March 2025 - Corpora

Call for Participation: Shared Task on Scientific Fact-Checking of Social Media Claims on Climate Change (ClimateCheck)
by Georg Rehm 05 Mar '25

05 Mar '25

ClimateCheck: Shared Task on Scientific Fact-Checking of Social Media Claims on Climate Change Hosted as part of the SDP 2025 Workshop July 31 or August 1st, 2025 (tbc) Vienna, Austria (co-located with ACL 2025) ClimateCheck Shared Task: https://sdproc.org/2025/climatecheck.html SDP 2025 Workshop: https://sdproc.org/2025/index.html Task Overview Social media facilitates discussions on critical issues such as climate change, but it also contributes to the rapid dissemination of misinformation, which complicates efforts to maintain an informed public and create evidence-based policies. In this shared task, we emphasise the need to link public discourse to peer-reviewed scholarly articles by gathering claims from social media about climate change (both real-life and automatically generated ones) as well as a corpus of about 400K abstracts of publications from the climate sciences domains. The participants will be asked to retrieve relevant abstracts for each claim (subtask I) and classify the relation between the claim and abstract as ‘supports’, ‘refutes’, or ‘not enough information’ (subtask II). The task will be hosted on Codabench (link will be provided soon on the webpage). Participants are allowed to take part either in subtask I only, or in both subtasks. Subtask I: Abstracts Retrieval Task: given a claim from social media about climate change and a corpus of abstracts, retrieve the top K most relevant abstracts. Evaluation: MAP and B-Pref accounting for retrieving relevant abstracts and not penalising unjudged documents. Subtask II: Claim Verification Task: given the claim-abstract pairs received from the previous subtask, classify their relation as ‘support’, ‘refutes’, or ‘not enough information’. Evaluation: F1 score based on judged documents from gold data; unjudged documents will not be included in computing the score. Important dates Release of training data: April 1, 2025 Release of testing data: April 15, 2025 Deadline for system submissions: May 16, 2025 Paper submission deadline: May 23, 2025 Notification of acceptance: June 13, 2025 Camera-ready paper due: June 20, 2025 Workshop: July 31, 2025 or August 1, 2025 (TBA) We encourage and invite participation from junior researchers and students from diverse backgrounds. Participants are also encouraged to submit a paper describing their systems to the SDP 2025 workshop. Organisers Raia Abu Ahmad (DFKI, Berlin, Germany) Aida Usmanova (Leuphana University, Lüneburg, Germany) Georg Rehm (DFKI, Berlin, Germany)

1 0

Annual Workshop in Experimental Methods in Language (acquisition) Research (EMLaR) XXI
by laiacolina＠gmail.com 05 Mar '25

05 Mar '25

*** REGISTER NOW: Hybrid conference on Experimental Methods in Language (acquisition) Research (EMLaR), April 15-17, 2025 - Utrecht University (The Netherlands) *** The Institute for Language Sciences (ILS) of Utrecht University is pleased to announce the 21st edition of EMLaR. This three-day conference will take place from April 15th – 17th 2025 (Tuesday to Thursday) in hybrid format. The physical location is Utrecht University, in the city center of Utrecht, The Netherlands. EMLaR aims at training PhD students and advanced MA students in experimental methods of language (acquisition) research. Experts in various domains of linguistic research will give lectures and hands-on tutorials, and speakers will give method-oriented talks during plenary sessions. We also provide the opportunity to present your (ongoing) research at the poster session. **Program** Keynote speaker: • Sonja Kotz (Maastricht University) Invited speakers: • Bram van Dijk (Leiden University Medical Center, Leiden Institute of Advanced Computer Science) • Michael Franke (University of Tübingen) • Mieke Slim (Max Planck Institute for Psycholinguistics) • Roberta D’Alessandro (Utrecht University) • Rowena Garcia (Leibniz-Centre General Linguistics, University of the Philippines) Tutorials: • Automatic Speech Recognition • Bayesian Hypothesis Evaluation Using JASP and R • Coloring Book – a tool for testing language comprehension with young children • Computational Methods • Event-related Brain Potentials (Introduction) • Event-related Brain Potentials (Advanced*) • Ethics and Privacy • Eye-tracking • Online experiments for language scientists • Open (your) Science Using the Statistical Package JASP • PRAAT • Probabilistic Pragmatics • Research with infants: Tips and tricks • Statistics with R (Introduction) • Statistics with R (Advanced*) • Visual World Paradigm For registration and more details, please visit our website: https://emlar.wp.hum.uu.nl/. If you have any questions, please send an email to EMLAR2025(a)uu.nl. We hope to see you there! Kind regards, EMLaR 2025 organization

