- Corpora - ELRA lists

36th International Conference on Advanced Information Systems Engineering (CAiSE 2024): First Call for Papers
by Announce 01 Oct '23

01 Oct '23

*** First Call for Papers *** 36th International Conference on Advanced Information Systems Engineering (CAiSE'24) June 3-7, 2024, 5* St. Raphael Resort and Marina, Limassol, Cyprus https://cyprusconferences.org/caise2024/ (*** Submission Deadline: November 24, 2023 AoE ***) The CAiSE’24 organization calls for full papers with a special emphasis on the theme of Information Systems in the Age of Artificial Intelligence. Artificial Intelligence (AI) has emerged as a transformative technology, revolutionizing various industries, and its significance in Information Systems cannot be overstated. AI-powered systems have the potential to streamline operations, enhance decision-making processes, and drive innovation across organizations. From data analysis to automated processes, AI is reshaping the way we leverage information in the digital age. The relevance of AI in IS extends beyond internal operations. AI-powered predictive analytics enables organizations to forecast trends, anticipate customer needs, and optimize resource allocation. This empowers businesses to adapt swiftly to changing market dynamics, gain a competitive edge, and make proactive decisions. AI algorithms can also detect anomalies and patterns that indicate potential security breaches, contributing to robust cybersecurity measures in information systems. However, while acknowledging the benefits, it is essential to consider the ethical implications of AI in information systems. Ensuring data privacy, addressing bias in algorithms, and maintaining transparency are vital aspects that need to be carefully managed and regulated to foster trust and accountability. In addition to offering an exciting scientific program, CAiSE’24 will feature a best paper award, a journal special issue, and a PhD-thesis award: • Best Paper Award‚ prize EUR 1000 (sponsored by Springer) • A small selection of best papers will be invited to submit enhanced versions for consideration in a special issue of Elsevier Information Systems journal dedicated to this conference. • PhD-Thesis Award • Best PhD thesis of a past CAiSE Doctoral Consortium author (co-sponsored by the CAiSE Steering Committee and Springer) Papers should be submitted in PDF format. Submissions must conform to Springer‚ LNCS format and should not exceed 15 pages, including all text, figures, references, and appendices. Submissions not conforming to the LNCS format, exceeding 15 pages, or being obviously out of the scope of the conference, will be rejected without review. See the guidelines here: https://www.springer.com/comp/lncs/authors.html . The results described must be unpublished and must not be under review elsewhere. Three to five keywords characterizing the paper should be listed at the end of the abstract. Each paper will be reviewed by at least two program committee members and, if positively evaluated, by one additional program board member. The selected papers will be discussed among the paper reviewers online and during the program board meeting. As the review process is not blind, please indicate your name and affiliation on your submission. Accepted papers will be presented at CAiSE’24 and published in the Springer Lecture Notes in Computer Science (LNCS) conference proceedings. We invite three types of original and scientific papers. The type of submission must be indicated in the submission system. Each contribution should explicitly address the engineering or the operation of information systems, clearly identify the information systems problem addressed, the expected impact of the contribution to information system engineering or operation, and the research method used. We strongly advise authors to clearly emphasize these aspects in their paper, including the abstract. Technical papers describe original solutions (theoretical, methodological or conceptual) in the field of IS Engineering. A technical paper should clearly describe the situation or problem tackled, the relevant state of the art, the position or solution suggested and its potential‚ as well as demonstrate the benefits of the contribution through a rigorous evaluation. Empirical papers evaluate existing problem situations including problems encountered in practice, or validate proposed solutions with scientific means, i.e., by empirical studies, experiments, case studies, experience reports, simulations, etc. Scientific reflection on problems and practices in industry also falls into this category. The topic of the evaluation presented in the paper as well as its causal or logical properties must be clearly stated. The research method must be sound and appropriate. Exploratory papers describe completely new research positions or approaches, in order to face a generic situation arising because of new ICT tools, new kinds of activities, or new IS challenges. They must precisely describe the situation and demonstrate why current methods, tools, ways of reasoning, or meta-models are inadequate. They must also rigorously present their approach and demonstrate its pertinence and correctness in addressing the identified situation. The topics of contribution include but are not limited to: • Novel Approaches to IS Engineering ◦ Artificial Intelligence and Machine Learning ◦ Robotic Process Automation (RPA) ◦ Big Data, Data Science and Analytics ◦ Blockchain applications in IS ◦ Simulation and Digital Twins  ◦ IS for collaboration and social computing  ◦ Virtual reality / Augmented Reality ◦ Context-aware, autonomous and adaptive IS • Models, Methods and Techniques in IS Engineering ◦ Ontologies and Ontology Engineering ◦ Conceptual modeling, languages and design ◦ Requirements engineering ◦ Process modeling, analysis and improvement ◦ Process automation, mining and monitoring ◦ Models and methods for evolution and reuse ◦ Domain and method engineering ◦ Product lines, variability and configuration management ◦ Compliance and alignment handling ◦ Active and interactive models ◦ Quality of IS models for analysis and design ◦ Visualization techniques in IS ◦ Decision models and business intelligence ◦ Knowledge graphs ◦ Human-centered techniques • Architectures and Platforms for IS Engineering ◦ Distributed, mobile and open architecture ◦ Big Data architectures ◦ Cloud- and edge-based IS engineering ◦ Service oriented and multi-agent IS engineering ◦ Multi-platform IS engineering ◦ Cyber-physical systems and Internet of Things (IoT) ◦ Workflow and Process Aware Information Systems (PAIS) ◦ Handling of real time data streams ◦ Content management and semantic Web ◦ Crowdsourcing platforms ◦ Conversational agents (chatbots) ◦ Microservices design and deployment • Domain-specific and Multi-aspect IS Engineering ◦ IT governance ◦ eGovernment ◦ Autonomous and smart systems (smart city management, smart vehicles, etc.) ◦ IS for healthcare ◦ Educational Systems and Learning Analytics ◦ Value and supply chain management ◦ Industry 4.0 ◦ Sustainability and social responsibility management ◦ Privacy, security, trust, and safety management ◦ IS in the post-COVID world Submit your paper using the Easy Chair link: https://easychair.org/conferences/?conf=caise2024 . IMPORTANT DATES • Abstract Submission: 24th November 2023 (AoE) • Paper Submission: 1st December 2023 (AoE) • Notification of Acceptance: 4th March 2024 • Camera-ready Papers: 5th April 2024 • Author registration: 5th April 2024 ORGANISATION General Chairs • Haris Mouratidis, University of Essex, UK • Pnina Soffer, University of Haifa, Israel Local Organizing and Finance Chair • George A. Papadopoulos, University of Cyprus, Cyprus Program Chairs • Giancarlo Guizzardi, University of Twente, The Netherlands • Flavia Maria Santoro, University of the State of Rio de Janeiro, Brazil Other Committee Members https://cyprusconferences.org/caise2024/committees/

