- Corpora - ELRA lists

Deadline extension (May 15th) SEPLN BEST 2023 THESIS AWARD
by aitziber.atucha＠ehu.eus 15 Apr '24

15 Apr '24

[Apologies for cross-posting] 23rd EDITION OF THE SEPLN AWARD TO THE BEST DOCTORAL THESIS IN NATURAL LANGUAGE PROCESSING [EXTENSION: May 15nd, 2024] The Spanish Society for Natural Language Processing announces the 23rd Edition of the SEPLN Award for the Best Doctoral Thesis in Natural Language Processing, which will be governed by the following bases: 1.- The purpose of this award is the promotion and dissemination of research in the field of natural language processing. 2.- The thesis will be awarded with a compact laptop (tablet) and €300 for attendance at the congress. The award will be presented at the 40th International Congress of the Spanish Society of Natural Language Processing (SEPLN 2024), after a brief presentation of the award-winning work by the author. 3.- In order to compete, the author of the doctoral thesis must be a member of the SEPLN at the time of submitting the work. No contestant may participate as author in more than one work. 4.- Doctoral theses read during the year 2023, written in a language of the Spanish State or in English, may be submitted to the competition. In addition to the complete thesis, it is essential to send: a) a 4-page summary of the thesis, clearly describing the topic and the relevance of the research, the objectives, methods, results achieved and contributions. b) a brief description of the scientific career of the author of the thesis, detailing the participation in scientific activities such as organization of competitive tasks, congresses, generation of open access resources such as sets of data, language models, etc., and participation in projects, contracts, and/or patents. The quality of the presentation, the technical and methodological correctness, the relevance, originality, the generation, evaluation and publication of resources, as well as the research trajectory during the pre-doctoral period will be the criteria used for the award of the prize by the jury. The works will be submitted through the website of the Society's magazine (http://journal.sepln.org) in PDF format before May 15nd 2024. The final decision will be communicated during the 40th International Congress of the Spanish Society for Natural Language Processing (SEPLN 2024). Submission instructions (http://www.sepln.org/sites/default/files/noticia/documentos_relacionados/20…) For more information aitziber.atucha(a)ehu.eus EDICIÓN XXIII PREMIO SEPLN A LA MEJOR TESIS DOCTORAL EN PROCESAMIENTO DEL LENGUAJE NATURAL [EXTENSIÓN: 15 de mayo de 2024] La Sociedad Española para el Procesamiento del Lenguaje Natural convoca la Edición XXIII del Premio SEPLN a la Mejor Tesis Doctoral en Procesamiento del Lenguaje Natural, que se regirá por las siguientes bases: 1.- La finalidad de este premio es la promoción y divulgación de la investigación en el campo del procesamiento del lenguaje natural. 2.- La tesis será premiada con una computadora portátil compacta (tablet) y 300€ para la asistencia al congreso. Se dará entrega del premio en el 40 Congreso Internacional de la Sociedad Española del Procesamiento del Lenguaje Natural (SEPLN 2024), tras una breve presentación del trabajo premiado por parte del autor. 3.- Para poder concursar, el autor de la tesis doctoral debe ser socio de la SEPLN en el momento de presentar el trabajo. Ninguna persona concursante podrá participar como autora en más de un trabajo. 4.- Se podrán presentar a concurso tesis doctorales leídas durante el año 2023, escritas en una lengua del Estado español o en lengua inglesa. Además de la tesis completa, es imprescindible enviar: a.- Un breve resumen de 4 páginas donde claramente se indique el tema y la relevancia de la investigación, los objetivos, métodos, resultados alcanzados y contribuciones. b.- Una breve descripción de la trayectoria científica del autor de la tesis, en la que se describa la participación en actividades científicas como organización de de tareas competitivas, congresos, generación de recursos open access como conjuntos de datos, modelos de lenguaje, etc, y participación en proyectos, contratos, y/o patentes. La calidad de la presentación, la corrección técnica y metodológica, la relevancia, originalidad, la generación, evaluación y publicación de recursos, así como la trayectoria investigadora durante el periodo predoctoral serán los criterios empleados para la adjudicación del premio por parte del jurado. Los trabajos se enviarán a través de la web de la revista de la Sociedad (http://journal.sepln.org) en formato PDF antes del 15 de mayo de 2024. La resolución del premio se comunicará durante el 40 Congreso Internacional de la Sociedad Española del Procesamiento del Lenguaje Natural (SEPLN 2024). Documento con las instrucciones (http://www.sepln.org/sites/default/files/noticia/documentos_relacionados/20…) Para más información dirigirse a aitziber.atucha(a)ehu.eus