1 0

Call for Participation: Shared Task on Field of Research Classification of Scholarly Publications (FoRC 2025)
by Georg Rehm 05 Mar '25

05 Mar '25

FoRC 2025: Shared Task on Field of Research Classification of Scholarly Publications Hosted as part of the NSLP 2025 Workshop 1 or 2 June 2024 (tbc) Portoroz, Slovenia (co-located with ESWC 2025) FoRC Shared Task: https://nfdi4ds.github.io/nslp2025/docs/forc_shared_task.html NSLP 2025 Workshop: https://nfdi4ds.github.io/nslp2025/ A core application of Natural Scientific Language Processing (NSLP) is classifying scientific articles for their respective field of research (FoR). The 2025 iteration of the FoRC shared task builds on the data developed for Subtask II of FoRC in 2024 <https://nfdi4ds.github.io/nslp2024/docs/forc_shared_task.html>, adding to it a weakly supervised dataset of over 40K ACL publications. Participants are asked to design classification systems based on FoRC4CL, a corpus of 1500 English scholarly articles in Computational Linguistics (CL), collected from the ACL Anthology (CC BY 4.0) and manually annotated according to a novel hierarchical taxonomy, Taxonomy4CL, which consists of 170 core CL (sub-)topics. In addition, over 40K weakly supervised publications are provided to supplement the corpus and potentially increase model capabilities. Metadata fields include ACL Anthology ID, title, abstract, author(s), URL to the full text, publisher, publication year and month, proceedings title, DOI, venue, and the full text of the respective article. Task Overview Given an article from the ACL Anthology and a taxonomy of NLP/CL sub-topics (Taxonomy4CL), predict the entities from the taxonomy that correspond to the main contributions of the article. As a highly unbalanced, multi-label, hierarchical classification problem, this task will be evaluated by computing micro, macro and weighted precison, recall, and F1-score. Codabench page for participation: https://www.codabench.org/competitions/5779 Important dates Training and testing data release: February 18, 2025 System submissions deadline: March 25, 2025 Paper submissions: March 27, 2025 Notification of acceptance: April 10, 2025 Camera-ready submission: April 17, 2025 We encourage and invite participation from junior researchers and students from diverse backgrounds. Participants are also encouraged to submit a paper describing their systems to the NSLP 2025 workshop. Organisers Maria Francis (DFKI, Berlin, Germany & University of Trento, Italy) Raia Abu Ahmad (DFKI, Berlin, Germany) Ekaterina Borisova (DFKI, Berlin, Germany) Georg Rehm (DFKI, Berlin, Germany)

