- Corpora - ELRA lists

EMNLP 2026 Call for Main Conference Papers
by Yuki Arase 07 Mar '26

07 Mar '26

Call for Main Conference Papers Overview EMNLP 2026 invites the submission of long and short papers featuring substantial, original, and unpublished research on empirical methods for Natural Language Processing. EMNLP 2026 has a goal of curating a diverse technical program—in addition to traditional research results, papers may contribute negative findings, survey an area, announce the creation of a new resource, argue a position, report novel linguistic insights derived using existing computational techniques, and reproduce (or fail to reproduce) previous results. As in recent years, some of the presentations at the conference will be of papers accepted by the Transactions of the ACL (TACL) and the Computational Linguistics (CL) journals. Important Dates ARR submission deadline (long & short papers) May 25, 2026 Reviewer registration deadline for ALL authors May 27, 2026 Author response and author-reviewer discussion July 7 - July 13, 2026 Meta review released July 30, 2026 EMNLP commitment deadline August 2, 2026 Notification of acceptance (long & short papers) August 20, 2026 Camera-ready papers due (long & short) September 20, 2026 Main Conference (dates for Workshops/Tutorials TBD) October 22 - 26, 2026 Note: All deadlines are 11:59PM UTC-12:00 (“anywhere on Earth”). Following the ACL and ARR policies, there is no anonymity period requirement. At the time of submission to ARR, authors will be asked to select a preferred venue (e.g., EMNLP 2026). This is used only to calculate acceptance rates. Authors who selected EMNLP 2026 as a preferred venue when submitting to ARR may choose not to commit to EMNLP 2026 after receiving their reviews, and authors who selected a preferred venue other than EMNLP 2026 when submitting to ARR are still welcome to commit to EMNLP 2026. New: Paper Integrity Policies at EMNLP There is growing concern in our community regarding unethical paper submissions that overwhelm community resources, including but not limited to, thinly sliced contributions, submissions with hallucinated citations, and entirely AI-generated papers (AI writing assistance is permitted). EMNLP will take actions against such submissions, as well as submissions that violate the ACL Policy on Publication Ethics. Such submissions may be desk rejected, and all authors involved in the submission may be ineligible to commit their paper(s) to EMNLP 2026 and EMNLP 2027. Paper Submission Information Dual submissions are not allowed! Please check the ARR Multiple Submission Policy for details. Papers must be submitted, at latest, by the ARR 2026 May cycle. Papers that have received reviews and a meta-review from ARR (whether from the ARR 2026 May cycle or an earlier ARR cycle) may be committed to EMNLP via the commitment link. Mandatory Reviewing Workload All authors are expected to sign up to review, or serve as an Area Chair or Senior Area Chair, with assignments subsequently based on qualifications. After submission, all authors must complete the author registration form by May 27, 2026 EoD AoE. If you receive assignments, your reviews must be completed by July 6, or your meta-reviews - by July 29. In case of any emergencies, the chairs should be warned via the emergency declaration form. Highly irresponsible reviewers may be ineligible to (re-)submit or commit their work during the next ARR cycle. The submitting authors should (a) make sure that all other authors are aware of this policy, and (b) check that everybody on their team(s) submits their (meta-)reviews on time and in accordance with the guidelines. You can read additional details on the definition of highly irresponsible reviewers and the corresponding ARR policy here: https://aclrollingreview.org/incentives2025 AI Reviewing Experiment (opt-in) The Program Committee plans on running an opt-in AI Reviewing Experiment to collect feedback from authors on the utility of AI Reviewers in the review process. The AI Reviews for opted-in submissions will not inform any part of the conference decision process. We will run this experiment under IRB approval, using open-weights models running on in-house compute resources, or closed models that guarantee zero-data retention. Submission Topics EMNLP 2026 aims to have a broad technical program. Relevant topics for the conference include, but are not limited to, the following areas: Clinical and Biomedical Applications NLP and Code Models Computational Social Science and Cultural Analytics Dialogue and Interactive Systems Discourse and Pragmatics Efficient Methods for NLP Ethics, Bias, and Fairness NLP and Symbolic Reasoning Generation Human-Centered NLP and Human-AI Interaction Information Extraction Information Retrieval and Text Mining Interpretability and Analysis of Models for NLP Language Modeling LLM Agents LLM Security Linguistic Theories, Cognitive Modeling, and Psycholinguistics Machine Learning for NLP Machine Translation Multilingualism and Cross-Lingual NLP Multimodality and Language Grounding to Vision, Robotics and Beyond NLP Applications Phonology, Morphology, and Word Segmentation Question Answering Resources and Evaluation Semantics: Lexical and Sentence-Level Sentiment Analysis, Stylistic Analysis, and Argument Mining Speech Recognition, Text-to-Speech and Spoken Language Understanding Summarization Syntax: Tagging, Chunking and Parsing Special Theme: New Missions for NLP Research EMNLP 2026 Theme Track: New Missions for NLP Research Large language models have rapidly shifted from research prototypes to widely used infrastructure. This new reality is changing the center of gravity of NLP research, and progress can no longer be measured only by fractional improvements in benchmark scores. When strong general-purpose models are increasingly