1 0

2023 ICR Outstanding Corpus Thesis Award
by Prof CK Jung 01 Oct '23

01 Oct '23

[Apologies for cross-posting] Dear all The ICR Outstanding Corpus Thesis Award is a prestigious annual distinction established to acknowledge recent graduates who have delivered exemplary theses at either the MA/MSc or PhD/EdD levels specifically within the domain of corpus research. *Eligibility Criteria:*- The candidate must have graduated from a recognised university that requires a thesis submission for the conferment of an MA/MSc or PhD/EdD degree. - The degree must have been awarded to the nominee in 2023. - The thesis presented should be acknowledged for its noteworthy contribution to the domain of corpus research. - Theses should be authored in English or Korean. Translations from other languages to English are permissible. It’s important to note that for the award to be retained, the nominee is required to successfully publish a full paper in the Asia Pacific Journal of Corpus Research within a year of receiving the award. Failure to do so will result in automatic revocation of the award. Upon successful publication, a certificate will be dispatched to the awardee. *Submission Details:*- Thesis title - Abstract - Recommender (Affiliation, Name, Position) - Candidate’s Name - Degree Conferment Date - Degree Granting University - For thesis submission (in PDF format), kindly forward to: help(a)icr.or.kr - Submission Deadline: 31 December 2023 *For more information, please visit http://icr.or.kr/awards <http://icr.or.kr/awards>.* Institute for Corpus Research --- *CK Jung BEng(Hons) Birmingham MSc Warwick EdD Warwick Cert Oxford* Associate Professor | Department of English Language and Literature, Incheon National University, *South Korea* President | The Korea Association of Secondary English Education, *South Korea *(http://kasee.org) Vice President | The Korea Association of Primary English Education, *South Korea *(http://kapee.or.kr) Director | Institute for Corpus Research, Incheon National University, *South Korea* (http://icr.or.kr) Editor-in-Chief | Asia Pacific Journal of Corpus Research, ICR, *International* (http://icr.or.kr/apjcr) Editorial Board | Corpora, Edinburgh University Press, *UK* Editorial Board | English Today, Cambridge University Press, *UK* E: ckjung(a)inu.ac.kr / T: +82 (0)32 835 8129