1 0

SemEval-2026: Call for Task Proposals
by Semeval Organizers 05 Mar '25

05 Mar '25

SemEval-2026: Call for Task Proposals URL: https://semeval.github.io/SemEval2026/cft # Call for Task Proposals We invite proposals for tasks to be run as part of SemEval-2026. SemEval (the International Workshop on Semantic Evaluation) is an ongoing series of evaluations of computational semantics systems, organized under the umbrella of SIGLEX, the Special Interest Group on the Lexicon of the Association for Computational Linguistics. SemEval tasks explore the nature of meaning in natural languages: how to characterize meaning and how to compute it. This is achieved in practical terms, using shared datasets and standardized evaluation metrics to quantify the strengths and weaknesses and possible solutions. SemEval tasks encompass a broad range of semantic topics from the lexical level to the discourse level, including word sense identification, semantic parsing, coreference resolution, and sentiment analysis, among others. For SemEval-2026, we welcome tasks that can test an automatic system for semantic analysis of text (e.g., intrinsic semantic evaluation, or an application-oriented evaluation). We especially encourage tasks for languages other than English, cross-lingual tasks, and tasks that develop novel applications of computational semantics. See the websites of previous editions of SemEval to get an idea about the range of tasks explored, e.g. SemEval-2020 (http://alt.qcri.org/semeval2020/) and SemEval-2021/2025 ( https://semeval.github.io). We strongly encourage proposals based on pilot studies that have already generated initial data, evaluation measures and baselines. In this way, we can avoid unforeseen challenges down the road that may delay the task. We suggest providing a reasonable baseline (e.g., providing a BERT baseline for a classification task) apart from majority vote / random guess. In case you are not sure whether a task is suitable for SemEval, please feel free to get in touch with the SemEval organizers at semevalorganizers(a)gmail.com to discuss your idea. ## Task Selection Task proposals will be reviewed by experts, and reviews will serve as the basis for acceptance decisions. Everything else being equal, more innovative new tasks will be given preference over task reruns. Task proposals will be evaluated on: - Novelty: Is the task on a compelling new problem that has not been explored much in the community? Is the task a rerun, but covering substantially new ground (new subtasks, new types of data, new languages, etc. - one addition is not sufficient)? - Interest: Is the proposed task likely to attract a sufficient number of participants? - Data: Are the plans for collecting data convincing? Will the resulting data be of high quality? Will annotations have meaningfully high inter-annotator agreements? Have all appropriate licenses for use and re-use of the data after the evaluation been secured? Have all international privacy concerns been addressed? Will the data annotation be ready on time? - Evaluation: Is the methodology for evaluation sound? Is the necessary infrastructure available or can it be built in time for the shared task? Will research inspired by this task be able to evaluate in the same manner and on the same data after the initial task? Is the task significantly challenging (e.g. room for improvement over the baselines)? - Impact: What is the expected impact of the data in this task on future research beyond the SemEval Workshop? - Ethical – The data must be compliant with privacy policies. e.g. a) avoid personally identifiable information (PII). Tasks aimed at identifying specific people will not be accepted, b) avoid medical decision making (compliance with HIPAA, do not try to replace medical professionals, especially if it has anything to do with mental health) c) these are representative and not exhaustive ## Submission Details The task proposal should be a self-contained document of no longer than 3 pages (plus additional pages for references). Please see website for further information. ## Important dates - Task proposals due 31 March 2025 (Anywhere on Earth) - Task selection notification 19 May 2025 ## Preliminary timetable - Sample data ready 15 July 2025 - Training data ready 1 September 2025 - Evaluation data ready 1 December 2025 (internal deadline; not for public release) - Evaluation start 10 January 2026 - Evaluation end by 31 January 2026 (latest date; task organizers may choose an earlier date) - Paper submission due February 2026 - Notification to authors March 2026 - Camera ready due April 2026 - SemEval workshop Summer 2026 (co-located with a major NLP conference) Tasks that fail to keep up with crucial deadlines (such as the dates for having the task and CodaLab website up and dates for uploading sample, training, and evaluation data) may be cancelled at the discretion of SemEval organizers. While consideration will be given to extenuating circumstances, our goal is to provide sufficient time for the participants to develop strong and well-thought-out systems. Cancelled tasks will be encouraged to submit proposals for the subsequent year’s SemEval. To reduce the risk of tasks failing to meet the deadlines, we are unlikely to accept multiple tasks with overlap in the task organizers. ## Chairs - Sara Rosenthal, IBM Research AI - Aiala Rosá, Universidad de la República, Uruguay - Marcos Zampieri, George Mason University, USA - Debanjan Ghosh, Educational Testing Service,