available through open releases and commercial platforms, the field faces a more foundational question: What are the missions of NLP research now, and what kinds of contributions most advance that mission? The EMNLP 2026 special theme invites papers that articulate, test, and advance visions for NLP in this era. We welcome work that reflects on the mission(s) of NLP research, reframes our collective research goals, proposes new evaluation and scientific methodologies, and builds bridges across multiple disciplines that can sharpen both our theories and our impact. Submissions may be empirical, theoretical, or position and survey papers, but should be grounded in clear claims, strong evidence, and actionable insights. Relevant topics include, but are not limited to: • Rethinking progress and evaluation in NLP For example, going beyond static leaderboards, including real-world impact, trustworthiness, robustness, and longitudinal behavior; what “generalization” should mean for humans vs models, and when models are reused, adapted, and deployed in diverse settings, etc. • From models to systems and ecosystems For example, how does system-level research on agentic workflows, tool use, and multi-model orchestration interface with human experiences; and at an ecosystem level, how do people, organizations, and communities use and interact with language technology. • Scientific understanding of language and cognition For example, using contemporary models as experimental instruments for psycholinguistics, cognitive science, language acquisition, and field linguistics; and what models reveal, and fail to reveal, about human cognition, the nature of language, learning, and meaning. • Data as a bottleneck and a responsibility For example, research on data scarcity and limits, contamination, and the consequences of synthetic data feedback loops, and new approaches to data creation, documentation, governance, and consent. • LLMs as research tools: AI in research For example, rigorous studies of how LLMs can support the research process in hypothesis generation, experiment design, analysis, and peer review support tools without eroding scientific standards. This special theme is intended to complement the breadth of EMNLP, not narrow it. We encourage submissions that are ambitious in scope while remaining concrete in claims and methodology, and that help the community clarify what research looks like in the next chapter of NLP. Two Stage Review: Submission to ARR, Commitment to EMNLP EMNLP 2026 will use ACL Rolling Review (ARR) as a reviewing system, but final decisions will be made by the conference. Both submissions of articles for review and commitment of reviewed articles to the conference will be performed via the Open Review platform. Specifically, authors will follow a two-step process: Authors submit articles to ARR, where submissions receive reviews and meta-reviews from ARR reviewers and action editors; Authors commit their reviewed articles to a publication venue (e.g., EMNLP 2026), where Senior Area Chairs and Program Chairs make acceptance decisions from the ARR reviews and meta-reviews. Authorship during commitment. During the commitment phase, it is not allowed to modify the author list (i.e., addition/deletion of authors is not allowed). However, modification of author order is possible. EMNLP 2026 has chosen this approach in coordination with *CL 2026 conferences, which are adopting the same procedure and a coordinated submission plan to allow maximum flexibility during their submission periods for the authors. At each cycle, after a paper has been fully reviewed, authors have the option to commit their paper to a conference, or revise and resubmit for another round of reviews. The reviewing process will continue to be double-blind. Reviewers will not see authors, nor will authors see reviewers and reviews on ARR will not be made publicly visible. However, authors will be given the option through ARR to make their anonymized submitted articles publicly visible. Paper Submission Details Both long and short paper submissions should follow all of the ARR submission requirements, including: Long Papers (8 pages) and Short Papers (4 pages) Instructions for Two-Way Anonymized Review Authorship Citation and Comparison Multiple Submission Policy, Resubmission Policy, and Withdrawal Policy ACL’s Publication Ethics Policy, and ARR’s Ethics Policy including the responsible NLP research checklist ACL’s Disclosure Policy Limitations Writing Assistance Paper Submission and Templates Optional Supplementary Materials Final versions of accepted papers will be given one additional page of content (up to 9 pages for long papers, up to 5 pages for short papers) to address reviewers’ comments. Presentation at the Conference All accepted papers must be presented at the conference to appear in the proceedings. The conference will include both in-person and virtual presentation options. Papers without at least one presenting author registered by the early registration deadline may be subject to rejection. Long and short papers will be presented orally or as posters as determined by the program committee. While short papers will be distinguished from long papers in the proceedings, there will be no distinction in the proceedings between papers presented orally and papers presented as posters. Contact Information General Chair: André Martins, Instituto Superior Técnico, Universidade de Lisboa Program Chairs: Sunipa Dev, Google Desmond Elliott, University of Copenhagen Hung-yi Lee, National Taiwan University Jessy Li, The University of Texas at Austin For questions related to paper submission, and the review process in general, email: editors(a)aclrollingreview.org For questions about commitment and post review related topics, email: emnlp2026-programchairs(a)googlegroups.com

