March 2025 - Corpora

SEPLN 24rd EDITION OF THE BEST DOCTORAL AWARD
by jipatsaa＠si.ehu.es 20 Mar '25

20 Mar '25

EDICIÓN XXIV PREMIO SEPLN A LA MEJOR TESIS DOCTORAL EN PROCESAMIENTO DEL LENGUAJE NATURAL [Plazo de presentación: 4 de mayo de 2025] La Sociedad Española para el Procesamiento del Lenguaje Natural convoca la Edición XXIV del Premio SEPLN a la Mejor Tesis Doctoral en Procesamiento del Lenguaje Natural, que se regirá por las siguientes bases: La finalidad de este premio es la promoción y divulgación de la investigación en el campo del procesamiento del lenguaje natural. La tesis será premiada con una computadora portátil compacta (tablet) y 300€ para la asistencia al congreso. Se dará entrega del premio en el 41 Congreso Internacional de la Sociedad Española del Procesamiento del Lenguaje Natural (< span style="font-size:12pt;font-family:Arial,sans-serif;color:#1155cc;background-color:transparent;font-weight:700;font-style:normal;font-variant:normal;text-decoration:underline;-webkit-text-decoration-skip:none;text-decoration-skip-ink:none;vertical-align:baseline;white-space:pre;white-space:pre-wrap;">SEPLN 2025), tras una breve presentación del trabajo premiado por parte del autor. Para poder concursar, el autor de la tesis doctoral debe ser socio de la SEPLN en el momento de presentar el trabajo. Ninguna persona concursante podrá participar como autora en más de un trabajo. Se podrán presentar a concurso tesis doctorales leídas durante el año 2024, escritas en una lengua del Estado español o en lengua inglesa. Además de la tesis completa, es imprescindible enviar: Un breve resumen de 4 páginas donde claramente se indique el tema y la relevancia de la investigación, los objetivos, métodos, resultados alcanzados y contribuciones. Una breve descripción de la trayectoria científica del autor de la tesis, en la que se describa la participación en actividades científicas como organización de de tareas competitivas, congresos, generación de recursos open access como conjuntos de datos, modelos de lenguaje, etc, y participación en proyectos, contratos, y/o patentes. La calidad de la presentación, la corrección técnica y metodológica, la relevancia, originalidad, la generación, evaluación y publicación de recursos, así como la trayectoria investigadora durante el periodo predoctoral serán los criterios empleados para la adjudicación del premio por parte del jurado. Los trabajos se enviarán a través de la web de la revista de la Sociedad (http://journal.sepln.org) en formato PDF antes del 4 de mayo de 2025. La resolución del premio se comunicará durante el 41 Congreso Internacional de la Sociedad Española del Procesamiento del Lenguaje Natural (SEPLN 2025). Documento con las instrucciones (aquí) Para más información dirigirse a aitziber.atucha(a)ehu.eus 24rd EDITION OF THE SEPLN AWARD TO THE BEST DOCTORAL THESIS IN NATURAL LANGUAGE PROCESSING [Submission deadline: May 4th, 2025] The Spanish Society for Natural Language Processing announces the 24rd Edition of the SEPLN Award for the Best Doctoral Thesis in Natural Language Processing, which will be governed by the following bases: The purpose of this award is the promotion and dissemination of research in the field of natural language processing. The thesis will be awarded with a compact laptop (tablet) and 300€ grant to help cover the cost of attending the conference. The award will be presented at the 41th International Congress of the Spanish Society for Natural Language Processing (SEPLN 2025), after a brief presentation of the award-winning work by the author. In order to compete, the author of the doctoral thesis must be a member of the SEPLN at the time of submitting the work. No contestant may participate as an author in more than one work. Doctoral theses read during the year 2024, written in a language of the Spanish State or in English, may be submitted to competition. In addition to the complete thesis, it is essential to send: a 4-page summary of the thesis, clearly describing the topic and the relevance of the research, the objectives, methods, results achieved and contributions. a brief description of the scientific career of the author of the thesis, detailing the participation in scientific activities such as organization of competitive tasks, congresses, generation of open access resources such as sets of data, language models, etc., and participation in projects, contracts, and/or patents. The quality of the presentation, the technical and methodological correctness, the relevance, originality, the generation, evaluation and publication of resources, as well as the research trajectory during the pre-doctoral period will be the criteria used for the award of the prize by the jury. The works will be submitted through the website of the Society's magazine (http://journal.sepln.org) in PDF format before May 4th 2025. The final decision will be communicated during the 41th International Congress of the Spanish Society for Natural Language Processing (SEPLN 2025). Submission instructions (here)