1 0

IndiREAD Workshop – 1st Call for Papers
by Iza Skrjanec 05 Mar '25

05 Mar '25

IndiREAD Workshop 2025: 1st Call for Papers Saarbrücken, Germany, November 26-27, 2025 IndiREAD is a workshop jointly organized by the ERC Project "Individualized Interaction in Discourse" IDDISC [1] and the MultiplEYE COST [2] action "Enabling multilingual eye-tracking data collection for human and machine language processing research". While experimental research in reading has a long tradition in identifying key factors that influence reading patterns--including text properties such as font difficulty, word and structure frequency, word predictability, and dependency length--recent studies have emphasized the importance of individual variability in reading behaviour (e.g., Haeuser & Kray, 2024; Kuperman et al., 2018; Nicenboim et al., 2016; Staub, 2021). This work has linked individual variability in reading patterns to differences in working memory capacity, reading skills, linguistic experience, and domain expertise among readers. This informs our understanding of how text characteristics and individual reader attributes interact to shape eye movements during reading. IndiREAD aims to bring together researchers interested in investigating individual differences in reading using both experimental and computational approaches. This workshop will focus on methods such as eye-tracking, self-paced reading, and the Maze task, with particular interest in how reading behaviour is correlated with individual differences. We also encourage submissions of computational models for eye movements or reading behavior that shed light on the mechanisms behind these differences. The goal is to foster collaboration between experimental and computational researchers to better understand individual variability among readers. We especially welcome submissions of reading time experiments and modelling of languages beyond English. The IndiREAD Workshop invites submissions of abstracts addressing the following questions:  * How do individual differences impact the way people read? * How do reading patterns vary across different languages, particularly in bilinguals? * How do reading patterns change across the lifespan? * Which individual difference measures are most suitable for capturing variability in reading patterns? * How can we evaluate psycholinguistic theories of reading and sentence processing across languages? * How can computational models account for individual differences in reading? * How does text adaptation influence reading patterns and comprehension among different individuals? * What statistical methods are best suited for reliably identifying latent groups and relating individual differences to reading performance? Workshop dates: November 26-27, 2025 Workshop format: The workshop will be held in-person in Saarbrücken, Germany. It will feature presentations from invited speakers, as well as contributions based on workshop submissions. The format of the presentations (oral or poster) will be determined based on the number of submissions we receive. Submission deadline: July 23, 2025. We invite 1000-word abstracts from interested presenters. Information about submission and formatting will be available on our website soon. Conference website: https://www.uni-saarland.de/indiread [3] Contact email: indiread(a)lst.uni-saarland.de Travel grants: This workshop is sponsored by the MultiplEYE COST Action, which will provide financial support to cover travel expenses for a limited number of participants. Authors will be invited to apply for travel funding upon abstract acceptance. Funding may be partial, and priority will be given to junior researchers. Best, Iza Škrjanec IndiREAD Organizing Committee Links: ------ [1] https://www.uni-saarland.de/lehrstuhl/demberg/individualized-interaction-in… [2] https://multipleye.eu/ [3] https://www.uni-saarland.de/indiread

1 0

CFP: The 26th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2025)
by vladana.perlic＠telecom-paris.fr 05 Mar '25