1 0

Call for Papers - 1st International Workshop on Science-Related Discourse on the Web (SDW'26)
by Philipp Leon Alfred Meier 06 Mar '26

06 Mar '26

** Call for Papers ** 1st International Workshop on Science-Related Discourse on the Web (SDW'26) We are excited to announce the 1st International Workshop on Science-Related Discourse on the Web (SDWâ€™26), collocated with ACM Web Science Conference 2026, 26-29 May, Braunschweig, Germany In recent years, a growing number of people have been engaging in science-related discussions on online platforms. This typically informal and sometimes decontextualized discourse may result in oversimplification, misinterpretation or instrumentalization of scientific knowledge. Analyzing such discourse is challenging: it differs from general online talk, spans multiple platforms, and requires interdisciplinary methods. This workshop provides a venue for interdisciplinary exchange on computational and social scientific approaches and resources to platform specific and cross platform analysis of science-related communication. ***Workshop Themes*** - Methodological challenges related to the analysis of science-related discourse on the Web, including data acquisition and processing - Insights concerning science-related discourse on the Web, e.g., its characteristics, evolution, and impact Topics of interest within these themes include, but are not limited to the following: - (Cross-platform-) crawling approaches for science-related discourse - Methods for the detection and filtering of science-related online discourse data - Issues and methods related to tracking/linking of users and messages within and across different platforms (e.g., X, Bluesky, Mastodon, Threads) - Practical/legal/ethical issues concerning data access - Detection of arguments, claims, evidence, sources, or stances in science-related online discourse data - Classification of scientific claims w.r.t. verifiability, credibility, or veracity (including distinguishing different types of misinformation such as oversimplification) - Analysis of science-related discourse on social media platforms and in online news - Assessment of the expertness of social media users (e.g., scientist, expert, lay person) - Classification of sources w.r.t. credibility, political leaning, and other biases - Usage of social media platforms (e.g., X, Bluesky, Mastodon, Threads) by different user groups - Usage of memes in science-related discourse on social media - Analysis of LLM-generated text in science-related discourse - Usage of preprints and open access publications in science-related Web discourse ***Submissions*** We invite contributions from Computer Science, Computational Social Science, Communication Science, Science Communication, Media and Communication Studies, Information Science, Computational Linguistics and related fields. We accept both technical and non technical submissions, including research papers (completed or in progress and unpublished work), annotated datasets, questionnaires, novel data collections, tools, and other resources. Emphasis is placed on discussion and exchange of ideas, thus we welcome submissions of work in progress. - full papers (6 - 10 pages, including references, appendices, etc.), - short papers (up to 5 pages including references, appendices, etc.), - extended abstracts for posters and demos (up to 2 pages including references, appendices, etc.). All accepted contributions except extended abstracts will be part of the WebSci'26 workshop proceedings, which will be published in a companion volume in the ACM Digital Library. Submission of all papers is electronic, using the EasyChair conference management system: https://easychair.org/conferences/?conf=sdw26 Please find more information on the workshop website: https://sdw2026.wordpress.com/dates-and-submission/ ***Important Dates*** Papers due: March 24, 2026 Paper notifications: April 3, 2026 Paper camera-ready versions due: April 14, 2026 Workshop: May 26, 2026

1 0

International Conference on Software and Systems Reuse, Product Lines, and Configuration (VARIABILITY 2026): Third Call for Research Papers
by Announce 06 Mar '26