1 0

11th CMC-Corpora Conference, Nice, France, 5-7 September 2024: Extension of submission deadline to 26 April
by Steven Coats 15 Apr '24

15 Apr '24

Dear colleagues, We have received many requests to extend the submission deadline for CMC-Corpora 2024 and are therefore pleased to announce an extension of the paper and abstract submission deadline to 23:59 CEST (GMT +2), April, 26th, 2024. We are also very happy to inform you that Susan Herring (Indiana University) will be our keynote speaker! For submission details, please see the conference website: https://cmc-corpora-nice.sciencesconf.org/ Looking forward to receiving your submission! On behalf of the organizing and steering committees, Céline Poudat and Steven Coats University Lecturer, Docent English, Faculty of Humanities University of Oulu P.O. Box 8000, FI-90014 University of Oulu Finland https://cc.oulu.fi/~scoats

1 0

Subject: Call for Shared Task Participation: Data Contamination Evidence Collection - CONDA workshop @ ACL 2024
by Eneko Agirre 15 Apr '24

15 Apr '24

We invite the community to participate in a shared task organized in the context of the CONDA workshop https://conda-workshop.github.io/ <https://conda-workshop.github.io/>. Data contamination, where evaluation data is inadvertently included in pre-training corpora of large scale models, and language models (LMs) in particular, has become a concern in recent times (Sainz et al. 2023 <https://aclanthology.org/2023.findings-emnlp.722/>; Jacovi et al. 2023 <https://aclanthology.org/2023.emnlp-main.308/>). The growing scale of both models and data, coupled with massive web crawling, has led to the inclusion of segments from evaluation benchmarks in the pre-training data of LMs (Dodge et al., 2021 <https://aclanthology.org/2021.emnlp-main.98/>; OpenAI, 2023 <https://arxiv.org/abs/2303.08774>; Google, 2023 <https://arxiv.org/abs/2305.10403>; Elazar et al., 2023 <https://arxiv.org/abs/2310.20707>). The scale of internet data makes it difficult to prevent this contamination from happening, or even detect when it has happened (Bommasani et al., 2022 <https://arxiv.org/abs/2108.07258>; Mitchell et al., 2023 <https://arxiv.org/abs/2212.05129>). Crucially, when evaluation data becomes part of pre-training data, it introduces biases and can artificially inflate the performance of LMs on specific tasks or benchmarks (Magar and Schwartz, 2022 <https://aclanthology.org/2022.acl-short.18/>). This poses a challenge for fair and unbiased evaluation of models, as their performance may not accurately reflect their generalization capabilities. The shared task is a community effort on centralized data contamination evidence collection. While the problem of data contamination is prevalent and serious, the breadth and depth of this contamination are still largely unknown. The concrete evidence of contamination is scattered across papers, blog posts, and social media, and it is suspected that the true scope of data contamination in NLP is significantly larger than reported. With this shared task we aim to provide a structured, centralized platform for contamination evidence collection to help the community understand the extent of the problem and to help researchers avoid repeating the same mistakes. The shared task also gathers evidence of clean, non-contaminated instances. The platform is already available for perusal at https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Database <https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Report>. Participants in the shared task need to submit their contamination evidence (see instructions below). The CONDA 2024 workshop organizers will review the evidence through pull requests. */Compilation Paper/* As a companion to the contamination evidence platform, we will produce a paper that will provide a summary and overview of the evidence collected in the shared task. The participants who contribute to the shared task will be listed as co-authors in the paper. */ /* */Instructions for Evidence Submission/* Each submission should report a case of contamination or lack of contamination thereof. The submission can be either about (1) contamination in the corpus used to pre-train language models, where the pre-training corpus contains a specific evaluation dataset, or about (2) contamination in a model that shows evidence of having seen a specific evaluation dataset while being trained. Each submission needs to mention the corpus (or model) and the evaluation dataset, in addition to some evidence of contamination. Alternatively, we also welcome evidence of a lack of contamination. Reports must be submitted through a Pull Request in the Data Contamination Report space at HuggingFace. The reports must follow the Contribution Guidelines provided in the space and will be reviewed by the organizers. If you have any questions, please contact us at conda-workshop(a)googlegroups.com <mailto:conda-workshop@googlegroups.com> or open a discussion in the space itself. URL with contribution guidelines: https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Database <https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Report> (“Contribution Guidelines” tab) */Important dates/* * Deadline for evidence submission: July 1, 2024 * Workshop day: August 16, 2024 */Sponsors/* * AWS AI and Amazon Bedrock * HuggingFace * Google */Contact/* * Website: https://conda-workshop.github.io/ <https://conda-workshop.github.io/> * Email: conda-workshop(a)googlegroups.com <mailto:conda-workshop@googlegroups.com> */Organizers/* Oscar Sainz, University of the Basque Country (UPV/EHU) Iker García Ferrero, University of the Basque Country (UPV/EHU) Eneko Agirre, University of the Basque Country (UPV/EHU) Jon Ander Campos, Cohere Alon Jacovi, Bar Ilan University Yanai Elazar, Allen Institute for Artificial Intelligence and University of Washington Yoav Goldberg, Bar Ilan University and Allen Institute for Artificial Intelligence