1 0

Deadline Extension (20 October 2023) Call for papers: SCOPUS indexed - Hybrid Event - Springer Publication
by Anu Bajaj 30 Sep '23

30 Sep '23

* Deadline Extension: please circulate this CFP to your colleagues and networks ** ------------On multiple requests from several authors, we have extended the submission deadline till October 20, 2023--------------- ------------*International Joint Conferences - Published by Springer LNNS Series (Scopus)*--------------- ** ISDA 2023 - HIS 2023 - SoCPaR 2023 - IBICA 2023 - IAS 2023 - NaBIC 2023 - WICT 2023 ** * *Onsite and On the World Wide Web ** *Publisher*: Springer Verlag, LNNS Series *Indexed by*: SCOPUS, DBLP, INSPEC, SCImago etc. ** Venue details and accommodation details are now published ** *Onsite Venues: *Olten, Switzerland; Porto, Portugal; Kaunas, Lithuania; Kochi, India *Please visit:* https://mirlabs.org/ias23/venue2.php <https://er-anubajaj-dot-yamm-track.appspot.com/2-2ypoYLoQkMn5Qu41DzfLDgoGhB…> ***Important Dates*** --------------------- Paper submission due:* September 30, 2023* Notification of paper acceptance: *October 31, 2023* Registration and Final manuscript due: *November 10, 2023* *Conferences:* December 11-15, 2023 -- *23rd International Conference on Intelligent Systems Design and Applications (ISDA 2023)* http://www.mirlabs.net/isda23 <https://er-anubajaj-dot-yamm-track.appspot.com/2U2Q7H3L2mEXiMb7qsUEVTfuRNMx…> Proceedings of ISDA’22: https://link.springer.com/book/10.1007/978-3-031-27440-4 <https://er-anubajaj-dot-yamm-track.appspot.com/2O2tJ6bhKv3ICtm_M4WrxSIHrkil…> *Submission link: *https://cmt3.research.microsoft.com/ISDA2023 <https://er-anubajaj-dot-yamm-track.appspot.com/2wh4gk1oJvcNdOHMcLgNOzPnw4zo…> -- *23rd International Conference on Hybrid Intelligent Systems (HIS 2023)* http://www.mirlabs.net/his23 <https://er-anubajaj-dot-yamm-track.appspot.com/2KyAHA4JA6zb_hBaM_bsJImXIgAt…> Proceedings of HIS'22: https://link.springer.com/book/10.1007/978-3-031-27409-1 <https://er-anubajaj-dot-yamm-track.appspot.com/2yRh-QHfBEQKmzsC3PRbjIKiVFkf…> *Submission link: *https://cmt3.research.microsoft.com/ICHIS2023 <https://er-anubajaj-dot-yamm-track.appspot.com/219rKKaeqKKMLf_silKq0SfhFaJP…> -- 19th International Conference on Information Assurance and Security (IAS 2023) http://www.mirlabs.org/ias23 <https://er-anubajaj-dot-yamm-track.appspot.com/21wiQCc4Wt-1_y8ainNwtVOS3ZJ3…> Proceedings of IAS'22: https://link.springer.com/book/10.1007/978-3-031-27409-1 <https://er-anubajaj-dot-yamm-track.appspot.com/2PwPMlBbwV5upqnvqjb12stz7RHg…> *Submission link*: https://cmt3.research.microsoft.com/IAS2023 <https://er-anubajaj-dot-yamm-track.appspot.com/2f5nc-HkpOPoHH5zV2ELFOTPcO7N…> -- *15th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2023)* http://www.mirlabs.org/socpar23 <https://er-anubajaj-dot-yamm-track.appspot.com/26WYgXBX1IVAz-8HIlhG4J3X5UmN…> Proceedings of SoCPaR'22: https://link.springer.com/book/10.1007/978-3-031-27524-1 <https://er-anubajaj-dot-yamm-track.appspot.com/2bBclcDkZ_zBGL9LjKb4XtcwnUji…> *Submission link: *https://cmt3.research.microsoft.com/SOCPAR2023 <https://er-anubajaj-dot-yamm-track.appspot.com/2froA_XLJVJVtN8PIfSl30KSaDbE…> -- *15th World Congress on Nature and Biologically Inspired Computing (NaBIC 2023)* http://www.mirlabs.net/nabic23 <https://er-anubajaj-dot-yamm-track.appspot.com/2vRWNTvT6HdjqEjlAtu-Dx_VxOgZ…> Proceedings of NaBIC'22: https://link.springer.com/book/10.1007/978-3-030-96302-6 <https://er-anubajaj-dot-yamm-track.appspot.com/2e0FX148bGU9zkNapVLGDkfuZGKh…> *Submission link:* https://cmt3.research.microsoft.com/NABIC2023 <https://er-anubajaj-dot-yamm-track.appspot.com/2I8hnoy33kvvJ3saB7AdxqmMZ3Qg…> -- *14th International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA 2023)* http://www.mirlabs.net/ibica23 <https://er-anubajaj-dot-yamm-track.appspot.com/2IiRZUltXA6P-_wvZajN9pHsxlov…> Proceedings of IBICA'22: https://link.springer.com/book/10.1007/978-3-031-27499-2 <https://er-anubajaj-dot-yamm-track.appspot.com/27yYWf93kHFSRPz0ZD0NtPNhoFqn…> *Submission link:* https://cmt3.research.microsoft.com/IBICA2023 <https://er-anubajaj-dot-yamm-track.appspot.com/21vjJoq7HraSAckJqrnShThGapG6…> -- *13th World Congress on Information and Communication Technologies (WICT 2023)* http://www.mirlabs.org/wict23 <https://er-anubajaj-dot-yamm-track.appspot.com/2gTahGNsaLYLIPjYob8MAqTKXhRc…> Proceedings of WICT'22: https://link.springer.com/book/10.1007/978-3-031-27499-2 <https://er-anubajaj-dot-yamm-track.appspot.com/22ohbgHGVdSeNCKioS-KvoMzCUJV…> *Submission link: *https://cmt3.research.microsoft.com/WICT2023 <https://er-anubajaj-dot-yamm-track.appspot.com/2gHXqW4-NwR-Vtm5OPrGaaKhJy6G…> ***Plenary Talks*** ------------------------ Christine Zarges, Aberystwyth University, UK Theresa Schmiedel, University of Applied Sciences and Arts Northwestern Switzerland, Basel, Switzerland Ke Feng, Singapore-ETH Centre, The National University of Singapore, Singapore Stefka Fidanova, Bulgarian Academy of Sciences, Bulgaria Diego Oliva, Universidad de Guadalajara, Mexico Sebastian Ventura, University of Cordoba, Spain Ana Maria Madureira, Instituto Superior de Engenharia do Porto, Portugal Nuno Bettencourt, Instituto Superior de Engenharia do Porto, Portugal Aboul Ella Hassanien, Cairo University, Egypt Milan Tuba, Singidunum University, Serbia Dalia Kriksciuniene, Vilnius University / Kaunas University of Applied Sciences, Lithuania Kusum Deep, Indian Institute of Technology Roorkee, India João Pedrosa, Instituto de Engenharia de Sistemas e Computadores, Portugal ** *About the International events* ** -------------------------------------------------- Provides an international forum to share the latest research results, ideas and experiences in intelligent systems design and applications; soft computing; information assurance and security; nature-inspired computing, pattern recognition; and information and communication technologies by bringing together the leading communities in this research space. These events are built on a solid history, through ISDA to WICT, connecting young researchers with highly experienced peers to forge connections, which can last for many years. ** *Topics (not limited to)* ** -------------------------------------- Artificial Intelligence Big Data Analytics Human Computer Interaction Intelligent Systems and Applications Hybrid Intelligent Systems Soft Computing and Pattern Recognition Nature and Biologically Inspired Computing Innovations in Bio-Inspired Computing and Applications Information and Assurance Security Innovations in Information and Communication Technologies Wireless Networks Data Mining IoT, Cloud Computing Software Engineering Digital Learning Cybersecurity ***Submission Guidelines*** ------------------------------------- Submission of paper should be made through the submission page from the conference web page. Please refer to the conference website for guidelines to prepare your manuscript. *Paper format templates:* https://www.springer.com/de/authors-editors/book-authors-editors/manuscript… <https://er-anubajaj-dot-yamm-track.appspot.com/2heWlEr4Mfm4TkVJmlOXS8CdvgjG…> ***Technical Contact*** --------------------------- Dr. Ajith Abraham Email: ajith.abraham(a)ieee.org [image: beacon]