1 0

2nd CfP R2CASS2025 at ICWSM 2025
by taimoor.nlp＠gmail.com 19 Mar '25

19 Mar '25

Dear colleagues, We invite research contributions to our workshop, focusing on reproducible and reusable computational models for social data analysis. The event will also feature an interactive replicability session to enhance hands-on learning and collaboration. Please feel free to share with those interested in your network. Keynote: Professor Carole Goble, University of Manchester (leading eScience Research Lab) Call for papers: R2CASS2025 – International workshop “Social Science Meets Web Data: Reproducible and Reusable Computational Approaches” at ICWSM 2025 Paper submission deadline: March 31st, 2025 Website: https://r2cass2025.wordpress.com/ Submission: https://easychair.org/my/conference?conf=r2ca The first international workshop “Social Science Meets web Data: Reproducible and Reusable Computational Approaches” (R2CASS2025) will be held in conjunction with “International AAAI Conference on Web and Social Media” (ICWSM 2025) in Copenhagen, Denmark on June 23rd, 2025. The workshop will be held in-person and at least one author of the accepted papers will be required to register and present it in the workshop. The papers presented will be published in the workshop proceedings of the conference. Artificial Intelligence (AI) based models have a growing influence in social science research for analyzing behavioral patterns on social media and other digital platforms. Computational reproducibility has been a concern with these models as they deal with living data that is likely to change, contain personal information and therefore, ethical restrictions on their use. The workshop aims to bring together researchers and practitioners to discuss and exchange ideas towards potential interdisciplinary collaborations from computer science, social science, meta-science and other related disciplines. It provides a platform to present and critically analyze computational reproducibility guidelines and checklists for social sciences. The participants will focus on the open challenges and propose methodologies in computational reproducibility for social science towards improving research transparency, reproducibility, and reusability. Workshop participants are also encouraged to volunteer for and participate in the interactive replicability session attempting to replicate existing methods on sample data. (for participation in the interactive replicability session, please contact the workshop organizers at https://r2cass2025.wordpress.com/contact-2/) The workshop calls for theoretical and practical research contributions that employ qualitative, quantitative and analytical approaches including full papers, short papers, resource papers, position papers and posters on the topics (but not limited to): • Data and software management in machine learning and natural language processing-driven studies • Computational methods on sentiment analysis, bias analysis, toxicity, and sexism detection • Text categorization and topic analysis • Digital behavior analysis on social media and other digital platforms • Computational reproducibility checklists and workflows in social science • FAIR principles in ML research for social science • Open Science applications and reproducibility challenges • Metadata standards for ML/NLP research • Tools for replicating complex social science models using web-based data • Integration of open-source ML/NLP tools for web data analysis Submission guidelines As per AAAI-ICWSM guidelines, all papers must be submitted as high-resolution PDF files formatted in AAAI two-column, camera-ready style, for US Letter (8.5” x 11”) paper. Full papers are recommended to be 8 pages long and must be at most 11 pages long, including only the main text and the references. The mandatory Ethics Checklist (and brief additional Ethics Statement, if desired, see below), optional appendices, etc. do not count toward the page limit and should be placed after the references. Appendices, if they exist, should be placed after the Ethics Checklist. Revision papers and final camera-ready full papers can be up to 12 pages. Dataset papers must be no longer than 10 pages, Poster papers must be no longer than 4 pages, and Demo descriptions must be no longer than 2 pages. No source files (Word or LaTeX) are required at the time of submission for review; only the PDF file is permitted. Finally, the copyright slug may be omitted in the initial submission phase, and no copyright form is required until a paper is accepted for publication. For more on paper formatting guidelines, please visit ICWSM guidelines. Co-organizers Fakhri Momeni, GESIS – Leibniz Institute for the Social Sciences, Germany M. Taimoor Khan, GESIS – Leibniz Institute for the Social Sciences, Germany Arnim Bleier, GESIS – Leibniz Institute for the Social Sciences, Germany Tony Ross-Hellauer, Know-Center, Austria Regards Taimoor

