resource Speech-to-Text * The Sentence End and Punctuation Prediction in NLG text (SEPP-NLG) * German Text Summarization Challenge * .. and many more (see the SwissText website archive)! FORMAT FOR PROPOSALS Proposals for shared tasks should contain: * a title and a brief description of the topic of the task * a description of the data sets that will be used in the shared task and their readiness * a sketch of how the submitted systems will be evaluated * a tentative timeline Proposals for workshops should contain: * a title and a brief description of the topic * a description of the intended audience * workshop format (paper presentations, poster session, etc.) * a tentative timeline Proposals for tutorials should contain: * a title and a brief description of the topic and the goal of the tutorial * an introduction of the workshop speakers and their background and expertise * a description of the intended audience and the required level of expertise (beginners, experts, etc.) * a tentative outline of the tutorial schedule Note that the organization and running of the shared tasks, workshops, and tutorial is in the hands of the respective organizers. The SwissText organizers will provide infrastructure (rooms, paper submission platform) and assist where they can, of course. Interested? We are looking forward to your proposals. Submit your proposals by email to info(a)swisstext.org<mailto:info@swisstext.org> no later than December 15, 2024. Notifications will be sent out in the beginning of 2025. ________________________________ ZHAW School of Engineering / CAI Dr. Don Tuggener Technikumstrasse 71 Postfach 8401 Winterthur Tel: +41 58 934 78 55 Web: https://www.zhaw.ch/de/ueber-uns/person/tuge/

1 0

LLMs4Subjects Shared Task 5 at SemEval 2025 -- Last and final call for participation
by D'Souza, Jennifer 08 Dec '24

08 Dec '24

Libraries are at the heart of our society and education, so we believe in driving technological innovation in these age-old institutions as well as modern digital libraries when we can! If you're passionate about bringing AI and LLMs into library workflows, join computer science researchers and AI enthusiasts worldwide in the LLMs4Subjects shared task! **We are excited to announce the 3rd Call for Participation to the LLMs4Subjects Shared Task organized as part of SemEval 2025.** Calling all researchers interested to explore research objectives or new research questions around which to test LLMs. Questions such as: To what extent do LLMs pass semantic subject comprehension tests given a technical context? How effectively do they function in bilingual contexts, specifically German and English? What strategies can enhance their capability as bilingual semantic comprehension models? If these questions spark your interest, we invite you to participate in the LLMs4Subjects shared task at SemEval 2025. **TL;DR Overview – LLMs4Subjects SemEval 2025 Shared Task:** LLMs4Subjects marks the first shared task of its kind, challenging participants to develop innovative LLM-based solutions for subject tagging of technical records from Leibniz University’s Technical Library (TIBKAT). The task requires systems to process documents in both German and English using the GND taxonomy. Successful implementations may be integrated into TIB’s operational workflows, enhancing the Leibniz Information Centre for Science and Technology. For more details, visit our website: https://sites.google.com/view/llms4subjects/ Why Participate? • Explore critical LLM research areas like prompting, fine-tuning, RAG techniques, agentic workflows, and more! 🔍 • The SemEval meeting is held is conjunction with premier NLP conferences like ACL, EMNLP, or COLING. Hence participants will have the opportunity to publish a paper, present and discuss your work at one of these venues! 🗣️ • Your solutions could be integrated into the workflows of the TIB Leibniz Information Centre! 🏛️ How to Participate: 1. please submit your interest to participate using our online form (https://forms.gle/YQzupcoySAyJi45c6), 2. sign up to the shared task Google Groups (https://groups.google.com/u/6/g/llms4subjects) for FAQs, news, and announcements, and, 3. last but not the least, download the datasets (https://github.com/jd-coderepos/llms4subjects/) to begin development. Participants have a month remaining to develop solutions, and we welcome hackathon-style proofs-of-concept to showcase promising directions. The official evaluation phase begins in January 2025. Don’t wait – get started today! And please, share this with your network if you think it might interest others.

1 0