05 Mar '25

CALL FOR PAPERS The 26th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2025) Conference: 15th - 21st December 2025 Modena, Italy Conference website: https://conferences-website.github.io/prima2025 ------------------------------------------------------------------------------------------------------------------- IMPORTANT DATES Abstract Submission Deadline: 15 July (AoE, UTC-12) Paper Submission Deadline: 22 July (AoE, UTC-12) Paper Notification: 29 September 2025 (AoE, UTC-12) Camera Ready Submission: 13 October 2025 (AoE, UTC-12) ------------------------------------------------------------------------------------------------------------------- We invite you to submit your best work on agents and multi-agent systems to PRIMA 2025, the 26th International Conference on Principles and Practice of Multi-Agent Systems, to be held in Modena (Italy) in December 2025. Papers will be submitted through CMT at the link: https://cmt3.research.microsoft.com/PRIMA2025/Submission/Index ------------------------------------------------------------------------------------------------------------------- Scope and Background Software systems are rapidly becoming more intelligent in the functionality they offer to users. They are also becoming more decentralized, with components that act autonomously and must communicate among themselves or with human users to achieve their goals. Examples of such systems include those in healthcare, disaster management, e-business, and smart grids. A multi-agent perspective is crucial to the proper conceptualization, deployment, and governance of these systems. Rooted in solid computational and software engineering foundations, this perspective offers abstractions such as intelligent agents, protocols, norms, organizations, trust and incentives, among others. As a large, but still growing research field of artificial intelligence, multi-agent systems today remain a unique enabler of interdisciplinary research. ------------------------------------------------------------------------------------------------------------------- Areas of Interest The conference areas of interest include, but are not limited to: ● Logic and Reasoning ○ Logics of Agency ○ Logics of Multi-Agent Systems ○ Logics of Belief and Knowledge ○ Norms, Obligations, Deontic Logic ○ Argumentation ○ Logics and Game Theory ○ Uncertainty in Agent Systems ● Agent and Multi-Agent Learning ○ Reinforcement Learning ○ Evolutionary approaches ○ Machine Learning Problems in Multi-Agent Systems ○ Agents Embodied with Large Language Models ● Engineering Multi-Agent Systems ○ Agent-Oriented Software Engineering ○ Interaction Protocols ○ Formal Specification and Verification ○ Agent Programming Languages ○ Middleware and Platforms ○ Testing, Debugging, and Evolution ○ Deployed System Case Studies ● Agent-Based Modeling and Simulation ○ Simulation Languages and Platforms ○ Artificial Societies ○ Virtual Environments ○ Emergent Behavior ○ Modeling System Dynamics ○ Application Case Studies ● Collaboration & Coordination ○ Multi-Agent Planning ○ Distributed Problem Solving and Optimization ○ Teamwork ○ Coalition Formation ○ Negotiation ○ Trust and Reputation ○ Commitments ○ Institutions and Organizations ○ Normative Systems ● Algorithmic Game Theory ○ Auctions and Mechanism Design ○ Bargaining and Negotiation ○ Behavioral Game Theory ○ Cooperative Games: Theory, Analysis, Computation ○ Game Theory for Practical Applications ○ Noncooperative Games: Theory, Analysis, Computation ● Computational Social Choice ○ Voting ○ Fair Division and Resource Allocation ○ Matching under Preferences ○ Coalition Formation Games ○ Aggregation of Beliefs, Opinions, Judgments ○ Ethics and Computational Social Choice ○ Participatory Budgeting ○ Facility Location ○ Communication Issues in Social Choice, Distortion ○ Behavioral Social Choice ● Human-Agent Interaction ○ Adaptive Personal Assistants ○ Embodied Conversational Agents ○ Virtual Characters ○ Multimodal User Interfaces ○ Mobile Agents ○ Human-Robot Interaction ○ Affective Computing ● Decentralized Paradigms ○ Cloud Computing ○ Service-Oriented Computing ○ Data spaces ○ Big data ○ Cybersecurity ○ Robotics and Multirobot Systems ○ Ubiquitous Computing ○ Social Computing ○ Internet of Things ○ Edge Computing ○ Blockchain ● Ethics and Social Issues ○ Explainable Artificial Intelligence ○ Ethics of AI Systems ○ Multi-Agent Systems for Social Good ● Application Domains for Multi-Agent Systems ○ Healthcare, Pandemics Management ○ Autonomous Systems ○ Transport and Logistics ○ Emergency and Disaster Management ○ Energy and Utilities Management ○ Sustainability and Resource Management ○ Games and Entertainment ○ e-Business, e-Government, and e-Learning ○ Smart Cities ○ Financial markets ○ Legal applications ○ Crowdsourcing ------------------------------------------------------------------------------------------------------------------- Information for Authors PRIMA 2025 invites submissions of original, unpublished work strongly relevant to multi-agent systems. Apart from theoretical work, we encourage the submission of reports on the development of applications or prototypes of deployed agent systems, and of experiments that demonstrate novel agent system capabilities. In addition to this, we also encourage the submission of position papers that are of relevance to the multi-agent community. All submitted papers must be in a form suitable for double-blind review. Specifically, in order to make blind reviewing possible, authors must omit their names and affiliations from the paper. Also, while the references should include all published literature relevant to the paper, including previous work of the authors, it should not include unpublished works. When referring to one's own work, use the third person rather than the first person. For example, say "Previously, Foo and Bar [2] have shown that…", rather than "In our previous work [2], we have shown that…". Such identifying information can be added back to the final camera-ready version of accepted papers. All papers will be reviewed by at least 2-3 experts in the area following a detailed review form that will assess the paper based on the significance and novelty of the idea, the technical description of the proposal, clarity and organization, the evaluation methodology, and any ethical considerations. All accepted papers will be published in Springer's Lecture Notes in Artificial Intelligence series (LNCS/LNAI). All papers must be submitted using the Springer LNCS/LNAI format. Type of submissions: ● Full papers, 16 pages plus references ● Short papers, 4 pages plus references ● Position papers, 2 pages plus references