1 0

Third call for participation - MentalRiskES@IberLEF2025: Early detection of mental risk
by María Dolores Molina González 19 Mar '25

19 Mar '25

*Release of training corpora and registration still open* *!!* ****We apologize for multiple postings of this e-mail**** MentalRiskES2025 describes the third edition of a novel task on early risk identification of mental disorders in Spanish comments from social media sources. The first and the second editions took place in the IberLEF evaluation forum as part of the SEPLN 2023 and SEPLN 2024. The task was resolved as an online problem, that is, the participants had to detect a potential risk as early as possible in a continuous stream of data. Therefore, the performance not only depended on the accuracy of the systems but also on how fast the problem is detected. These dynamics are reflected in the design of the tasks and the metrics used to evaluate participants. For this third edition, we propose two novel tasks, the first subtask is about the detection of the gambling disorder and the second subtask consists of detecting a type of Addiction. We would like to invite you to participate in the following tasks: 1. Risk Detection of Gambling Disorders (Binary classification) 2. Type of Addiction Detection (Multiclass classification) Find out more at https://sites.google.com/view/mentalriskes2025. MentalRiskES 2025 is part of the IberLEF Workshop and will be held in conjunction with the SEPLN 2025 conference in Zaragoza (Spain). ------------------------------------------------------------------------------- Important Dates ------------------------------------------------------------------------------- Feb 14th Registration open Feb 25th Release of trial corpora (trial server available) *Mar 19th Release of training corpora* Mar 31st Registration closed Apr 7th Release of test corpora and start of the evaluation campaign (test server available and trial submissions closed) Apr 14th End of evaluation campaign (deadline for submission of runs) Apr 18th Publication of official results and release of test gold labels May 12th Deadline for paper submission May 30th Acceptance notification Jun 16th Camera-ready submission deadline Sep TBD Publication of proceedings Note: All deadlines are 11:59PM UTC-12:00 Please reach out to the organizers at MentalRiskEs@IberLEF2025. The MentalRiskES 2025 organizing committee. ----------------------------------------------------------- Mas informacion sobre listas de correo en la Univ. de Jaen http://www.ujaen.es/sci/redes/listas/ -----------------------------------------------------------

1 0

1st Call for Papers: SLM4Health workshop @ AIME 2025
by Douglas Teodoro 19 Mar '25

19 Mar '25

SLM4Health: Improving Healthcare with Small Language Models (Workshop held in conjunction with AIME 2025 conference, June 26, 2025, 9am-5 pm, in Pavia (Italy) https://slm4health2025.netlify.app/ SLM4Health focuses on exploring the role and potential of Small Language Models (SLMs) in healthcare-related natural language processing (NLP) tasks. As SLMs gain traction in clinical settings due to their adaptability, efficiency, and lower resource demands, they offer a promising alternative to larger models, especially in resource-constrained environments. However, challenges such as performance trade-offs and ethical concerns—bias, privacy, and interpretability—need to be addressed. The workshop will bring together researchers and practitioners to discuss SLM applications in clinical tasks, compare them with large language models, and explore methods to overcome these challenges, ultimately aiming to improve patient care and clinician support through more tailored NLP tools. We invite researchers to present their latest research results on the following topics: Applications of SLMs for information extraction, sentiment analysis, named entity recognition, relation extraction from medical documents; Adaptation of SLMs to effectively handle diverse languages, especially those with limited resources; Sustainability of SLMs compared to LLMs; Ethical aspects, including safety, privacy concerns and bias mitigation, explainability; Possibilities and challenges of SLMs in tasks of medical language processing; Comparisons of SMLs and LLMs on specific use cases in healthcare; Evaluation metrics, datasets, and benchmarks. To enable reproducibility and some level of comparison among approaches, we encourage researchers to use the MIMIC-III or MIMIC-IV dataset. Submission deadline: April 15, 2025 __________________________________ Prof. Douglas Teodoro, PhD Department of Radiology and Medical Informatics Faculty of Medicine | University of Geneva Campus Biotech G6-N3 | Chemin des Mines 9, 1202 Genève tel: 022 379 02 25 | douglas.teodoro(a)unige.ch <mailto:douglas.teodoro@unige.ch> www.unige.ch/medecine <http://www.unige.ch/medecine>