1 0

NLP Tenure-Track faculty position at Brandeis University
by Nianwen Xue 29 Sep '23

29 Sep '23

The Department of Computer Science at Brandeis University invites applications for a tenure-track assistant professor in computational linguistics, beginning Fall 2024. Qualifications required of all applicants include a Ph.D., in hand by Fall 2024, in Computer Science or a related discipline, a strong research record, and a commitment to teaching at the undergraduate and graduate levels. Particular attention will be given to candidates pursuing research in the broad area of speech, dialogue, or multimodal language processing. This position is subject to budgetary approval. The Department consists of a diverse group of 20 full-time faculty members and researchers and offers programs leading to B.A./B.S., M.S., and Ph.D. degrees in Computer Science and an M.S. in Computational Linguistics. The Department has research strengths in computational linguistics, theoretical linguistics, machine learning, computer vision, data mining, networking, distributed systems, operating systems, databases, algorithms, and software design and implementation. In addition, members of the Department collaborate closely with faculty across the university including biology, neuroscience, economics, physics, political science, among others. At Brandeis, we believe that diversity, equity, and inclusion are essential components of academic excellence. Brandeis University is an affirmative action, equal opportunity employer that is committed to creating equitable access and opportunities for applicants to all employment positions. Because diversity, equity, and inclusion are at the core of Brandeis’ history and mission, we value and are seeking candidates that represent a variety of social identities, including those that have been underrepresented in higher education, who possess skills that spark innovation, and who, through their scholarly pursuits, teaching, and/or service experiences, bring expertise in building, engaging, and sustaining a pluralistic, just, and inclusive campus community. Applicants should submit a CV, research statement, and teaching statement, and arrange for at least three reference letters to be submitted to Academic Jobs Online (AJO). Qualified applicants should apply at https://academicjobsonline.org/ajo/jobs/25467. First consideration will be given to applications received by December 20, 2023. Questions about the position can be directed to Professor James Pustejovsky . Additional information about the Department is available at https://www.brandeis.edu/computer-science/, and information about the Computational Linguistics program is available at https://www.brandeis.edu/computer-science/computational-linguistics/index.h… .

1 0

philosophyideas.com: contextual, "hierarchical"/tree-like browsing of terminology, themes, concepts ...
by Albretch Mueller 29 Sep '23

29 Sep '23

our understanding tends to find its way into our language, but there is definitely more to an idea than its paraphrasing as a one liner. Some way to browse themes based on a GUI which would enable the noticing of differing deltas and how they branch into other topics would be very useful especially when it comes to philosophy which terms (and themes) tend to be semantically overloaded. I have haven’t had the time to spend more time at your site and I have no way of knowing what criteria did you choose to parse what you consider to be ideas (did you just read philosophical terms off a dictionary and parsed them in source texts?). For example, you don't list "piety" as one of your themes, nor do you "question" as such (even though you do "argument" 8), but I don't see the one liner: “Questioning is the piety of thought” by Martin Heidegger (which original statement in the source language: „Fragen ist die Frömmigkeit des Denkens“, I would include (some translations are a bit too "explaining", my translation would be: "questioning is the way to worship thoughts" or "worship thoughts by questioning (them)")): http://www.philosophyideas.com/search/response_philosopherTe.asp?era_no=A&e… Take "techne": 11365, as a general concept with a rich and protracted history in philosophy. That concept and its constellation of ideas were one of the earliest and most crucially constitutive for the development of later sciences and technologies. Both Plato and Aristotle engaged it at length in more or less explicit ways and was the underlying structuring concept in the most important text ever written: the deductive corpus compiled by Euclid 300 BC ("Euclid’s Elements"). However, this is all you have to say about it: [filed under theme 1. Philosophy / B. History of Ideas / 3. Greek-English Lexicon ] Full Idea: Techne: skill, practical knowledge Gist of Idea: Techne: skill, practical knowledge Source: PG (Db (lexicon) [c.1001 BCE], 82) ~ lbrtchx