1 0

Data in Historical Linguistics seminar: Tracing the characteristics of early medieval notarial scripta with the help of a Latin database.
by Mathilde Bru 04 Mar '25

04 Mar '25

The fifth talk of the Data in Historical Linguistics Seminar Series 2025 will take place remotely on Monday 17th March 2025 at 5pm GMT. Cecilia Valentini (Ca’ Foscari University of Venice, Italy) will present on ‘Tracing the characteristics of early medieval notarial scripta with the help of a Latin database.’ Registration for this talk will close at midnight on Friday 14th March and the link for this can be accessed here: https://docs.google.com/forms/d/e/1FAIpQLSc3GDH4hYkvduAzrKmMsCbDtSDmyTEKp9l… Participants will receive a Microsoft Teams link via email on the morning of the talk. The abstract for this talk can be found here: https://datainhistoricallinguistics.wordpress.com/2024/12/31/valentini/ The programme and registration links for all talks in the series can be found on our website: https://datainhistoricallinguistics.wordpress.com/2025-programme/ This seminar series is run by Andrea Farina and Mathilde Bru (King’s College London) and is aimed at PhD students and early career researchers. The purpose of this seminar series is to bring together researchers working on historical linguistics with a quantitative approach, and to discuss current avenues of research in this topic. We hope that these seminars will nurture international collaboration and establish academic ties among researchers working on similar topics in this field. Join our mailing list<https://datainhistoricallinguistics.wordpress.com/join-us/>!

1 0

2 Open Research Positions, Bielefeld University, Semantic Computing Group, Application Deadline: 20th of March
by cimiano＠cit-ec.uni-bielefeld.de 04 Mar '25

