- Corpora - ELRA lists

*Extended deadline: 30 Sept 2024* OSNEM Special Issue:AI in Online Social Networks: opportunities and challenges
by Andrea Passarella 30 Jul '24

30 Jul '24

------------------------------------------------------------------------------ CALL FOR PAPERS Elsevier Online Social Networks and Media Journal (OSNEM) Special issue on AI in Online Social Networks: opportunities and challenges ****** EXTENDED SUBMISSION DEADLINE ******** Submission Deadline: Continuous submissions September 30st, 2024 ******************************************** https://www.sciencedirect.com/journal/online-social-networks-and-media ------------------------------------------------------------------------------ Online Social Networks and Media are a fundamental component of everyday life and the use of AI technologies in OSNEM can further boost their role. The use of AI in online social networks offers great opportunities and, at the same time, raises several challenges. AI's ability to analyze vast amounts of data in real-time allows social media platforms to offer highly personalized experiences to users. The use of AI may raise concerns about ethical issues such as privacy, algorithmic bias, misinformation, etc., but AI can also be used for content moderation on social media to detect and remove harmful or inappropriate content, identifying and mitigating the spread of fake news. etc. The use of AI on OSNEM can promote the democratic processes by facilitating the dissemination of information and encourage political engagement. On the other hand, AI algorithms can create echo chambers, influence voting behavior and generate significant risks for democracy. AI-driven security measures can help to protect OSNEM users from fraud and privacy breaches but, malicious actors can also use AI to support their attacks. The exponential diffusion of generative AI adds novel dimensions to this landscape, on the one hand supporting novel forms of interactions spanning into the Metaverse, but on the other hand exposing vulnerable users to dramatic threats. The aim of this special issue is to push the state of the art in using AI in OSNEM, by presenting quantitative contributions that investigate the opportunities and challenges of using AI in Online Social Networks. Within this framework, topics include, but are not limited to: - Using AI in OSNEM for personalization, efficiency, and recommendations; - AI-based studies for analysis and modelling of information and opinion dynamics in OSNEM; - AI-based predictions based on OSNEM data analysis; - AI impact on OSNEM security, trustworthiness and privacy; - Generative AI in OSNEM; - AI and social networking in the Metaverse; - AI methodologies for large-scale OSNEM data collection and analysis - AI methods to safeguard OSNEM users (e.g., bot detection, toxic content identification, content moderation, echo chamber avoidance) - Case studies of AI application in OSNEM Online Social Networks and Media is a multidisciplinary journal for the wide community of computer and network scientists working on developing OSNEM platforms and services and using OSNEM as a big data source to mine, learn and model the (online) human behaviour. Manuscripts only based on questionnaires, even focused on the reported use of social media, are outside the scope of the journal. On the other hand, the journal welcomes papers which present analyses based on big data mined from social networks/media. ----------------------------------------------------------------------------- Schedule Manuscript submission deadline: continuous submission until September 30th, 2024 (*) First notification: two months after the submission Expected publication: papers are published a few weeks after acceptance. Guest Editors Marco Conti, IIT-CNR, Italy Andrea Passarella, IIT-CNR, Italy ------------------------------------------------------------------------------ Instructions for submission Manuscripts must not have been previously published nor currently under review by other journals or conferences. If prior work was published in a conference, the submitted manuscript should include a substantial extension of at least 35% novel contributions. In this case, authors are also required to submit their published conference articles and a summary document explaining the enhancements made in the journal version. The submission website for this journal is located at https://www2.cloud.editorialmanager.com/osnem/default2.aspx. Please select ''VSI:AI&OSNEM'' when you reach the ''Article Type'' step in the submission process. To ensure that all manuscripts are correctly identified, for consideration by the special issue, the authors should indicate in the cover letter that the manuscript has been submitted for the special issue on “AI&OSNEM”. (*) Manuscripts can be submitted continuously until the deadline. Once a paper is submitted, the review process will start immediately. Accepted papers will be published continuously in the journal (in the first issue available as soon as the paper is accepted). All accepted papers will be listed together in an online virtual special issue published in the journal website. For further information, please contact the guest editors at {m.conti,a.passarella} at iit.cnr.it

1 0

Ulysses Tesemõ: a new large corpus for Brazilian legal and governmental domain
by Ellen Souza 29 Jul '24