1 0

ArabicNLP 2024 - Third Call for Papers
by Salam Khalifa 14 Apr '24

14 Apr '24

Dear all, (Apologies for cross-posting) This is the third CFP for the second Arabic Natural Language Processing Conference (ArabicNLP 2024) Co-located with ACL 2024 in Bangkok, Thailand, August 16, 2024. (Hybrid Mode). Conference URL: https://arabicnlp2024.sigarab.org/ Upcoming deadline: May 3, 2024: Abstract of direct conference paper submissions due date (Open Review) ArabicNLP 2024 builds on eight previous conference and workshop editions, which have been very successful drawing in a large active participation in various capacities (See Scholar Page <https://scholar.google.com/citations?user=LGzh8jYAAAAJ>). This conference is timely given the continued rise in research projects focusing on Arabic NLP. The conference is organized by the Special Interest Group on Arabic NLP (SIGARAB <https://www.sigarab.org/>), an Association for Computational Linguistics Special Interest Group on Arabic NLP. Call for Papers We invite long (up to 8 pages), short (up to 4 pages), and demo paper (up to 4 pages) submissions. Long and short papers will be presented orally or as posters as determined by the program committee; presentation mode does not reflect the quality of the work. Submissions are invited on topics that include, but are not limited to, the following: - Enabling technologies: (any size) language models, diacritization, lemmatization, morphological analysis, disambiguation, tokenization, POS tagging, named entity detection, chunking, parsing, semantic role labeling, sentiment analysis, Arabic dialect modeling, etc. - Applications: dialog modeling, machine translation, speech recognition, speech synthesis, optical character recognition, pedagogy, assistive technologies, social media analytics, etc. - Resources: dictionaries, annotated data, corpora, etc. Submissions may include work in progress as well as finished work. Submissions must have a clear focus on specific issues pertaining to the Arabic language whether it is standard Arabic, dialectal, classical, or mixed. Papers on other languages sharing problems faced by Arabic NLP researchers, such as Semitic languages or languages using Arabic script, are welcome provided that they propose techniques or approaches that would be of interest to Arabic NLP, and they explain why this is the case. Additionally, papers on efforts using Arabic resources but targeting other languages are also welcome. Descriptions of commercial systems are welcome, but authors should be willing to discuss the details of their work. We also welcome position papers and surveys about any of the above topics. Conference Paper Submission URL: <https://softconf.com/emnlp2022/WANLP2022> https://openreview.net/group?id=SIGARAB.org/ArabicNLP/2024/Conference Important Dates for Conference Papers - May 3, 2024: Abstract of direct conference paper submissions due date (Open Review) - May 10, 2024: Full direct conference paper submissions due date (Open Review) - May 17, 2024: ARR commitment date <https://aclrollingreview.org/dates> - May 31, 2024: Reviews submission deadline - June 17, 2024: Notification of acceptance - July 1, 2024: Camera-ready papers due - August 16, 2024: ArabicNLP conference All deadlines are 11:59 pm UTC -12h <https://www.timeanddate.com/time/zone/timezone/utc-12> (“Anywhere on Earth”). There are eight exciting shared tasks: https://arabicnlp2024.sigarab.org/shared-tasks - Task 1: AraFinNLP: Arabic Financial NLP - Task 2: FIGNEWS 2024: Shared Task on News Media Narratives of the Israel War on Gaza - Task 3: ArAIEval: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content - Task 4: StanceEval2024: Arabic Stance Evaluation Shared Task - Task 5: WojoodNER 2024: The 2nd Arabic Named Entity Recognition Shared Task - Task 6: ArabicNLU Shared-Task: Arabic Natural Language Understanding - Task 7: NADI 2024: Nuanced Arabic Dialect Identification - Task 8: KSAA-CAD Shared Task: Contemporary Arabic Reverse Dictionary and Word Sense Disambiguation If you have any questions, please contact us at arabicnlp-pc-chairs(a)sigarab.org The ArabicNLP 2024 Organizing Committee -- Salam Khalifa PhD Student at Stony Brook Linguistics <https://www.linguistics.stonybrook.edu/>.