04 Mar '25

The Semantic Computing Group at Bielefeld University performs research at the intersection of natural language processing and knowledge representation. We have two openings for research positions in the LLM4KMU project. The project is carried out in cooperation with several companies in the area of Bielefeld (Semalytix, CLAAS, PrimeLine, MatPlus etc.) and has the goal of understanding how LLM-based models can be adapted effectively to real use cases. The research involves investigating the adaptation, transfer, etc. of models across tasks. It also involves researching how models can be made more robust and how hallucinations can be reduced. The two available positions will have a different focus: Position Wiss25002: The position holder will work in particular in the area of text generation and develop and evaluate new methods for smaller companies. Conceivable examples include methods for interacting with unstructured data or methods for improving and maintaining corporate language. In addition, the position holder will be responsible for leading and implementing the development of a benchmarking platform for LLMs. on non-academic tasks. See [1] for details. Position Wiss25008: The position holder will conduct research in the field of information extraction and develop methods for extracting information from published clinical studies. On this basis, a portal for searching and summarizing the results of clinical studies will be developed. See [2] for details. Position requirements: - master’s degree in computational linguistics, computer science, data science or a related field, - demonstrated ability to work scientifically (e.g. through Master thesis or publications) - strong analytical, conceptual and communicative skills - ability to work in a larger team The following aspects are a plus but not necessary: - experience in natural language processing or natural language generation learning, LLMs, - experience in software development in a non-academic environment - experience in the development of web applications (only for Position Wiss25008). The positions are available for 3 years starting from June 2025. The positions offer the opportunity to pursue a PhD. Postdoctoral candidates can apply as well. Knowledge of German is not required but is an advantage. The application deadline is the 20th of March, 2025. Please send your applications to cimiano(a)cit-ec.uni <mailto:cimiano@cit-ec.uni>-bielefeld with a CV, short motivation letter and publication record, if applicable. Please indicate in your application whether you are applying for Position Wiss25002 or Position Wiss25008, or both. [1] https://uni-bielefeld.hr4you.org/job/view/4054/research-position-text-gener… [2] https://uni-bielefeld.hr4you.org/job/view/4059/research-position-informatio… Prof. Dr. Philipp Cimiano AG Semantic Computing Coordinator of the Cognitive Interaction Technology Center (CITEC) Co-Director of the Joint Artificial Intelligence Institute (JAII) Universität Bielefeld Tel: +49 521 106 12249 Fax: +49 521 106 6560 Mail: cimiano(a)cit-ec.uni-bielefeld.de Personal Zoom Room: https://uni-bielefeld.zoom-x.de/my/pcimiano Office CITEC-2.307 Universitätsstr. 21-25 33615 Bielefeld, NRW Germany

1 0

2nd Call for Participation: SHARED TASK in analysis of Persuasion Techniques — in parliamentary debates and social media, for Slavic Languages
by Roman Yangarber 04 Mar '25

04 Mar '25

*Call for Participation* ** Shared Task: Detection and Classification of Persuasion Techniquesin Parliamentary Debates and Social Media, for Slavic Languages * Co-located with Slav-NLP 2025 <http://bsnlp.cs.helsinki.fi/>Workshop, at ACL 2025 http://bsnlp.cs.helsinki.fi/shared-task.html <http://bsnlp.cs.helsinki.fi/shared-task.html> * * TASK DESCRIPTION: * * The task focuses on detection and classification of Persuasion Techniques in 5 Slavic languages — Bulgarian, Polish, Croatian, Slovene and Russian — in two types of texts: (a) parliamentary debates on hotly-contested topics, and (b) social media posts, related to the spread of disinformation. The task has two subtasks: 1. Subtask 1: Detection — Given a text and a list of fragment offsets, determine for each fragment whether it contains one or more persuasion techniques, from a given taxonomy of persuasion techniques, 2. Subtask 2: Classification —Given a text and a list of fragment offsets, determine for each fragment which persuasion techniques are employed therein. We use a rich taxonomy with 25 persuasion techniques: Name-calling or labelling, Guilt by association, Casting doubt, Appeal to hypocrisy, Questioning the reputation, Flag waiving, Appeal to authority, Appeal to popularity, Appeal to fear and prejudice, Appeal to values, Strawman, Whataboutism, Red herring, Appeal to pity, Causal oversimplification, False dilemma or no choice, Consequential oversimplification, False equivalence, Slogans, Conversation killer, Appeal to time, Loaded language, Obfuscation-Intentional vagueness-confusion, Exaggeration or minimization, Repetition. Subtask 1 is a binary classification task, while Subtask 2 is a multi-class multi-label classification task. The text fragments correspond to paragraphs. For information about training and test data, guidelines, and participation, please see theShared Task Home Page. <http://bsnlp.cs.helsinki.fi/shared-task.html> IMPORTANT: Participants may join both subtasks or only one. It is not mandatory to submit responses for all languages. Up to 5 system responses per language per team may be submitted. Important Dates * Registration deadline: 20 April 2025 * Release of Testdata to registered participants: *22 April*2025 * Submission of system responses: 26 April 2023 * Results announced to participants: *29*April 2025 * Submission of shared task papers (optional): 11 May 2025 * ** *Questions and contact: bsnlp(a)cs.helsinki.fi<mailto:bsnlp@cs.helsinki.fi>* -- Roman Yangarber Professor, University of Helsinki, Finland Digital Humanities INEQ: Helsinki Inequality Initiative <https://helsinki.fi/en/ineq-helsinki-inequality-initiative> — Linguistic Inequalities and Translation Technologies ------------------------------------------------------------------------ e-Learning & language learning Language Learning Lab Unioninkatu 40, Metsätalo A214 revitaAI.github.io <https://revitaai.github.io> helsinki.fi/language-learning-lab <https://www.helsinki.fi/language-learning-lab> mobile: +358 50 41 51 71 3 ------------------------------------------------------------------------ RЯ <https://www.helsinki.fi/language-learning-lab>