1 0

Invitation to #SMM4H-HeaRD Shared Task 1: Detection of adverse drug events in multilingual and multi-platform social media posts
by Pierre Zweigenbaum 19 Mar '25

19 Mar '25

We are happy to announce the next round of [#SMM4H-HeaRD](https://healthlanguageprocessing.org/smm4h-2025/), which will be co-located with [AAAI ICWSM](https://www.icwsm.org/2025/index.html) 2025, the International AAAI Conference on Web and Social Media in June 23-26, 2025, Copenhagen, Denmark. Our team is organizing **Shared Task 1: Detection of adverse drug events in multilingual and multi-platform social media posts**. We provide data in German, French, Russian, and English, from platforms such as X and patient forums. We invite you to participate and attempt to beat our multilingual baseline! As the deadline is approaching, please [register](https://docs.google.com/forms/d/e/1FAIpQLScOdaY58DZQ_2aw_rISJut3G… as soon as possible. Here is the schedule: - Training and validation data available: February 14, 2025 - System predictions for validation data due: March 31, 2025 (23:59 CodaLab server time); this is a simple test to check that teams have a syntactically valid system - Test data available: April 7, 2025 - System predictions for test data due: April 11, 2025 (23:59 CodaLab server time) - Submission deadline for system description papers: May 2, 2025 - Notification of acceptance: May 23, 2025 - Camera-ready papers due: June 6, 2025 - Workshop: June 23, 2025 Please share this call with interested colleagues. Organizers of Task 1: Lisa Raithel, Philippe Thomas, Roland Roller, Elena Tutubalina, Takeshi Onishi, Dongfang Xu, Pierre Zweigenbaum BIFOLD, TU Berlin (XplaiNLP), DFKI SLT, AIRI, Cedars-Sinai Medical Center, LISN, CNRS, Université Paris Saclay

1 0

2nd CFP: The 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
by Ekaterina Kochmar 19 Mar '25