29 Jul '24

Ulysses Tesemõ, a large corpus specifically built for the Brazilian legal domain. The corpus consists of over 3.5 million files, totaling 30.7 GiB of raw text, collected from 159 sources encompassing judicial, legislative, academic, news, and other related data. https://doi.org/10.1007/s10579-024-09762-8 Best Regards, Ellen Souza

1 0

CFP - SIMBig 2024 in Peru - Artificial Intelligence
by Juan Antonio Lossio-Ventura 27 Jul '24

27 Jul '24

> [Apologies for cross-posting] > ========================================================================== > SECOND CALL FOR PAPERS - SIMBig 2024 > ========================================================================== > > 11th International Conference on Information Management and Big Data - SIMBig 2024 > Where: Universidad Nacional de Moquegua, Ilo, PERU > When: November 20 - 22, 2024 > Website: https://simbig.org/SIMBig2024/ > Free of Cost: no fees associated with Publication > ========================================================================== > > OVERVIEW > ---------------------------------- > > SIMBig 2024 seeks to present new methods of Artificial Intelligence (AI), Data Science, Machine Learning, Natural Language Processing, Semantic Web, and related fields, for analyzing, managing, and extracting insights and patterns from large volumes of data. > > > KEYNOTE SPEAKERS > ---------------------------------- > Aaron Courville, Université de Montréal, Canada Mona Diab, Carnegie Mellon University, USA Anna Korhonen, University of Cambridge, UK Huan Liu, Arizona State University, USA > > IMPORTANT DATES > ---------------------------------- > > August 10, 2024 --> Full papers and short papers due > September 30, 2024 --> Notification of acceptance > October 28, 2024 --> Camera-ready versions > November 20-22, 2024 --> Conference held in Moquegua, Peru > > PUBLICATION > ---------------------------------- > > All accepted papers of SIMBig 2024 (tracks including) will be published with Springer CCIS Series <https://www.springer.com/series/7899>. > > > TOPICS OF INTEREST > ---------------------------------- > > SIMBig 2024 has a broad scope. We invite contributions on theory and practice, including but not limited to the following technical areas: > > Artificial Intelligence > Big/Masive Data > Data Science > Machine Learning > Deep Learning > Natural Language Processing > Semantic Web > Data-driven Software Engineering > Healthcare Informatics > Biomedical Informatics > Data Privacy and Security > Information Retrieval > Ontologies and Knowledge Representation > Social Networks and Social Web > Information Visualization > > SPECIAL TRACKS > ---------------------------------- > > SIMBig 2024 proposes a special track in addition to the main conference: > > DISE <https://simbig.org/SIMBig2024/call-for-paper/track-on-data-driven-software-…> - Data-Driven Software Engineering > > CONTACT > ---------------------------------- > > SIMBig 2024 General Chairs > > Juan Antonio Lossio-Ventura, National Institutes of Health, USA (juan.lossio(a)nih.gov <mailto:juan.lossio@nih.gov>) > Hugo Alatrista-Salas, Léonard de Vinci Pôle Universitaire Research Center, Paris, France (hugo.alatrista_salas(a)devinci.fr <mailto:halatrista@pucp.pe>)

1 0

PhD position: Language Modeling
by Dietrich Klakow 26 Jul '24

26 Jul '24

PhD position: Language Modeling ===================== (Computer Science, Computational Linguistics, Physics, Mathematics or similar) The research group is focusing on getting a deeper understanding of how language models work and how they can be applied. Our recent achievements include a best paper award at COLING 2022 and a best theme paper award at ACL 2023. Possible more specific topics could be: * Language modeling for Speech Recognition * Language models for Chemicals and Proteins * Deep learning for highly non-linear Dynamical Systems We expect the successful candidate to make herself/himself familiar with the group for about half a year before a final decision will be made which specific topic to pursue. The ideal candidate for the position would have: 1. Excellent knowledge of LLMs, machine learning and deep learning 2. Excellent programming skills 3. Masters degree in Computer Science, Computational Linguistics, Physics, Mathematics or similar 4. Successful experiences working both independently and as part of a small team Salary: The PhD position will be 75% of full time on the German E13 scale (TV-L) which is about 3144€ per month before tax and social security contributions. The appointments will be for three years with a possible extension at 50% for a fourth year. About the department: The department of Language Science and Technology is one of the leading departments in the speech and language area in Europe. The flagship project at the moment is the CRC on Information Density and Linguistic Encoding. It also runs a significant number of European and nationally funded projects. In total, it has seven faculty and around 50 postdoctoral researchers and PhD students. The department is part of the Saarland Informatics Campus. With 900 researchers, two Max Planck institutes and the German Research Center for Artificial Intelligence, it is one of the leading locations for Informatics in Germany and Europe. How to apply: Please send us a letter of motivation, your CV, your transcripts, if available a list of publications, and the names and contact information of at least two references, as a single PDF or a link to a PDF if the file size is more than 5 MB. Please apply latest by August 18th, 2024. Contact: Applications and any further inquiries regarding our research should be directed to phd_position_fall_2024(a)lsv.uni-saarland.de