06 Mar '26

*** Third Call for Research Papers *** International Conference on Software and Systems Reuse, Product Lines, and Configuration (VARIABILITY 2026) 29 September - 2 October 2026, 5* St. Raphael Resort and Marina Limassol, Cyprus https://conf.researchr.org/home/variability-2026 The International Conference on Software and Systems Reuse, Product Lines, and Configuration (VARIABILITY 2026) invites high-quality contributions from researchers and practitioners in software engineering, systems engineering, and related disciplines focussing on a broad spectrum of methods, concepts, and tools for variability. VARIABILITY aims to be the premier forum for the exchange of ideas, experiences, and results in all aspects of software and systems variability management, reuse, software configuration, and customization. As software and systems become increasingly configurable, reusable, and adaptable, managing their variability across all lifecycle phases is more critical—and more challenging —than ever. VARIABILITY 2026 seeks to bring together the diverse communities that address these challenges from theoretical, technical, and practical perspectives. VARIABILITY results from a merge of three prominent conferences focussing on software and systems variability, configuration and reuse: SPLC (the International Systems and Software Product Line Conference, 29 successful editions), VaMoS (the International Working Conference on Variability Modelling of Software-Intensive Systems, 19 successful editions), and ICSR (the International Conference on Systems and Software Reuse, 22 successful editions). VARIABILITY is by design open as a conference. It welcomes new fields of variability- intensive research, such as artificial intelligence, hybrid software-hardware systems, etc. For this first edition of VARIABILITY, we strive to continue the success of the predecessor conferences ICSR, SPLC, and VaMoS by welcoming high-quality submissions for the research track in numerous closely related areas, such as systems and software product lines, systems and software reuse, configurable systems and software, product configuration, and systems and software variability. We will award the best research paper and the best artifact paper. Topics of Interest We invite contributions on variability management, reuse, and configuration across all phases of the software and systems lifecycle. The topics of interest include, but are not limited to: Requirements & Domain Engineering • Domain analysis and variability modeling • Decision modeling and support • Customization and personalization specification • Requirements variability and traceability Architecture & Design • Variability-aware software architectures • Architecture-centric product line engineering • Model-driven engineering (MDE) • Multi-product lines, program families, product lines of product lines, software ecosystems Implementation & Code Generation • Generative programming and code synthesis • Modularization techniques for reusable code • Programming languages and frameworks for variability • Open-source strategies for software reuse Testing, Verification & Quality Assurance • Testing and analysis of configurable systems • Safety and security in variable systems • Formal Methods for Software Product Lines • Non-functional properties: quality-aware analysis, quality-driven configuration • Reuse in testing, verification, and quality assurance Evolution, Maintenance & Operation • Refactoring and restructuring of configurable systems • Reverse engineering, variability mining, and refactoring • Runtime variability and dynamic (software) product lines • Maintenance strategies for large-scale reused systems • Variability in DevOps and CI/CD pipelines AI and Data-Driven Methods • Machine learning for variability management • AI-assisted product configuration • Data and repository mining from product lines and configuration histories • Recommendation systems for reuse and customization Publication of Proceedings Accepted papers will be published in the VARIABILITY 2026 proceedings by Springer in the LNCS series. Submission Guidelines Paper Types We invite the following types of submissions: • Full Papers (up to 18 pages excluding references): Research papers must present original, unpublished work with validated results through empirical evaluation, formal analysis, or implementation-based experiments. Submissions must clearly articulate the problem, its relevance, the proposed contribution, and validation results. • Short Papers (6 - 8 pages excluding references): Short papers present early-stage research, novel ideas, or conceptual proposals that are not yet fully developed or validated but offer promising directions. These papers should articulate the vision, motivation, and potential impact. Formatting Papers must use the Springer LNCS template according to: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-gu… Springer provides author guidelines that should be consulted for further details: https://resource-preview-cms.springernature.com/springer-cms/rest/v1/conten… Submission Link Submissions should be made via Easy Chair, selecting the research track: https://easychair.org/conferences?conf=variability2026 Paper Originality, Double-Anonymous Policy, Reviewing All papers must be original and not under review elsewhere. Submissions will be double- anonymous and reviewed by at least three experts. Submissions will be evaluated based on their novelty, relevance, rigor, transparency, and presentation. Authors of submissions to the first deadline might be invited to submit a revision of their papers to the second deadline, which will be reviewed as a revision. Revisions Research-track papers can be submitted to the first or second cycle. In the first cycle, papers can receive the following decisions: accept, revision, or reject. Revision means that the reviewers believe that the paper has potential, but that its quality or contribution is not yet ready for publication. Such papers are offered lightweight shepherding by a community member, who is not necessarily a PC member or reviewer. Revised papers should be submitted to the second cycle together with a response letter, explaining how the reviewer comments were addressed. They are then reviewed by the same PC members. Papers rejected in the first cycle can be resubmitted in the second cycle, but need to contain an appendix “Changes to First-Cycle Submission” at the end of the PDF (after references, regardless of the page limit) that lists the major changes in bullet-point format. Best Paper Awards Springer will sponsor the awards for bet papers with an overall amount of €1000. Journal Special Issue Selected accepted papers will be invited to submit extended versions with at least 30% additional and original material, to be published in a special issue in a reputable Software Engineering journal (currently under negotiation). Important Dates (AoE) • Paper Submission Deadline: 2 April 2026 • Notification of Acceptance: 1 June 2026 • Camera-Ready Deadline: 15 July 2025 • Author Registration: 15 July 2025 Organisation General Chairs • George A. Papadopoulos, University of Cyprus, Cyprus • Gilles Perrouin, FNRS & University of Namur, Belgium Research Track Chairs • Thorsten Berger, Ruhr University Bochum, Germany • Ina Schaefer, KIT, Germany Industry Track Chairs • Shaukat Ali, Simula Research Lab and Oslo Metropolitan University, Norway • Martin Becker, Fraunhofer IESE, Germany Journal First Track Chairs • Mathieu Acher, University Rennes, Inria, CNRS, IRISA, France • Xhevahire Tërnava, LTCI, Télécom Paris, Institut Polytechnique de Paris, France Doctoral Symposium Track Chairs • Rick Rabiser, LIT CPS, Johannes Kepler University Linz, Austria • Iris Reinhartz-Berger, University of Haifa, Israel Demos and Tools Track Chairs • Sandra Greiner, University of Southern Denmark, Denmark • Leopoldo Teixeira, Federal University of Pernambuco Projects Showcase Chairs • Daniel Struber, Chalmers, University of Gothenburg, Radbound University, Sweden • Dalila Tamzalit, Nantes Université, France Hall of Fame Chairs • Martin Becker, Fraunhofer IESE, Germany • Goetz Botterweck, Lero - The Irish Software Research Centre and University of Limerick, Ireland • Natsuko Noda, Shibaura Institute of Technology, Japan Workshops Chairs • Lidia Fuentes, Universidad de Malaga, Spain • Malte Lochau, University of Siegen, Germany Tutorials Chairs • Loek Cleophas, Eindhoven University of Technology and Stellenbosch University, The Netherlands • Mahsa Varshosaz, IT University of Copenhagen, Denmark Proceedings Chair • Sophie Fortz, King's College London, UK Publicity Chairs • Wesley Assunção, North Carolina State University, USA • Kentaro Yoshimura, Hitachi Ltd, Japan Local Organiser and Finance Chair • George A. Papadopoulos, University of Cyprus, Cyprus

1 0

LREC 2026: Early-Bird Deadline Extension to March 15, 2026 (23:59 AoE)
by Helene Mazo 05 Mar '26

05 Mar '26

[Apologies for multiple postings] The Early-Bird Deadline has been extended to March 15, 2026 (23:59 AoE) All participants are encouraged to take advantage of the extended deadline and register. Main Conference authors must submit their camera-ready paper(s) and complete their registration for LREC 2026 by this date. We also encourage on-site participants to book their accommodation in Palma as soon as possible. Two partner hotel options are currently available for LREC participants. 1. Meliá Hotels: https://events.melia.com/en/events/palma-port/LREC-2026 2. Aubamar Palma Resort: https://www.aubamar.com/en/?promocode=LREC2026 <https://www.aubamar.com/en/?promocode=LREC2026&utm_source=lrec2026&utm_medi…> Please consider using these options when arranging your stay. LREC 2026 Management Chairs --- Fees: https://lrec2026.info/registration-fees/ Registration Policy: https://lrec2026.info/registration-policy/ *LREC 2026 Contacts* * Invitation and visa letters: german.rigau(a)ehu.es * ELRA membership, payment, invoices: elrasecretariat(a)lrec2026.info * Scientific programme and Main conference papers: lrec2026-pcs(a)googlegroups.com * Workshops: lrec2026-workshop-chairs(a)googlegroups.com * Tutorials: lrec2026-tutorial-chairs(a)googlegroups.com General contact: info(a)lrec2026.info https://lrec2026.info Follow us on LinkedIn

1 0

Final Call for Papers: PrivateNLP co-located with ACL 2026 - Submission deadline extension until March 19
by Ivan Habernal 05 Mar '26