1 2

PR: ELDA releases air-traffic control data from ATCO2 Project
by info＠elda.org 29 Sep '23

29 Sep '23

[Apologies for multiple postings]/ / /Press Release - Immediate Paris, France, September 29, 2023/ *ELDA releases air-traffic control data from ATCO2 Project* ELDA is pleased to announce the release of ATCO2 Project Data.ATCO2 project collected the real-time voice communication between air-traffic controllers and pilots available either directly through publicly accessible radio frequency channels or indirectly from air-navigation service providers (ANSPs). In addition to the voice communication data, contextual information is available in a form of metadata (i.e. surveillance data). The dataset consists of two subsets: * a corpus of more than 4000 hours with untranscribed data * a corpus of 4 hours with transcribed data of air-traffic control speech collected across different airports (Sion, Bern, Zurich, etc.). Ca. 1 hour of annotation has followed a human re-checking. The datasetcan be found in the ELRA Catalogue of Language Resources under the following links and references: ATCO 2 Project Data <http://catalog.elra.info/en-us/repository/browse/ELRA-S0484/>, *ISLRN: *589-403-577-685-7 <http://www.islrn.org/resources/589-403-577-685-7> For more information and/or questions, please write to contact(a)elda.org <mailto:contact@elda.org>. *About ATCO2 project* ATCO2 project (Automated data collection and semi-supervised processing framework for deep learning) aims at developing a unique platform allowing to collect, organize and pre-process air-traffic control (voice communication) data from air space. It has received funding from the Clean Sky 2 Joint Undertaking (JU) under grant agreement No 864702. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and the Clean Sky 2 JU members other than the Union. The following partners collaborated on this project: IDIAP Research Institute (Switzerland), Opensky Network (Switzerland), ELDA (France), ReplayWell (Czech Republic), Romagnatech (Italy), Universität des Saarlandes (Germany), Brno University of Technology (Czech Republic). To find out more about ATCO2 project, please visit: https://www.atco2.org/ <https://www.atco2.org/> ** *About ELDA* The Evaluation and Language resources Distribution Agency (ELDA) identifies, collects, markets, and distributes language resources, along with the dissemination of general information in the field of Human Language Technologies (HLT). ELDA has considerable knowledge and skills in HLT applications. ELDA is part of major French, European and international projects in the field of HLT. To find out more about ELDA, please visit our web site: http://www.elda.org/ <http://www.elda.org/>

1 0

Eighteenth century corpora
by claire.etty＠oup.com 29 Sep '23

29 Sep '23

Hi, I'd be interested in hearing about any corpora containing eighteenth century English, beyond what's on the English Historical Book Collection (Gale Cengage’s ECCO-TCP – 2473 titles printed in the United Kingdom between the years 1701 and 1800 and Readex’s Evans-TCP – 5007 books published in America during the years 1639–1800.) Many thanks! Claire Etty Senior Editor (Research), Lexicography Oxford English Dictionary

2 1

Job - Researcher-developer for Digital Text Analysis
by Tim Van de Cruys 29 Sep '23

29 Sep '23

Researcher-developer for Digital Text Analysis KU Leuven, Belgium Deadline for applications: Monday 2 October, 2023 Within the context of the CLARIAH-VL research infrastructure project, the Centre for Computational Linguistics (CCL) seeks to hire a full-stack developer to contribute to the development of a Digital Text Analysis Dashboard and Pipeline. More information and applications: https://www.kuleuven.be/personeel/jobsite/jobs/60257605

1 0

CfP SemEval 2024 Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
by Mickus, Timothee 29 Sep '23

