December 2024 - Corpora

GermEval: Call for Shared Task Proposals
by Christian Wartena 03 Dec '24

03 Dec '24

GermEval: Call for Shared Task Proposals We cordially invite proposals for the GermEval Shared Task 2025 co-located with Konvens 2025 in Hildesheim, Germany (September 9-12), https://konvens-2025.hs-hannover.de/ . Background GermEval is a series of shared task evaluation campaigns that focus on Natural Language Processing for the German language and has been running since 2014, traditionally co-located with Konvens. Previous shared tasks Previous shared tasks have been devoted to: * Named entity recognition (2014) * Lexical Substitution (2015) * Aspect-based Sentiment in Social Media Customer Feedback (2016) * Offensive Language (2018, 2019) * Hierarchical classification of blurbs (2019) * Lemmatization of German web and social media texts (2019) * Text Complexity (2022) * Speaker Attribution (2023) * Sexism Detection in German Online News Fora (2024) See also https://germeval.github.io/tasks/ for details. Time schedule Proposal submission deadline: December 15, 2024 Notification: December 20, 2024 Extended submission period January 4 - February 14, 2025 Extended notification: One week after submission Workshop: September 10, 2025 The early deadline facilitates a quick start of the organization of a shared task. Later submission is possible until February 14. We will try to review the proposal in that case within one week. While fixing the exact timeline for the shared task is up to the task organizers, we propose the following tentative schedule: Trial data ready: March 8, 2025 Training data ready: April 12, 2025 Test data ready: May 17, 2025 Evaluation start: June 16, 2025 Evaluation end: June 27, 2025 Paper submission due: July 11, 2025 Camera ready due: August 15, 2025 Submission guidelines For GermEval proposals are invited for any shared task involving natural language processing in the context of the German language. For a detailed questionnaire to be submitted please see: https://gscl.org/germeval Proposals should be submitted by e-mail to info.konvens2025(a)gscl.org<mailto:info.konvens2025@gscl.org>, from the email of the contact person, with the subject "GermEval-2025 Shared Task Proposal". Proposals should make clear that a schedule similar to that suggested above can be implemented, especially for the preparation of resources (trial/training/development/test data sets). Proposals should be 2 to 3 pages long, in ACL - PDF format. We encourage proposers to include appendices with examples that help understanding the data and type of evaluation. Proposals will be reviewed by the KONVENS Program Committee. Proposers might be contacted during the reviewing period to provide further information. Potential proposers should feel free to indicate the intention to submit by emailing info.konvens2025(a)gscl.org<mailto:info.konvens2025@gscl.org>. We are also happy to answer your questions about the process, or to solicit early feedback for a proposal. Proceedings Peer-reviewed workshop papers can be published in the KONVENS 2025 Proceedings. A camera-ready version of all accepted papers should be available at latest on August 22, 2025. Prof. Dr. Christian Wartena Hochschule Hannover Fakultät III - Medien, Information und Design Abt. Information und Kommunikation Lehrgebiet Sprach- und Wissensverarbeitung Expo Plaza 12 30539 Hannover e-mail: christian.wartena(a)hs-hannover.de<mailto:christian.wartena@hs-hannover.de> [DATA-H-Logo_RGB_Unterzeile_klein] Prof. Dr. Christian Wartena Hochschule Hannover Fakultät III - Medien, Information und Design Abt. Information und Kommunikation Lehrgebiet Sprach- und Wissensverarbeitung Expo Plaza 12 30539 Hannover e-mail: christian.wartena(a)hs-hannover.de<mailto:christian.wartena@hs-hannover.de> [DATA-H-Logo_RGB_Unterzeile_klein]

1 0

Last Call for Abstracts: LLM fails – Failed experiments with Generative AI and what we can learn from them
by Ngoc Duyen Tanja Tu 03 Dec '24

03 Dec '24

more information on our Workshop-Website: https://www.ids-mannheim.de/home/lexiktagungen/llm-fails Dear list members, we would like to invite you to submit abstracts to our workshop "LLM fails – Failed experiments with Generative AI and what we can learn from them" taking place from April 8-9, 2025 at the Leibniz Institute for the German Language, Mannheim, Germany. If the extended short papers are positively reviewed, there is an opportunity to publish them in a special issue of the Journal for Language Technology and Computational Linguistics. Further information (automatic English translation): Failed experiments typically have no place in scientific discourse; they are discarded and not published. We believe this leads to a loss of potential knowledge. After all, a systematic reflection on the reasons for failure allows for the questioning and/or improvement of methods used. Furthermore, when previously failed experiments are repeated and succeed, explicit progress can be determined. Thus, the discussion and documentation of failures creates added value for the scientific community from the perspective of methodological reflection. This is even more relevant in a field like research into and with Generative Artificial Intelligence (AI), which cannot look back on decades of tradition and where best practices are still being negotiated. This workshop focuses on linguistic and NLP experiments with Generative AI that did not yield the desired results, such as but not limited to: • Using Generative AI as a Named-Entity Recognizer • Using Generative AI for automatic transcription of spoken language data • Using Generative AI for the creation of dictionary entries • Using Generative AI for the detection of language change phenomena The contribution should clarify how this failure can contribute to knowledge gain regarding the work with Generative AI. Unpublished proposals can be submitted anonymously as an abstract (500-750 words) in either German or English to the following email address by December 11, 2024: llmfails(at)ids-mannheim.de The organization team will decide on the acceptance of contributions by December 16, 2025. If a contribution is accepted, a short paper (4-6 pages without references) in English will be requested by February 15, 2025. The short papers will undergo double-blind peer review and will be published in a special issue of the Journal for Language Technology and Computational Linguistics and archived at ACL Anthology. Best, Annelen Brunner, Christian Lang, Ngoc Duyen Tanja Tu (Organising committee) -- Dr. Ngoc Duyen Tanja Tu Leibniz-Institut für Deutsche Sprache Abteilung Grammatik Tel: +49 621-1581-242

1 0

Junior Professorship in Information&Language Processing / AI at LMU Munich
by Hinrich Schuetze 03 Dec '24

03 Dec '24

Dear community members, We cordially invite applications for the following position. Thanks - Hinrich Junior Professorship (W1) Information and Language Processing Using AI Methods LMU Munich tenure track apply by December 12 https://job-portal.lmu.de/jobposting/7815e9257475585704e21860f79f54abceadb4…

1 0

Corpora of English novels
by Martin Wynne 02 Dec '24

02 Dec '24

I have a student who is interested in tracing the development of the English novel from its origins to the present day (or at least to the start of the twentieth century), and I'm trying to gather information about relevant corpora covering this text type and period. We know about the European Literary Text Collection (ELTeC, https://www.distant-reading.net/eltec/) which will be very useful for the later end of the timescale. We also know it is possible to assemble a corpus from Project Gutenberg, archive.org, Oxford Text Archive, etc. , but would be interested in re-using any corpora that people might already have made, which aim to be representative of particular periods within this genre. The student has some flexibility with her research question, so while the original idea of 'English novels' was probably 'novels in English from Great Britain and Ireland', other related areas such as US novels might be interesting as well. Any tips and suggestions gratefully received. If we get a number of interesting direct emails, I'll be happy to summarize the results to the list. Best wishes, Martin -- Senior Researcher in Corpus Linguistics Faculty of Linguistics, Philology and Phonetics, University of Oxford National Co-ordinator, CLARIN-UK martin.wynne(a)ling-phil.ox.ac.uk https://orcid.org/0000-0002-4155-0530

4 5