1 0

MSCA DTN PhD Position on NLP at MaIAGE (France) and Univ. of Szeged (Hungary)
by Claire Nedellec 14 Apr '24

14 Apr '24

Job title: Design of Information Extraction Tools to characterize molecules produced or degraded by microbes and applications to plant-fermented food ecosystems. MaIAGE-Bibliome (INRAE, University Paris-Saclay), a transdisciplinary research lab, offers a PhD position in NLP applied to biology and food science. The candidate will work within the FAIROmics doctoral network; a Marie Skłodowska-Curie Action that aims to leverage AI techniques to improve and discover knowledge about fermented food. The position is located in Jouy-en-Josas (near Paris) and includes a twelve-month secondment at the Applied AI Research Group at the University of Szeged (Hungary). Both universities will award the PhD diploma. We are looking for candidates with: - Master’s degree in Computer Science with a solid background in NLP, AI, and/or ML. Strong academic records are highly recommended. - Experience in deep learning approaches for NLP. - Programming skills in Python. - Very good English skills (both writing and speaking). - An interest in biology, bioinformatics, and food science. Application deadline: 15/05/2024 23:59 - Europe/Brussels. Application form: https://sondages.inrae.fr/index.php/342264 <https://sondages.inrae.fr/index.php/342264>(select DC9) Detailed description: https://www.dn-fairomics.eu/open-phd-positions/dc-9-phd-position <https://www.dn-fairomics.eu/open-phd-positions/dc-9-phd-position> FAIROmics Doctoral Network: https://www.dn-fairomics.eu <https://www.dn-fairomics.eu/> MaIAGE-Bibliome: https://maiage.inrae.fr/en/bibliome <https://maiage.inrae.fr/en/bibliome> Department of Software Engineering - University of Szeged: https://www.sed.inf.u-szeged.hu <https://www.sed.inf.u-szeged.hu> Feel free to contact us for any questions: Robert.Bossy(a)inrae.fr <mailto:Robert.Bossy@inrae.fr>

2 1

Call for Papers – Special issue of Information Processing & Management on Large Language Models and Data Quality for Knowledge Graphs
by Stefano Marchesin 14 Apr '24