29 Sep '23

Welcome to SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes! Task description: SHROOM participants will need to detect grammatically sound output that contains incorrect semantic information (i.e. unsupported or inconsistent with the source input), with or without having access to the model that produced the output. Overview of the task: The modern NLG landscape is plagued by two interlinked problems: On the one hand, our current neural models have a propensity to produce inaccurate but fluent outputs; on the other hand, our metrics are most apt at describing fluency, rather than correctness. This leads neural networks to “hallucinate”, i.e., produce fluent but incorrect outputs that we currently struggle to detect automatically. For many NLG applications, the correctness of an output is, however, mission critical. For instance, producing a plausible-sounding translation that is inconsistent with the source text puts in jeopardy the usefulness of a machine translation pipeline. With our shared task, we hope to foster the growing interest in this topic in the community. With SHROOM we adopt a post hoc setting, where models have already been trained and outputs already produced: participants will be asked to perform binary classification to identify cases of fluent overgeneration hallucinations in two different tracks: a model-aware and a model-agnostic track. In the former, participants have access to the model that produced the output; in the latter, they do not. To ensure a low barrier to entry, we format the task as a binary classification problem. All systems will be rated on accuracy (i.e., the proportion of test examples correctly labeled) and calibration (i.e., the correlation between the probability assigned by a system and the proportion of annotators marking a production as hallucinatory). We provide participants with a collection of checkpoints, inputs, references and outputs of systems covering three NLG tasks: definition modeling (DM), machine translation (MT), and paraphrase generation (PG), trained with varying degrees of accuracy. The development set provides binary annotations from five different annotators and a majority vote gold label. Anyone wishing to participate in the task is welcome! Participants will have to * Submit at least once during the evaluation phase next January; * Write a system description paper; * Review other system description papers (max. 2). Trial, dev and train data are now available on the task website: https://helsinki-nlp.github.io/shroom/ Codalab competition: https://codalab.lisn.upsaclay.fr/competitions/15726 Join the mailing group: https://groups.google.com/u/1/g/semeval-2024-task-6-shroom Updates on Twitter: @shroom2024<https://twitter.com/shroom2024> Important dates: * Sample data ready: July 15th, 2023 * Validation data ready: September 11th, 2023 * Unlabeled train data ready: September 22nd, 2023 * Evaluation period starts (test set released): January 10th, 2024 * Evaluation period ends: January 31st, 2024 * Workshop paper submission deadline: February 29th, 2024 * Notification to authors: April 1st, 2024 * SemEval workshop: TBA (Summer 2024, collocated with a major NLP conference) Task organizers * Elaine Zosa, University of Helsinki, Finland * Raúl Vázquez, University of Helsinki, Finland * Jörg Tiedemann, University of Helsinki, Finland * Vincent Segonne, Universite Grenoble Alpes, France * Teemu Vahtola, University of Helsinki, Finland * Alessandro Raganato, University of Milano-Bicocca, Italy * Timothee Mickus, University of Helsinki, Finland * Marianna Apidianaki, University of Pennsylvania, USA

1 0

Jobs: PhD positions for LLM research
by Marcel Bollmann 29 Sep '23

29 Sep '23

The NLP group at Linköping University, Sweden<https://www.ida.liu.se/divisions/aiics/nlp/>, is currently looking for up to 3 PhD students for research on large language models. Specific research topics include: * modularisation techniques for multilingual pre-training * efficient fine-tuning and targeted adaptation to specific tasks * tokenisation and embedding alignment techniques * addressing grammatical correctness and bias in pre-training * benchmarking and evaluation PhD students will be supervised by Marco Kuhlmann<https://liu.se/en/employee/marku61> and Marcel Bollmann<https://marcel.bollmann.me/>. All PhD positions are full-term, salaried positions with attractive employee benefits and pension contributions. Linköping University (LiU) is an AI research excellence centre with strong and broad research and education in AI from a technical and interdisciplinary perspective. LiU is the coordinator of one of the four EU-funded networks of AI research excellence centres (TAILOR<https://tailor-network.eu/>) and the host of the largest basic research programme in Sweden (WASP<https://wasp-sweden.org/>). LiU also hosts the Swedish National Academic Infrastructure for Supercomputing in Sweden (NAISS<https://www.naiss.se/>), which includes an NVIDIA SuperPOD (Berzelius<https://www.nsc.liu.se/systems/berzelius/>). For detailed information about the positions and instructions on how to apply, please see https://www.ida.liu.se/divisions/aiics/nlp/phd-student/ Potential candidates are welcome to contact Marco or me for additional information. The application deadline is 2023-10-19. Kind regards, Marcel -- Marcel Bollmann, Dr. phil. Associate Professor in Natural Language Processing Department of Computer and Information Science, Linköping University, Sweden www: https://marcel.bollmann.me/

1 0

2026

2025

2024

2023

2022

Corpora