19 Mar '25

Second Call for Papers: *The 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)* *Location*: Vienna, Austria and online (co-located with ACL 2025) *Date*: Thursday, July 31 and Friday, August 1, 2025 *Website*: https://sig-edu.org/bea/2025 <https://sig-edu.org/bea/2025> *Submission Deadline*: Thursday, April 17, 2025, 11:59pm UTC-12 *Submission Link*: https://softconf.com/acl2025/bea2025/ WORKSHOP DESCRIPTION The BEA Workshop is a leading venue for NLP innovation in the context of educational applications. It is one of the largest one-day workshops in the ACL community with over 100 registered attendees in the past several years. The growing interest in educational applications and a diverse community of researchers involved resulted in the creation of the Special Interest Group in Educational Applications (SIGEDU) (https://sig-edu.org<https://sig-edu.org/>) in 2017, which currently has over 400 members. The 20th BEA workshop will be the first edition of BEA as *a 2-day workshop*, and it will feature a keynote by *Kostiantyn Omelianchuk (Grammarly)*, oral presentation sessions and large poster sessions to facilitate the presentation of a wide array of original research. This year, the workshop is also hosting *a shared task on Pedagogical Ability Assessment of AI-powered Tutors*, and *a half-day tutorial on LLMs for Education: Understanding the Needs of Stakeholders, Current Capabilities and the Path Forward *(more details on both to follow). We expect that the workshop will continue to highlight novel technologies and opportunities for educational NLP in English as well as other languages. The workshop will accept submissions of both full papers and short papers, eligible for either oral or poster presentation at https://softconf.com/acl2025/bea2025/. We solicit papers that incorporate NLP methods, including, but not limited to: - use of generative AI in education and its impact; - automated scoring of open-ended textual and spoken responses; - automated scoring/evaluation for written student responses (across multiple genres); - game-based instruction and assessment; - educational data mining; - intelligent tutoring; - collaborative learning environments; - peer review; - grammatical error detection and correction; - learner cognition; - spoken dialog; - multimodal applications; - annotation standards and schemas; - tools and applications for classroom teachers, learners and/or test developers; and - use of corpora in educational tools. INVITED TALKS The workshop will feature a keynote by Kostiantyn Omelianchuk (Grammarly), and an invited talk by a speaker from one of the IAALDE (https://alliancelss.com<https://alliancelss.com/>) societies. SHARED TASK The workshop will also host a shared task on Pedagogical Ability Assessment of AI-powered Tutors. See more details here: https://sig-edu.org/sharedtask/2025 IMPORTANT DATES All deadlines are 11.59 pm UTC-12 (anywhere on earth). - Submission deadline: *Thursday, April 17, 2025* - Notification of acceptance: *Thursday, May 22, 2025* - Camera-ready papers due: *Monday, June 9, 2025* - Workshop: *Thursday, July 31, and Friday, August 1, 2025* SUBMISSION INFORMATION We will be using the ACL Submission Guidelines for the BEA Workshop this year. Authors are invited to submit a long paper of up to eight (8) pages of content, plus unlimited references; final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers’ comments can be taken into account. We also invite short papers of up to four (4) pages of content, plus unlimited references. Upon acceptance, short papers will be given five (5) content pages in the proceedings. Authors are encouraged to use this additional page to address reviewers’ comments in their final versions. We generally follow ACL submission guidelines and will require that all submitted papers should include a dedicated "Limitations" section, which does not count toward the page limit. Papers which describe systems are also invited to give a demo of their system. If you would like to present a demo in addition to presenting the paper, please make sure to select either “long paper + demo” or “short paper + demo” under “Submission Category” in the START submission page. Previously published papers cannot be accepted. The submissions will be reviewed by the program committee. As reviewing will be blind, please ensure that papers are anonymous. Self-references that reveal the author’s identity, e.g., “We previously showed (Smith, 1991) …”, should be avoided. Instead, use citations such as “Smith previously showed (Smith, 1991) …”. We have also included conflict of interest in the submission form. You should mark all potential reviewers who have been authors on the paper, are from the same research group or institution, or who have seen versions of this paper or discussed it with you. We will be using the START conference system to manage submissions: https://softconf.com/acl2025/bea2025/ DOUBLE SUBMISSION POLICY We will follow the official ACL double-submission policy. Specifically, papers being submitted both to BEA and another conference or workshop must: - Note on the title page the other conference or workshop to which they are being submitted. - State on the title page that if the authors choose to present their paper at BEA (assuming it was accepted), then the paper will be withdrawn from other conferences and workshops. ORGANIZING COMMITTEE - Ekaterina Kochmar, MBZUAI - Andrea Horbach, Hildesheim University - Ronja Laarmann-Quante, Ruhr University Bochum - Marie Bexte, FernUniversität in Hagen - Anaïs Tack, KU Leuven, imec - Victoria Yaneva, National Board of Medical Examiners - Bashar Alhafni, New York University (NYU) & CAMeL Lab in NYUAD - Zheng Yuan, King’s College London - Jill Burstein, Duolingo Workshop contact email address: bea.nlp.workshop(a)gmail.com<mailto:bea.nlp.workshop@gmail.com> PROGRAM COMMITTEE https://sig-edu.org/bea/2025#program-committee

1 0

2nd Call for participation: Robust WSI Shared Task @ CoNLL-2025
by Ondřej Herman 19 Mar '25

19 Mar '25

Dear colleagues, We invite you to participate in the Robust Word Sense Induction shared task, which is organized as a part of CoNLL-2025 in Vienna (31.7 - 1. 8. 2025). TASK OVERVIEW The task focuses on unsupervised word sense induction without relying on predefined sense inventories. Participants will receive sentences containing target words and cluster them according to word sense usage. What makes this task unique is the novel evaluation approach using multi-annotated data and robust metrics that account for natural sense ambiguity and provide a fairer evaluation compared to traditional approaches. The benchmark datasets will be available in English, Czech, German, Spanish, Estonian and Chinese. The submissions are currently open. Please note that the deadlines have been slightly postponed. IMPORTANT DATES - Updated 25. 4. 2025 - Test phase ends 2. 5. 2025 - Submission of system description papers 31. 7. 2025 or 1. 8. 2025 - The CoNLL-2025 workshop at ACL 2025 in Vienna For more information and participation instructions, please visit https://projects.sketchengine.eu/conll2025/. This shared task is organized by Ondřej Herman, Miloš Jakubíček, Pavel Rychlý and Vojtěch Kovář at Lexical Computing and Masaryk University. If you have any questions, please contact us at conll2025(a)sketchengine.eu. Best regards, The Shared Task Organizers