14 Apr '24

Apologies for crossposting. Call for Papers Information Processing & Management (IPM), Elsevier - CiteScore: 14.8 - Impact Factor: 8.6 Guest editors: - Omar Alonso, Applied Science, Amazon, Palo Alto, California, USA. E-mail: omralon(a)amazon.com - Stefano Marchesin, Department of Information Engineering, University of Padua, Padua, Italy. E-mail: stefano.marchesin(a)unipd.it - Gianmaria Silvello, Department of Information Engineering, University of Padua, Padua, Italy. E-mail: gianmaria.silvello(a)unipd.it Special Issue on “Large Language Models and Data Quality for Knowledge Graphs” In recent years, Knowledge Graphs (KGs), encompassing millions of relational facts, have emerged as central assets to support virtual assistants and search and recommendations on the web. Moreover, KGs are increasingly used by large companies and organizations to organize and comprehend their data, with industry-scale KGs fusing data from various sources for downstream applications. Building KGs involves data management and artificial intelligence areas, such as data integration, cleaning, named entity recognition and disambiguation, relation extraction, and active learning. However, the methods used to build these KGs involve automated components that could be better, resulting in KGs with high sparsity and incorporating several inaccuracies and wrong facts. As a result, evaluating the KG quality plays a significant role, as it serves multiple purposes – e.g., gaining insights into the quality of data, triggering the refinement of the KG construction process, and providing valuable information to downstream applications. In this regard, the information in the KG must be correct to ensure an engaging user experience for entity-oriented services like virtual assistants. Despite its importance, there is little research on data quality and evaluation for KGs at scale. In this context, the rise of Large Language Models (LLMs) opens up unprecedented opportunities – and challenges – to advance KG construction and evaluation, providing an intriguing intersection between human and machine capabilities. On the one hand, integrating LLMs within KG construction systems could trigger the development of more context-aware and adaptive AI systems. At the same time, however, LLMs are known to hallucinate and can thus generate mis/disinformation, which can affect the quality of the resulting KG. In this sense, reliability and credibility components are of paramount importance to manage the hallucinations produced by LLMs and avoid polluting the KG. On the other hand, investigating how to combine LLMs and quality evaluation has excellent potential, as shown by promising results from using LLMs to generate relevance judgments in information retrieval. Thus, this special issue promotes novel research on human-machine collaboration for KG construction and evaluation, fostering the intersection between KGs and LLMs. To this end, we encourage submissions related to using LLMs within KG construction systems, evaluating KG quality, and applying quality control systems to empower KG and LLM interactions on both research- and industrial-oriented scenarios. Topics include but are not limited to: - KG construction systems - Use of LLMs for KG generation - Efficient solutions to deploy LLMs on large-scale KGs - Quality control systems for KG construction - KG versioning and active learning - Human-in-the-loop architectures - Efficient KG quality assessment - Quality assessment over temporal and dynamic KGs - Redundancy and completeness issues - Error detection and correction mechanisms - Benchmarks and Evaluation - Domain-specific applications and challenges - Maintenance of industry-scale KGs - LLM validation via reliable/credible KG data Submission guidelines: Authors are invited to submit original and unpublished papers. All submissions will be peer-reviewed and judged on originality, significance, quality, and relevance to the special issue topics of interest. Submitted papers should not have appeared in or be under consideration for another journal. Papers can be submitted *up *to 1 September 2024. The estimated publication date for the special issue is 15 January 2025. Papers submission via IP&M electronic submission system: https://www.editorialmanager.com/IPM To submit your manuscript to the special issue, please choose the article type: "VSI: LLMs and Data Quality for KGs". More info here: https://www.sciencedirect.com/journal/information-processing-and-management… Instructions for authors: https://www.sciencedirect.com/journal/information-processing-and-management… Important dates: - Submissions close: 1 September 2024 - Publication date (estimated): 15 January 2025 References: Weikum G., Dong X.L., Razniewski S., et al. (2021) Machine knowledge: creation and curation of comprehensive knowledge bases. Found. Trends Databases, 10, 108–490. Hogan A., Blomqvist E., Cochez M. et al. (2021) Knowledge graphs. ACM Comput. Surv., 54, 71:1–71:37. B. Xue and L. Zou. 2023. Knowledge Graph Quality Management: A Comprehensive Survey. IEEE Trans. Knowl. Data Eng. 35, 5 (2023), 4969 – 4988 G. Faggioli, L. Dietz, C. L. A. Clarke, G. Demartini, M. Hagen, C. Hauff, N. Kando, E. Kanoulas, M. Potthast, B. Stein, and H. Wachsmuth. 2023. Perspectives on Large Language Models for Relevance Judgment. In Proc. of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval, ICTIR 2023, Taipei, Taiwan, 23 July 2023. ACM, 39 – 50. S. MacAvaney and L. Soldaini. 2023. One-Shot Labeling for Automatic Relevance Estimation. In Proc. of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023. ACM, 2230 – 2235. X. L. Dong. 2023. Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact. Proc. VLDB Endow. 16, 12 (2023), 4130 – 4137. S. Pan, L. Luo, Y. Wang, C. Chen, J. Wang, and X. Wu. 2023. Unifying Large Language Models and Knowledge Graphs: A Roadmap. CoRR abs/2306.08302 (2023). -- Stefano Marchesin, PhD Assistant Professor (RTD/a) Information Management Systems (IMS) Group Department of Information Engineering University of Padua Via Gradenigo 6/a, 35131 Padua, Italy Home page: http://www.dei.unipd.it/~marches1/