05 Mar '26

Final Call for papers Final Call for Papers: The Seventh Workshop on Privacy in Natural Language Processing (PrivateNLP) co-located with ACL 2026, San Diego, July 2-7, 2026 Submission deadline extension Website: https://sites.google.com/view/privatenlp2026/ PrivateNLP invites quality research contributions in different formats: Original research papers (long and short) Position and opinion papers All submissions will undergo a double-blind review process, and accepted submissions will be presented at the workshop. Topics of interest include but are not limited to: Privacy preserving machine learning for language models Generating privacy preserving test sets Data extraction attacks on NLP systems (e.g. membership inference attacks) Differential privacy for NLP models and data Generating Differentially private derived data NLP, privacy and regulatory compliance Private Generative Adversarial Networks Privacy in Active Learning and Crowdsourcing Privacy and Federated Learning in NLP User perceptions on privatized personal data Auditing provenance in language models Continual learning under privacy constraints NLP for studying privacy policies and other texts about privacy Ethical ramifications of AI/NLP in support of usable privacy Homomorphic encryption for language models Machine unlearning methods for language models Auditing privacy-preserving methods applied to NLP models and data Memorization of private information by language models Important Dates Submission deadline: Extended to March 19, 2026 Fast-track submission deadline: March 24, 2026 Acceptance notification: April 28, 2026 Camera-ready versions: May 12, 2026 Submission deadline for presenting findings papers: May 28, 2026 Workshop: July 2 or 3, 2026 All deadlines 23:59 Anywhere on Earth Submission Instructions Two types of submissions are invited: full papers and short papers. Please follow the ACL submission policies. Full papers should not exceed eight (8) pages of text, plus unlimited references. Final versions of full papers will be given one additional page of content (up to 9 pages) so that reviewers' comments can be taken into account. Short papers may consist of up to four (4) pages of content, plus unlimited references. Upon acceptance, short papers will still be given up to five (5) content pages in the proceedings. We also ask authors to include a limitation section and broader impact statement, following guidelines from the main conference. We will be using OpenReview for submissions: https://openreview.net/group?id=aclweb.org/ACL/2026/Workshop/PrivateNLP Please note OpenReview's moderation policy for newly created profiles: New profiles created without an institutional email will go through a moderation process that can take up to two weeks. New profiles created with an institutional email will be activated automatically. No anonymity period will be required for papers submitted to the workshop, per the latest updates to the ACL anonymity policy. However, submissions must still remain fully anonymized. Fast-Track Submission If your paper has been reviewed by ACL, EMNLP, EACL, or ARR and the average rating is higher than 2.5 (either average soundness or excitement score), the paper is qualified to be submitted to the fast-track. In the appendix, please include the reviews and a short statement discussing what parts of the paper have been revised. Link to fast-track submissions: Link TBD Please upload the following 3 documents in a single ZIP file: ARR reviews (including discussions and the meta-review) as a single PDF (e.g. printing the review webpage to PDF) The submitted anonymous paper as PDF A plain text file with the corresponding author's name and contact email Dual Submission Policy In addition to previously unpublished work, we invite papers on relevant topics which have been submitted to alternative venues (such as other NLP or ML conferences). Please follow the double-submission policy from ACL. Accepted cross-submissions will be presented as posters, with an indication of the original venue. Selection of cross-submissions will be determined solely by the organizing committee. Non-Archival Option There are no formatting or page restrictions for non-archival submissions. The accepted papers to the non-archival track will be displayed on the workshop website, but will NOT be included in the workshop proceedings or otherwise archived. Workshop organizers Ivan Habernal (ruhr-uni-bochum.de) Sepideh Ghanavati (maine.edu) Sara Haghighi (maine.edu) Krithika Ramesh (jhu.edu) Timour Igamberdiev (univie.ac.at) Shomir Wilson (psu.edu) Contact privatenlp26-orga(a)lists.ruhr-uni-bochum.de

1 0

Call for Participation – ECIR 2026
by Yifei Yuan 05 Mar '26

05 Mar '26

Join us at the 48th European Conference on Information Retrieval (ECIR 2026), Europe's premier forum for research in Information Retrieval (IR). ECIR brings together researchers, practitioners, and industry experts to share new, unpublished, and innovative research that is shaping the future of IR. 29 March – 2 April 2026 Delft, The Netherlands ECIR 2026 will take place as a fully in-person conference, fostering vibrant discussions and meaningful networking opportunities. The programme includes tutorials on Sunday, 29 March, the main conference from 30 March to 1 April, and a dedicated workshop day on Thursday, 2 April. What to Expect at ECIR 2026 Multiple research tracks covering recent advances in Information Retrieval Three distinguished keynote speakers offering inspiring insights A dedicated Industry Day bridging research and real-world innovation Workshops, tutorials, posters, and rich networking opportunities A welcoming environment with a strong tradition of supporting early-career researchers, including postgraduate students and postdoctoral fellows Whether you are presenting new research, engaging in thought-provoking discussions, or connecting with leading experts in academia and industry, ECIR 2026 promises an inspiring and dynamic experience. Explore the full program schedule: https://ecir2026.eu/programme/program-schedule Learn more about the conference, tracks, keynote speakers, and Industry Day: https://ecir2026.eu/ Register now to secure your place: https://ecir2026.dryfta.com/registration-page We look forward to welcoming you to Delft as we explore the latest advancements and challenges in Information Retrieval at ECIR 2026!