1 0

Junior Professorship : Artificial Intelligence for Rare or Low-Resource Languages
by Damien Nouvel 24 Jul '24

24 Jul '24

Inalco, (l’Institut national des langues et civilisations orientales, the National Institute of Oriental Languages and Civilizations) invites applications for a Junior Professorship in "Artificial Intelligence for Rare or Under-Resourced Languages." This is a fixed-term contract (5 years) with a reduced teaching load, after evaluation leading ultimately to tenure as a full professor. Applications must be submitted no later than September 2, 2024, 4 p.m. (Paris time, UTC+02:00) with the appointment to begin no later than December 31, 2024. Online link: https://www.inalco.fr/institut/concours-recrutement/chaire-de-professeur-ju… RESEARCH Inalco is a specialized top-level public institution of higher education and research, recognized for its contribution to the study of the world's languages, cultures and societies across a range of humanities and social sciences disciplines such as linguistics, sociology, economics, geography, history, international relations, political science, as well as literary and artistic studies. The Institute’s research and teaching activities cover a vast range of languages (over 100) and cultural areas, giving it a singular and internationally recognized academic reputation. The digitization of resources (languages, texts, documentation, cultural objects) and their analysis represent a major challenge for Inalco, both in terms of research implementation (digital humanities, access to primary data, open-source intelligence, digital fieldwork) and the promotion of languages and cultures (access to the information society for speakers of rare and under-resourced languages). Based within Inalco itself, ERTIM (Texts, Computer Science, Multilingualism Research Team, https://ertim.inalco.fr) is a research team specializing in Natural Language Processing (NLP), with a focus on multilingual data processing, multilingual NLP methodologies and language technology applications. The team uses and creates methods and tools for the analysis and processing of languages in both written and spoken datasets. Its collaborative activities focus on Digital Humanities and the description of specific languages (such as Chinese, Arabic, Vietnamese, Bambara, Burmese, Quechua and Hindi), as well as IT applications (text mining, text classification, text annotation, information extraction, etc.). ERTIM is looking for a highly experienced candidate, specialized in current NLP methods (Deep Learning, Large Language Models, Speech Processing), capable of designing and developing research for the analysis and processing of under-resourced languages. The successful candidate will be able to demonstrate how their theoretical and applied research experience will enable them to address complex issues in innovative ways, both in terms of linguistic modeling (models of under-resourced or insufficiently resourced languages) and discursive modeling (processing code-switching, creolization, language variation, language contact, etc.). The Junior Chair professorship has a prospect of tenure. In this role, the candidate must be able to conceptualize and supervise the necessary pre- and post-language modeling tasks (eg. speech processing and recognition, OCR, automatic translation. Through their expertise and associated research projects, the person recruited will also participate in discussions within the institute on the use of Artificial Intelligence in teaching and research for languages and for areal studies based on oriental language sources. More specifically, they will be involved in the development of a range of teaching tools for language teachers wishing to integrate the use of AI, and methodological tools for students and researchers unable to undertake fieldwork in person due to physical restrictions. Affiliated Research Team: ERTIM Location: Maison de la recherche de l’Inalco, 2 rue de Lille, 75007, Paris, France Research Unit Director: Damien Nouvel Telephone: +33 1 81 70 10 37 E-mail: damien.nouvel(a)inalco.fr Website: https://ertim.inalco.fr TEACHING The person recruited will teach undergraduate and postgraduate (1st and 2nd cycle) courses in Inalco's NLP training program and, more widely, as part of general training in Digital Humanities and language data processing methodology, at Master's and Doctoral levels. Students of these courses are distinctive, in that they often come from humanities and social science backgrounds, and are speakers (or learners) of languages from the Inalco sphere of reference (Asia, Africa, the Americas, Oceania, Eastern Europe). Courses will be chosen in consultation with the teaching team and according to the skills of the person recruited. They may be generic (algorithms, programming, etc.), methodological (processing and contextualization of data from digital fieldwork) or specific to the candidate's areas of expertise. The creation of new courses may also be envisaged, in