1 0

BEA 2025 Shared Task: Pedagogical Ability Assessment of AI-powered Tutors
by Ekaterina Kochmar 19 Mar '25

19 Mar '25

Conversational agents offer promising opportunities for education as they can fulfill various roles (e.g., intelligent tutors and service-oriented assistants) and pursue different objectives (e.g., improving student skills and increasing instructional efficiency), among which serving as an AI tutor is one of the most prevalent tasks. Recent advances in the development of Large Language Models (LLMs) provide our field with promising ways of building AI-based conversational tutors, which can generate human-sounding dialogues on the fly. The key question posed in previous research, however, remains: *How can we test whether state-of-the-art generative models are good AI teachers, capable of replying to a student in an educational dialogue?* In this shared task, we will focus on educational dialogues between a student and a tutor in the mathematical domain grounded in student mistakes or confusion, where the AI tutor aims to remediate such mistakes or confusions, with the goal of evaluating the quality of tutor responses along the key dimensions of tutor’s ability to (1) identify student’s mistake, (2) point to its location, (3) provide the student with relevant pedagogical guidance, that is also (4) actionable. Dialogues used in this shared task include the dialogue contexts from MathDial (Macina et al., 2023) and Bridge (Wang et al., 2024) datasets, including the last utterance from the student containing a mistake, and a set of responses to the last student’s utterance from a range of LLM-based tutors and, where available, human tutors, aimed at mistake remediation and annotated for their quality. **Tracks** This shared task will include five tracks. Participating teams are welcome to take part in any number of tracks. - Track 1 - Mistake Identification: Participants are invited to develop systems to detect whether tutors' responses recognize mistakes in students' solutions. - Track 2 - Mistake Location: Participants are invited to develop systems to assess whether tutors' responses accurately point to genuine mistakes and their locations in the students' responses. - Track 3 - Pedagogical Guidance: Participants are invited to develop systems to evaluate whether tutors' responses offer correct and relevant guidance, such as an explanation, elaboration, hint, examples, and so on. - Track 4 - Actionability: Participants are invited to develop systems to assess whether tutors' feedback is actionable, i.e., it makes it clear what the student should do next. - Track 5 - Guess the tutor identity: Participants are invited to develop systems to identify which tutors the anonymized responses in the test set originated from. **Participant registration** All participants should register using the following link: https://forms.gle/fKJcdvL2kCrPcu8X6 **Important dates** All deadlines are 11:59pm UTC-12 (anywhere on Earth). - March 12, 2025: Development data release - April 9, 2025: Test data release - April 23, 2025: System submissions from teams due - April 30, 2025: Evaluation of the results by the organizers - May 21, 2025: System papers due - May 28, 2025: Paper reviews returned - June 9, 2025: Final camera-ready submissions - July 31 and August 1, 2025: BEA 2025 workshop at ACL **Shared task website**: https://sig-edu.org/sharedtask/2025 **Organizers** - Ekaterina Kochmar (MBZUAI) - Kaushal Kumar Maurya (MBZUAI) - Kseniia Petukhova (MBZUAI) - KV Aditya Srivatsa (MBZUAI) - Justin Vasselli (Nara Institute of Science and Technology) - Anaïs Tack (KU Leuven) **Contact**: bea.sharedtask.2025(a)gmail.com<mailto:bea.sharedtask.2025@gmail.com>

1 0

Third call for participation - MentalRiskES@IberLEF2025: Early detection of mental risk
by María Dolores Molina González 19 Mar '25