1 0

CorpusLab
by Michael Barlow 04 Mar '26

04 Mar '26

Colleagues, I have updated the corpuslab.com website with a simple concordance/collocation interface. You can search IMRDC sections of research articles in Arts, Economics, Engineering, Psychology and Social Science. It is not heavy-duty text analysis; you get 100 hits. You can sort by clicking the left or right context and you can highlight hedges, boosters, connectives, and reporting verbs. It is meant to be a gentle introduction to text analysis, an aid to student writers. There are also details of quite advanced disciplinary writing books written by me and Claude. As noted in those, many disciplines don’t follow the IMRDC structure, but use alternative labels or thematic headings. I am assuming, in the concordance search described above, the language features found in the Method section will still be present in articles that use an alternative heading, such as Experiment 1. I should perhaps add some explicit statement about the typical macrostructure found in these disciplines. Let me know if you have any questions, find any problems etc. Michael --- Michael Barlow. www.michaelbarlow.com<http://www.michaelbarlow.com/> Assoc. Prof. Applied Linguistics, University of Auckland Recent publications M. Barlow. 2026. Writing the Social Science Research Article.<https://www.amazon.com/dp/0940753367/ref=sr_1_1_so_ABIS_BOOK?crid=25EQBROGY…> Athelstan. M. Barlow. 2026. Writing the Humanities Research Article.<https://www.amazon.com/s?k=writing+the+humanities+research+article&i=stripb…> Athelstan. M.Barlow. 2026. Writing the Business Research Article<https://www.amazon.com/dp/0940753405/ref=sr_1_2?crid=2XO1YCSNL8ZT&dib=eyJ2I…>.<https://www.amazon.com/dp/0940753405/ref=sr_1_2?crid=2XO1YCSNL8ZT&dib=eyJ2I…> Athelstan M.Barlow. 2026. Writing the Economics Research Article<https://www.amazon.com/dp/0940753383/ref=sr_1_1?crid=2XO1YCSNL8ZT&dib=eyJ2I…>. Athelstan M. Barlow 2023. Ten Lectures on Corpora and Cognitive Linguistics<https://brill.com/display/title/61682>. Brill Le, Pham & Barlow 2023. The Academic Discourse of Mechanical Engineering<https://benjamins.com/catalog/scl.107>. Benjamins

1 0

Call for papers First Workshop on Evaluating LLMs for Specialized Domains (Eval4SD)
by carolin.holtermann＠uni-hamburg.de 04 Mar '26

04 Mar '26

Dear colleagues, We invite submissions to the First Workshop on Evaluating LLMs for Specialized Domains (Eval4SD), to be held co-located with KONVENS 2026 in Hamburg, Germany (September 14th - 17th). The workshop focuses on the evaluation of large language models in specialized domains such as—but not limited to—law, medicine, science, finance, digital humanities, social sciences, education, and politics. In this space, we have identified three core areas detailed below: LLM Benchmarking, Domain Research Replication, and Evaluation Methodology. Work that fits within the general theme but not any of the focus areas is also welcome! - **LLM Benchmarking:** We invite contributions that evaluate multiple models, datasets, inference methods, or prompting techniques on existing data or introduce novel, specialized benchmarking datasets. Papers in this direction may seek to answer questions like: ‘Which model should I use for my social science project?’ ‘Are open-weight models inferior for specialized tasks?’, or ‘Given a limited budget, what is my best choice of LLM for my digital humanities question?’ We especially encourage submissions that evaluate performance in low- and medium-resource languages. - **Domain Research Replication:** Does information automatically extracted using a different model or a slightly altered approach still support the same domain conclusions? We invite submissions that attempt to replicate existing domain research using a tweaked LLM setup. For us, testing open-weight models is especially important in light of replicability. We are excited to see how robust domain research is to adaptations of the automation setups, from prompting to model weights and training data. - **Metrics and Evaluation Methodology:** We invite submissions on methodology for assessing LLM outputs in complex tasks. This includes work on LLM judge setups or novel rule-based metrics for specialized tasks. We allow submissions in two categories: - **Long Papers (up to 8 pages + references):** Complete research contributions with novel findings, experimental results, and thorough analysis. Suitable for mature work on LLM evaluation methodology or new benchmark proposals. - **Short & Position Papers (up to 4 pages + references):** Preliminary results, position papers, system descriptions, and focused contributions. Great for provocative arguments or narrowly scoped empirical studies. Submissions follow the ACL template; reviews are double-blind and are conducted via OpenReview (https://openreview.net/group?id=GSCL.org/KONVENS/2026/Workshop/Eval4SD). Additionally, we welcome non-archival submissions to present recently published work or seek feedback on work-in-progress without violating dual-submission policies. Accepted papers will be presented at the workshop, but will not be included in the official proceedings. Important dates: - Submission deadline: July 03, 2026 (23:59 CEST) - Notification of acceptance: July 31, 2026 - Camera-ready deadline: August 15, 2026 - Workshop date: co-located with KONVENS (14th - 17th), exact day TBA Website: https://eval4sd.github.io/ Contact: eval4sd-organizers(a)googlegroups.com

1 0

[CFP] First International Workshop on Extraction from Triplet Text-Table-Knowledge Graph and associated Challenge @ ESWC 2026 - deadline extended
by Raphaël Troncy 04 Mar '26