line with the teaching and learning objectives of existing programs. The Inalco NLP Master’s is co-accredited with Sorbonne Nouvelle University and Paris Nanterre University. The degree comprises separate research and professional streams, leading to careers in data science, NLP development, computational linguistics, etc. The teaching load will be 64 hours in the first year, 96 hours in the second and third years, and 128 hours in the fourth and fifth years (considered “equivalent TD”, French academic standard tutorials/seminars). At the end of the contractual period, if hired as a full professor, the statutory teaching load will be 192 hours. Teaching Department: TIM Location: 2 rue de Lille (Paris) and 65 rue des Grands Moulins (Paris) Department director: Mathieu Valette E-mail: mvalette(a)inalco.fr Website: https://www.inalco.fr/textes-informatique-multilinguisme JUNIOR PROFESSORSHIP DESCRIPTION Contract for Junior Professorship: five-year fixed-term contract under public law CNU Section (if applicable) : 27, 07 Salary: French civil service index 735 (approx. 3,680€ gross per month) Keywords: Artificial Intelligence; Natural Language Processing; Under-resourced Languages; Digitization; Speech Recognition APPLICATION Applications accepted no later than September 2, 2024, 4 p.m. (Paris time, UTC+02:00) Application procedure: Registration and submission of the application dossier in PDF format via the dedicated ministerial application platform: https://galaxie.enseignementsup-recherche.gouv.fr/antares/can/index.jsp Applications must include: - Application form to be uploaded to the candidate’s profile on the Galaxie application platform (see online link) - Photo ID - Copy of PhD degree or equivalent diploma - Academic CV with full list of publications - Three outstanding publications - Presentation of research, teaching and integration proposals within the institute and the context of the Junior Chair Professorship (10 pages maximum) - Doctoral dissertation (including doctoral defense report if applicable) and summary of dissertation in English - Dissertation (“Habilitation à Diriger des Recherches”), or any other document demonstrating aptitude for doctoral supervision SELECTION CRITERIA AND INTERVIEW PROCEDURE Candidates should hold a PhD and have a well-established research record showing research activity in areas relevant to the job description (see below), such as publications in leading international journals, academic involvement in research projects, etc. The successful candidate will be able to demonstrate proficiency in one of the languages of their area of specialization, as well as the ability to teach in English. Fluency in French is not required at the time of recruitment, but the candidate is expected to have acquired a sufficient level of competence by the end of the contract, i.e. at the time of tenure. Candidates will be evaluated by a recruitment committee comprising internal and external experts. Only those candidates shortlisted by the committee will be invited to an interview based on a review of their applications. Evaluation criteria will focus on the candidate's excellence, motivation and supervisory skills; the quality and originality of their proposed research and teaching activities; their capacity to integrate their proposals within the research team and to coordinate the Chair's program activities, as well as their ability to establish collaborative networks on an international scale. Interviews may be conducted in French or English. JUNIOR PROFESSORSHIP CHAIR PROGRAM CONDITIONS Amount of associated funding: The Junior Professorship will receive a 200,000€ research grant from the French National Research Agency (ANR) for the five-year period. The Chair program may also be eligible for additional funding from other national and international partners. This may include funding for project managers, PhD students under contract, postdocs, conference participation, access to databases, equipment, subscriptions to services (algorithms or data), etc. At the end of the five-year pre-tenure period, the person recruited must have demonstrated that they qualify for the title of University Professor: have taken on collective responsibilities, supervised students and interns, supervised or co-supervised doctoral students and, lastly, participated in the academic life of the research team and the institute. A tenure commission will meet to assess the candidate's academic merit and professional aptitude, enabling them to be granted tenure in the corps of university professors. At the time of tenure, an HDR (“Habilitation à Diriger des Recherches”) will be required. Publication of at least six articles in peer-reviewed journals is expected at the end of the five-year pre-tenure period. During the pre-tenure period, collaboration is also expected on projects initiated from within Inalco, as are significant contributions in promoting the Junior Professorship Chair program (conferences, seminars, dissemination, etc.).