1 0

CIRCE Online Seminar 31/03/2025 - Prof. Rob Drummond "Ten things everybody should know about (spoken) language"
by Claudia Soria 04 Mar '25

04 Mar '25

** *🎓 *We are happy to announce the next webinar in the CIRCE online seminar series organized by the CIRCE <https://www.circe-project.eu/>project in collaboration with DFCLAM University of Siena <https://www.dfclam.unisi.it/en>, H2IOSC <https://www.h2iosc.cnr.it/>project and CNR-ILC <https://www.ilc.cnr.it/en/>.** * Speaker:Rob Drummond (Manchester Metropolitan University, UK)Title:Ten things everybody should know about (spoken) languageDate: Monday, March 31, 2025 - 16:30 CET Venue: OnlineAttendees: Secondary school teachers, researchers, language instructors Summary:I spend a lot of my time trying to persuade people to have a more accepting attitude towards language variation and language change. In fact, we should be doing a lot more than accepting it – we should be enjoying it and celebrating the fact that we all use language in different ways. We should take time to appreciate the fundamental connection between the way we speak, and who we are. In this talk, I will present my top ten reflections and insights that aim to improve everyone’s relationship with their own, and other people’s, use of English. Bio:Rob Drummond is Professor of Sociolinguistics at Manchester Metropolitan University, where he researches, teaches and writes about the relationship between spoken language and identity. He recently led the community-focused Manchester Voices project, exploring the accents, dialects and identities of people in Greater Manchester, and he co-leads The Accentism Project, which strives to challenge and raise awareness of language-based prejudice. Rob does a lot of public-facing academic work and is the author of You’re All Talk: Why we are what we speak (Scribe Publications, 2023), a book for a general audience that sheds light on the fascinating relationship between ourselves and our language. Upcoming webinars:· Sender Dovchin (Monday, April 14, 2025)· Alice Henderson (Monday, April 28, 2025)· Ana Tankosic (Thursday, June 5, 2025)The seminar is free of charge, but participants must register.To access this and next events, you should create an account on theH2IOSC Training Environment <https://h2iosc-training-platform.ilc4clarin.ilc.cnr.it/registration>. Once logged in with your credentials, choose the course “Language and Accent Discrimination - Online Seminar Series” and activate it with the code PbK837GtE. Make sure to have the Teams platform installed. The registrations of the previous CIRCE Seminars are also available on the H2IOSC Training Environment. For any inquiry, write to contact(a)circe-project.eu <mailto:contact@circe-project.eu>. * -- facebook <https://www.facebook.com/CNRsocialFB> twitter <https://twitter.com/CNRsocial_> instagram <https://www.instagram.com/cnrsocial/> linkedin <https://www.linkedin.com/company/283032> Claudia Soria CNR, ISTITUTO DI LINGUISTICA COMPUTAZIONALE "ANTONIO ZAMPOLLI" claudia.soria(a)ilc.cnr.it Tel. 0503153166 Via Giuseppe Moruzzi, 1, 56124 – Pisa www.ilc.cnr.it *www.cnr.it* <http://www.cnr.it/> Devolvi il 5×1000 al CNR CF 80054330586

1 0

2025

2024

2023

2022

Corpora March 2025