04 Mar '26

[Apologies for cross-postings] Call for Papers First International Workshop on Extraction from Triplet Text-Table-Knowledge Graph and associated Challenge https://ecladatta.github.io/triplet2026/ in conjunction with the 23rd European Semantic Web Conference (ESWC 2026) https://2026.eswc-conferences.org/, Dubrovnik, Croatia Important dates: - **Submission deadline (extended)**: 13 March, 2026 (11:59pm, AoE) - **Notifications**: 31 March, 2026 - **Challenge registration deadline**: 15 March, 2026 - **Challenge results submission**: 10 April, 2026 - **Camera-ready deadline**: 15 April, 2026 (11:59pm, AoE) - **Workshop**: Sunday 10 May OR Monday 11 May 2026 Motivation: Understanding information spread across text and table is essential for tasks such as question answering and fact checking. Existing benchmarks primarily deal with semantic table interpretation or reasoning over tables for question answering, leaving a gap in evaluating models that integrate tabular and textual information, perform joint information extraction across modalities, or can automatically detect inconsistencies between modalities. This workshop aims to provide a forum for exchanging ideas between the NLP community working on open information extraction and the vibrant Semantic Web community working on the core challenge of matching tabular data to Knowledge Graphs, on populating knowledge graphs using texts and on reasoning across text, tabular data and knowledge graphs. The workshop also targets researchers focusing on the intersection of learning over structured data and information retrieval, for example, in retrieval augmented generation (RAG) and question answering (QA) systems. Hence, the goal of the workshop is to connect researchers and trigger collaboration opportunities by bringing together views from the Semantic Web, NLP, database, and IR disciplines. Scope: The topics of interest include but are not limited to: - Semantic Table Interpretation - Automated Tabular Data Understanding - Using Large Language Models (LLMs) for Information Extraction - Generative Models and LLMs for Structured Data - Knowledge Graph Construction and Completion with Tabular Data and Texts - Analysis of Tabular Data on the Web (Web Tables) - Benchmarking and Evaluation Frameworks for Joint Text-Table Data Analysis - Applications (e.g. data search, fact-checking, Question-Answering, KG alignment) Submission Guidelines: We invite two types of submissions: 1. Full research papers (12-15 pages) including references and appendices 2. Challenge papers (6-8 pages) including references and appendices All submissions should be formatted in the CEUR layout format, https://www.overleaf.com/latex/templates/template-for-submissions-to-ceur-w… This workshop is double-blind and non-archival. Submissions are managed through EasyChair at https://easychair.org/conferences/?conf=triplet2026. All accepted papers will be presented as posters or as oral talks. **TRIPLET Challenge:** In recent years, the research community has shown increasing interest in the joint understanding of text and tabular data, often, for performing tasks such as question answering or fact checking where evidences can be found in texts and tables. Hence, various benchmarks have been developed for jointly querying tabular data and textual documents in domains such as finance, scientific publications, and open domain. While benchmarks for triple extraction from text for Knowledge Graph construction and semantic annotation of tabular data exist in the community, there remains a gap in benchmarks and tasks that specifically address the joint extraction of triples from text and tables by leveraging complementary clues across these different modalities. The TRIPLET 2026 challenge is proposing three sub-tasks and benchmarks for understanding the complementarity between tables, texts, and knowledge graphs, and in particular to propose a joint knowledge extraction and reconciliation process. #Sub-Task 1: Assessing the Relatedness Between Tables and Textual Passages The goal of this task is to assess the relatedness between tables and textual passages (within documents and across documents). For this purpose, we have constructed LATTE (Linking Across Table and Text for Relatedness Evaluation), a human annotated dataset comprising table–text pairs with relatedness labels. LATTE consists of 7,674 unique tables and 41,880 unique textual paragraphs originating from 3,826 distinct Wikipedia pages. Each text paragraph is drawn from the same or contextually linked pages as the corresponding table, rather than being artificially generated. LATTE provides a challenging benchmark for cross-modal reasoning by requiring classification of related and unrelated table–text pairs. Unlike prior resources centered on table-to-text generation or text retrieval, LATTE emphasizes fine-grained semantic relatedness between structured and unstructured data. The Figure below provides an example, using a web-annotation tool we developed, of how we identify the relatedness between the sentence containing the entity AirPort Extreme 802.11n (highlighted in Orange) and the data table providing information about output power and frequency for this entity. Participants are provided with tables and textual passages that would need to be ranked. The evaluation will use metrics such as P@k, R@k and F1@k. Go to https://www.codabench.org/competitions/12776/ and enroll to participate in this Task. #Sub-Task 2: Joint Relation Extraction Between Texts and Tables The goal of this task is to automatically extract knowledge jointly from tables and related texts. For this purpose, we created ReTaT, a dataset that can be used to train and evaluate systems for extracting such relations. This dataset is composed of (table, surrounding text) pairs extracted from Wikipedia pages and has been manually annotated with relation triples. ReTaT is organized in three subsets with distinct characteristics: domain (business, telecommunication and female celebrities), size (from 50 to 255 pairs), language (English vs French), type of relations (data vs object properties), close vs open list of relation, size of the surrounding text (paragraph vs full page). We then assessed its quality and suitability for the joint table-text relation extraction task using Large Language Models (LLMs). Given a Wikipedia page containing texts and tables and a list of predicates defined in Wikidata, a participant system should extract triples composed of mentions located partly in the text and partly in the table and disambiguated with entities and predicates identified in the Wikidata reference knowledge graph. For example, in the Figure below, an annotation triple <Q13567390, P2109, 24.57> is associated with mentions highlighted in orange (subject), blue (predicate) and green (object) to annotate the document available at https://en.wikipedia.org/wiki/AirPort_Extreme. Similar to the Text2KGBench evaluation (https://link.springer.com/chapter/10.1007/978-3-031-47243-5_14), and because the set of triples are not exhaustive for a given sentence, to avoid false negatives, we follow a locally closed approach by only considering the relations that are part of the ground truth. The evaluation then uses metrics such as P, R and F1. Go to https://www.codabench.org/competitions/12936/ and enroll to participate in this Task. # Sub-Task 3: Detecting Inconsistencies Between Texts, Tables and Knowledge Graphs The goal of this task is to check the consistency of knowledge extracted from tables and texts with existing triples in the Wikidata knowledge graph. Different kind of inconsistencies will be considered in this task. Participants to this task will be able to report on their findings in their system paper. See the Figure at https://ecladatta.github.io/images/triplet_annotation_tool.png # Data & Evaluation: For the first 2 sub-tasks, we have released a training dataset with ground-truth annotations, enabling participant teams to develop machine learning-based systems, and in particular for training purposes and for hyperparameter optimizations and internal validations. A separate blind test dataset will remain private and be used for ranking the submissions. Participants should register on Codabench and then enroll for each sub-task separately (Task 1: https://www.codabench.org/competitions/12776/ and Task 2: https://www.codabench.org/competitions/12936/). Each team are allowed a limited number of daily submissions, and the highest achieved accuracy will be reported as the team's final result. We encourage participants to develop open-source solutions, to utilise and fine-tune pre-trained language models and to experiment with LLMs of various size in zero-shot or few-shot settings. # Challenge Important Dates: - Release of training set: 13 February 2026 - Deadline for registering to the challenge: 15 March 2026 - Release of test set: 24 March 2026 - Submission of results: 10 April 2026 - System Results & Notification of Acceptance: 17 April 2026 - Submission of System Papers: 28 April 2026 - Presentations @ TRIPLET Workshop: May 2026 Workshop Organizers - Raphael Troncy (EURECOM, France) - Yoan Chabot (Orange, France) - Véronique Moriceau (IRIT, France) - Nathalie Aussenac-Gilles (IRIT, France) - Mouna Kamel(IRIT, France) Contact: For discussions, please use our Google Group, https://groups.google.com/g/triplet-challenge The workshop is supported by the ECLADATTA project funded by the French National Funding Agency ANR under the grant ANR-22-CE23-0020. -- Raphaël Troncy EURECOM, Campus SophiaTech Data Science Department 450 route des Chappes, 06410 Biot, France. e-mail: raphael.troncy(a)eurecom.fr & raphael.troncy(a)gmail.com Tel: +33 (0)4 - 9300 8242 Fax: +33 (0)4 - 9000 8200 Web: http://www.eurecom.fr/~troncy/