1 0

Last call for Birds of a Feather (BoF) sessions at ECAI 2024
by Samia Touileb 23 Jul '24

23 Jul '24

The Diversity & Inclusion (D&I) chairs are welcoming applications for Birds of a Feather (BoF) sessions at ECAI- 2024. Are you interested in having a focused discussion on a particular theme within AI or more specific research domains related to ECAI? We invite you to submit your proposals for BoF sessions where you can engage with fellow researchers, share insights, and explore collaborative opportunities. These sessions aim to create a space for networking, idea exchange, and building new collaborations. Whether you are an early-career researcher or an expert, these gatherings provide a platform to connect. We encourage collaborative thinking, and encourage you to identify during these sessions potential research partners, discuss ongoing projects, and ignite new collaborations. We expect each session to be led by one or two experienced researchers who will guide the conversation. Each session can be conducted during the pre-conference programme or at the end of the days of the main conference. Each session should take at least 2 hours. The available time slots are from 19th until the 23th (from 14h till 19h). Don’t miss out on this opportunity to connect, learn, and collaborate. Your next collaborator might be sitting right across from you! *Deadline:* - Submission form opening: Thursday, 27 June 2024 - Submission form closing: *Friday, 26 July 2024* - Notification of selection: Monday, 9 September 2024 - Deadline with the details of the session: Monday, 23 September 2024 All deadlines are at the end of the day specified, anywhere on Earth (UTC-12). If you are interested in hosting such sessions, please fill out the proposal form that you can find in our website: https://www.ecai2024.eu/calls/birds-of-a-feathers-sessions Each bird of Birds-of-a-Feather (BoF) Sessions submission should consist of a description in PDF format, with the following sections: title, abstract, keywords about the session, target audience, and agenda (with the duration) for the session. The document must be written in English, and uploaded in the chairing tool <https://chairingtool.com/conferences/BOAF24/MainTrack>. If you have any questions, please contact the diversity and inclusion chairs, Samia Touileb and Isabel Neto, at diversityinclusion-chairs(a)ecai2024.eu See you at the BoF sessions! Isabel Neto and Samia Touileb, The diversity and inclusion chairs @ECAI2024.

1 0

Call for papers: CRAC 2024: Workshop on Reference, Anaphora and Coreference at EMNLP 2024
by maciej.ogrodniczuk＠gmail.com 15 Jul '24