19 Mar '25

*Release of training corpora and registration still open* *!!* ****We apologize for multiple postings of this e-mail**** MentalRiskES2025 describes the third edition of a novel task on early risk identification of mental disorders in Spanish comments from social media sources. The first and the second editions took place in the IberLEF evaluation forum as part of the SEPLN 2023 and SEPLN 2024. The task was resolved as an online problem, that is, the participants had to detect a potential risk as early as possible in a continuous stream of data. Therefore, the performance not only depended on the accuracy of the systems but also on how fast the problem is detected. These dynamics are reflected in the design of the tasks and the metrics used to evaluate participants. For this third edition, we propose two novel tasks, the first subtask is about the detection of the gambling disorder and the second subtask consists of detecting a type of Addiction. We would like to invite you to participate in the following tasks: 1. Risk Detection of Gambling Disorders (Binary classification) 2. Type of Addiction Detection (Multiclass classification) Find out more at https://sites.google.com/view/mentalriskes2025. MentalRiskES 2025 is part of the IberLEF Workshop and will be held in conjunction with the SEPLN 2025 conference in Zaragoza (Spain). ------------------------------------------------------------------------------- Important Dates ------------------------------------------------------------------------------- Feb 14th Registration open Feb 25th Release of trial corpora (trial server available) *Mar 19th Release of training corpora* Mar 31st Registration closed Apr 7th Release of test corpora and start of the evaluation campaign (test server available and trial submissions closed) Apr 14th End of evaluation campaign (deadline for submission of runs) Apr 18th Publication of official results and release of test gold labels May 12th Deadline for paper submission May 30th Acceptance notification Jun 16th Camera-ready submission deadline Sep TBD Publication of proceedings Note: All deadlines are 11:59PM UTC-12:00 Please reach out to the organizers at MentalRiskEs@IberLEF2025. The MentalRiskES 2025 organizing committee. ----------------------------------------------------------- Mas informacion sobre listas de correo en la Univ. de Jaen http://www.ujaen.es/sci/redes/listas/ -----------------------------------------------------------

1 0

Fully funded PhD position in NLP & Interactive Information Retrieval at HHU Düsseldorf
by Stefan Dietze 19 Mar '25

19 Mar '25

* PhD position (salary group TV-L 13, working time 100 %, initially limited to 3 years) * ******************************************************************* We are seeking a highly motivated PhD candidate to join the Data & Knowledge Engineering group (https://www.cs.hhu.de/en/research-groups/data-knowledge-engineering https://www.cs.hhu.de/en/research-groups/data-knowledge-engineering) at Heinrich-Heine-University Düsseldorf in collaboration with GESIS, Cologne (http://www.gesis.org) in the context of the DFG-funded research project "EmergentIR: Improving Informational Web Search for Emerging Topics". The project investigates web search behavior and algorithms in the context of emerging topics, i.e. for novel and less-well understood search queries. An example is the search for COVID-19 related terms and topics during the early days of the pandemic, where available online resources and information were evolving quickly and reliable high quality information was sparse. * Your responsibilities * ************************ - Research in fields such as information retrieval, information extraction/NLP and/or human-computer interaction to investigate and support web search on emerging topics, e.g. to predict search intents, detect emerging topics or support ranking and retrieval of information. - Work and collaborate with an interdisciplinary team of researchers to develop and evaluate computational methods in the context of web search. - Publish and present research results at major scientific events * Your profile * **************** - Master’s degree in computer science or a related field. - Background in the following areas: information retrieval, natural language processing, or machine learning/deep learning. - Experience in programming (e.g. Python) and with machine learning frameworks such as PyTorch or TensorFlow - Fluency in English. German language skills are desirable but not required. * Contact & application process * ******************************** Please send your complete application documents (CV, certificates & transcripts) as a single PDF file to Stefan Dietze (stefan.dietze(a)hhu.de) by 15 April. For any informal enquiries about the position, please don't hesitate to get in touch via the same email address. -- Prof. Dr. Stefan Dietze Scientific Director Knowledge Technologies for the Social Sciences GESIS - Leibniz Institute for the Social Sciences Web: https://www.gesis.org/en/kts Chair of Data & Knowledge Engineering Heinrich-Heine-University Düsseldorf Web: https://www.cs.hhu.de/en/research-groups/data-knowledge-engineering Phone: +49 (0)221-47694-421 Web: http://stefandietze.net

1 0

2025

2024

2023

2022

Corpora March 2025