1 0

Call for papers - Workshop on New Trends in Automatized Language Assessment (TALA)
by Romane Werner 04 Mar '26

04 Mar '26

Call for papers - Workshop on New Trends in Automatized Language Assessment (TALA) The Workshop on New Trends in Automatized Language Assessment (TALA) will take place on 7 April 2026 in Louvain-la-Neuve, Belgium, and online (hybrid event). This meeting aims to provide an overview of various recent approaches of automatized language assessment and to offer researchers, academics and (PhD) students an excellent opportunity to share and discuss recent trends and cutting-edge methods on language assessment-related research. In particular, the workshop will focus on proficiency assessment by mainly targeting automatic readability assessment (ARA) and automated essay scoring (AES). Automatic readability assessment constitutes an interdisciplinary field of research concerned with the linguistic, cognitive, and typographic factors that influence the ease with which a text can be read and understood by different audiences. It is gaining increasing importance across a wide range of domains, including education, institutional communication, digital accessibility, and automated assessment of language proficiency. It has been an active field within natural language processing since the beginning of the 21st century. Automated essay scoring aims to analyze written productions in order to generate an evaluation of writers’ competence in a specific field. For language-oriented AES, it is the written linguistic skills that are targeted. This task is particularly critical in language assessment contexts, but it can also support learning processes and the generation of formative feedback. The workshop will include an invited speaker talk and some presentations based on abstract selection. Invited speaker: Rodrigo Wilkens (University of Exeter) is a specialist in computational readability modeling and automated essay scoring. His research focuses on multilingual proficiency assessment, linguistic feature modeling, and the use of large language models for educational applications. He has contributed to the development and evaluation of ARA and AES systems, with particular emphasis on non-English languages. His recent work explores the representational capacity of transformer models for proficiency prediction, interpretability in automated assessment, and readability-guided text generation. We welcome abstracts addressing literature review, research results, ongoing research or negative results on the topics related to the main theme, with particular interest in the following subfields: · AI and LLM-based approaches to automated language assessment, especially AES and ARA · Computational and linguistic modeling of readability and writing proficiency · Evaluation methodologies, validation frameworks, and interpretability in automated assessment · Multilingual and non-English language assessment · Corpus creation, annotation schemes, and new benchmark tasks · Fairness, bias, and ethical considerations in automated assessment · Theoretical perspectives linking linguistic features and proficiency modeling · Critical reviews and meta-analyses in ARA/AES research Submission format: Abstracts may be submitted in French or English and should be between 300 and 500 words. Authors are encouraged to include a short list of relevant references, which will not count toward the word limit. Abstracts should be anonymized for review. Author names and affiliations must be provided separately in the submission form. Submissions must be made via the online form available at: https://forms.gle/w1L6JNx8YAEgtswB7. Please note that no proceedings will be later organized, as this workshop aims to foster scientific exchanges above all. Important dates: Abstract deadline: 20 March Acceptance notification: 1st of April Workshop: 7 April Organizing Committee: Prof. Thomas François, Prof. Rodrigo Wilkens, Dr. Eleonora Guzzi, Lingyun Gao, Amandine Pay, Elodie Vanzeveren, Romane Werner.

1 0

2026

2025

2024

2023

2022

Corpora