15 Jul '24

<https://sites.google.com/view/crac2024/> CRAC 2024, the Seventh Workshop on Computational Models of Reference, Anaphora and Coreference, will be held at EMNLP 2024 <https://2024.emnlp.org/> in Miami on November 15, 2024. About the workshop The CRAC workshop is a forum for presenting work on all aspects of computational work on anaphora resolution and annotation, including both coreference and types of anaphora such as bridging reference resolution and discourse deixis. Since 2016, the annual CRAC <https://aclanthology.org/venues/crac/> (and its predecessor, CORBON <https://aclanthology.org/venues/corbon/> ) workshop has become the main forum for researchers interested in computational modelling of reference, anaphora and coreference to discuss and publish their results. Over the years, this workshop series has been held at major NLP conferences and has successfully organised 7 shared tasks, which stimulating interest in new problems in this research area, facilitating discussion and dissemination of results on new problems/directions (e.g. multimodal reference resolution). Topics of interest We are interested in your work on any aspect of theoretical or applied computational work on anaphora/coreference resolution. Some suggested topics include: - Coreference resolution for less-researched languages - Annotation and interpretation of anaphoric relations, including relations other than identity coreference (e.g., bridging references) - Investigation of difficult cases of anaphora and their resolution - Coreference resolution in noisy data (e.g. in social media) - New applications of coreference resolution - <https://universalanaphora.github.io/UniversalAnaphora/> Universal Anaphora - CorefUD <https://ufal.mff.cuni.cz/corefud> CRAC 2024 Shared Task on Multilingual Coreference Resolution The workshop will also present the results of our Shared Task on Multilingual Coreference Resolution <https://ufal.mff.cuni.cz/corefud/crac24> , based on 17 coreference datasets for 12 languages harmonized under a common CoNLL-U scheme. Important dates - Workshop papers due: August 22, 2024 - ARR commitment date: September 16, 2024 - Notification of acceptance: September 22, 2024 - Camera-ready papers due: October 4, 2024 - Workshop date: November 15, 2024 Paper categories - Research papers (theoretical computational linguistics, empirical/data-driven approaches, paradigms/techniques/strategies, analysis papers, resources and evaluation, negative result) - Survey papers (surveys a popular or emerging area of anaphora/coreference resolution) - Position papers (presents one side of an arguable opinion about an issue) - Challenge papers (a challenge to the field in terms of setting out a goal for the next 5/10/20 years) - Demo papers (systems, tools, visualizations) - Extended abstracts (describe work in progress) Double submission We allow for double submissions. Please indicate at the time of submission which other conference or workshop your work has been submitted to. We also invite authors of papers accepted for the Findings of major conferences (e.g. ACL, NAACL, EMNLP) to present their work at the workshop. If these papers have been removed from the Findings, they may be included in the workshop proceedings without further review. Submission link You can either submit your paper to SoftConf <https://softconf.com/emnlp2024/CRAC2024/> (by the August 22 submission deadline) or commit your ARR-reviewed paper to CRAC 2024 (by the September 16 commitment deadline). If you choose to commit your ARR-reviewed paper to CRAC, the latest ARR cycle to which you need to submit your paper for review is the June 2024 cycle. All submissions must follow the *ACL formatting instructions <https://acl-org.github.io/ACLPUB/formatting.html> . An Overleaf template <https://www.overleaf.com/latex/templates/association-for-computational-ling uistics-acl-conference/jvxskxpnznfj> is also available. All other information All other information can be found on the CRAC 2024 website <https://sites.google.com/view/crac2024/> or by e-mailing the organizers <mailto:maciej.ogrodniczuk@gmail.com> . See you at CRAC 2024! Maciej Ogrodniczuk (on behalf of all the organizers: Vincent Ng, Sameer Pradhan, Anna Nedoluzhko and Massimo Poesio)

1 0

German Linguist/Annotator Position
by Katarzyna Marszałek-Kowalewska 15 Jul '24

15 Jul '24

*ANNOTATOR / KNOWLEDGE ENGINEER (STUDENT/FREELANCER)* Berlin · Remote · Part-Time · Immediately YUKKA Lab AG is looking for a German annotator/knowledge engineer to join our Data & Resources Team. *Requirements* - Student in linguistics, philology, or translation - Good understanding of language analysis, e.g. part-of-speech, morphology, syntax, semantics - Native (for native-like) fluency in German - Excellent English skills - Creativity and motivation to push product development - Technically-minded - Ability to research and collect information from a wide variety of resources - Interest in information extraction *Nice to have* - Experience with creating ontologies, knowledge bases - Knowledge of additional languages *Responsibilities* - Annotation of data with linguistic information - Development of language resources, such as lexica, gazetteers - Development of knowledge bases/ontologies *More About Us* We are a fast-growing FinTech and hiring talented engineers with a broad understanding of technology, and visionary and creative thinking for thrilling development tasks. We are unique in sentiment analysis by screening professional print and media content. Our focus is the financial market but we are enlarging our products for overall market sentiment detection. We understand the value of data. Our software analyses online and print news and derives market sentiments. We analyze sectors, indexes, and securities all over the financial markets. *Contact* Do you believe that you would be a good fit for YUKKA Lab? Great! Please send your application with a possible start date to Katarzyna Marszalek-Kowalewska (kmk(a)yukkalab.com). No recruiters, please.

1 0

Two-year postdoctoral position - An engaging discussion robot for mental health preservation
by Christophe Lohr 10 Jul '24

10 Jul '24

Hello, The Interaction Lab-STICC Department is seeking candidates to fill a 2-year postdoctoral position within a project about conversational agents for the preservation of mental health of socially isolated people. The job description is available here: "DiscoBot - An engaging discussion robot for mental health preservation" https://labsticc.fr/mediacenter/uploads/job-profile-discobot_may2024.pdf Regards, Christophe IMT Atlantique <https://www.imt-atlantique.fr> *Christophe LOHR* Enseignant Chercheur 02 29 00 14 05 Technopôle Brest-Iroise CS 83818 29238 Brest Cedex 3 Une école de l'IMT <https://www.imt.fr>

1 0

Second Call for Participation - CoLI-Dravidian@FIRE 2024: Word-level Code-Mixed Language Identification in Dravidian Languages
by Sabur B 09 Jul '24

09 Jul '24

****We apologize for multiple postings of this e-mail**** CALL FOR PARTICIPATION FIRE 2024 Task - CoLI-Dravidian: Word-level Code-Mixed Language Identification in Dravidian Languages Held as a shared task in the 16th meeting of Forum for Information Retrieval Evaluation (FIRE 2024 <http://fire.irsi.org.in/fire/2024/home>) December 12-15, 2024. DAIICT, Gandhinagar, India Website: https://sites.google.com/view/coli-dravidian-2024/datasets?authuser=0 Codalab link: https://codalab.lisn.upsaclay.fr/competitions/19357 Dear All, We are inviting researchers and students to participate in the shared task CoLI-Dravidian: Word-level Code-Mixed Language Identification in Dravidian Languages, which is held as a shared task in the 16th meeting of Forum for Information Retrieval Evaluation (FIRE 2024 <http://fire.irsi.org.in/fire/2024/home>). Language Identification (LI) involves detecting the language(s) used in a given text, which is a preliminary step for many applications such as sentiment analysis, machine translation, information retrieval, and natural language understanding. In multilingual India, especially among the youth, social media often features code-mixed text, blending local languages with English at various levels. However, this poses significant challenges for LI, particularly when languages are mixed within a single word. Dravidian languages, extensively spoken in southern India, are under-resourced despite their rich morphological structure. These languages face technological challenges, especially in script representation on digital platforms, leading users to prefer Roman or hybrid scripts for communication. This prevalent code-mixing offers vast linguistic data for research yet remains understudied. To address word-level LI challenges in code-mixed Dravidian languages, we are conducting a shared task by providing code-mixed datasets for four languages - Kannada, Tamil, Malayalam, and Tulu, to encourage the development of advanced LI models. There will be a real-time leaderboard, and the participants will be allowed to make a maximum of 10 submissions in the training phase and 5 submissions in the testing phase through CodaLab. Each team will have to select the best submission for ranking. To download the data and participate, go to: https://codalab.lisn.upsaclay.fr/competitions/19357. Best regards, The CoLI-Dravidian 2024 Organizing Committee Important dates - 14th June 2024 - open track websites and training data release - 1st July 2024– test data release - 25th July – run submission deadline - 27th July – results declared - 27th August – Working notes due - 10th September - Reviews - 30th October – Camera-ready copies of working notes NOTE: All dates mentioned here are in the AoE (Anywhere on Earth) zone. Organizing Committee - Shashirekha Hosahalli Lakshmaiah, Department of Computer Science, Mangalore University, India. - Ameeta Agrawal, Department of Computer Science, Portland State University, USA. - Fazlourrahman Balouchzahi, CIC, IPN, Mexico. - Asha Hegde, Department of Computer Science, Mangalore University, India. - Sabur Butt, IFE, Tecnologico de Monterrey, Mexico. - Sharal Coelho, Department of Computer Science, Mangalore University, India. - Kavya G, Department of Computer Science, Mangalore University, India. - Harshitha, Department of Computer Science, Mangalore University, India. - Sonith D, Department of Computer Science, Mangalore University, India. *Sabur Butt, Ph.D. *(He/Him) Institute for the Future of Education (IFE) *Tecnológico de Monterrey, Mexico* Address: Av. Eugenio Garza Sada 2501 Sur Tecnológico, 64849 Monterrey, N.L. LinkedIn <https://www.linkedin.com/in/saburb> - GitHub <https://github.com/saburbutt> - Scholar <https://scholar.google.com/citations?user=re7md-0AAAAJ&hl=en> - Website <https://saburbutt.github.io/>

1 0

2025

2024

2023

2022