1 0

CfP: Corpus Approaches to Lexicogrammar
by Costas Gabrielatos 13 Apr '24

13 Apr '24

9th Symposium on Corpus Approaches to Lexicogrammar (LxGr2024) CALL FOR PAPERS Extended deadline for abstract submission: 15 April 2024 The symposium will take place online on Friday 5 and Saturday 6 July 2024. Invited Speakers Lise Fontaine<http://www.uqtr.ca/PagePerso/Lise.Fontaine> (Université du Québec à Trois-Rivières): Reconciling (or not) lexis and grammar Ute Römer-Barron<http://alsl.gsu.edu/profile/ute-romer> (Georgia State University): Phraseology research in second language acquisition LxGr primarily welcomes papers reporting on corpus-based research on any aspect of the interaction of lexis and grammar - particularly studies that interrogate the system lexicogrammatically to get lexicogrammatical answers. However, position papers discussing theoretical or methodological issues are also welcome, as long as they are relevant to both lexicogrammar and corpus linguistics. If you would like to present, send an abstract of 500 words (excluding references) to lxgr(a)edgehill.ac.uk<mailto:lxgr@edgehill.ac.uk> Abstracts for research papers should specify the research focus (research questions or hypotheses), the corpus, the methodology (techniques, metrics), the theoretical orientation, and the main findings. Abstracts for position papers should specify the theoretical orientation and the potential contribution to both lexicogrammar and corpus linguistics. Abstracts will be double-blind reviewed by members of the Programme Committee<https://sites.edgehill.ac.uk/lxgr/committee>. Full papers will be allocated 35 minutes (including 10 minutes for discussion). Work-in-progress reports will be allocated 20 minutes (including 5 minutes for discussion). There will be no parallel sessions. Participation is free. For details, visit the LxGr website: https://sites.edgehill.ac.uk/lxgr/lxgr2024 If you have any questions, contact gabrielc(a)edgehill.ac.uk<mailto:gabrielc@edgehill.ac.uk> ________________________________ Edge Hill University<http://ehu.ac.uk/home/emailfooter> Modern University of the Year, The Times and Sunday Times Good University Guide 2022<http://ehu.ac.uk/tef/emailfooter> University of the Year, Educate North 2021/21 ________________________________ This message is private and confidential. If you have received this message in error, please notify the sender and remove it from your system. Any views or opinions presented are solely those of the author and do not necessarily represent those of Edge Hill or associated companies. Edge Hill University may monitor email traffic data and also the content of email for the purposes of security and business communications during staff absence.<http://ehu.ac.uk/itspolicies/emailfooter>

1 0

Job opening in Helsinki: University Lecturer in Humanities Data Science / Computational Humanities
by Tiedemann, Jörg 12 Apr '24

12 Apr '24

The Department of Digital Humanities, Faculty of Arts, University of Helsinki, invites applications for the position of UNIVERSITY LECTURER IN HUMANITIES DATA SCIENCE / COMPUTATIONAL HUMANITIES for a permanent appointment starting 1st of September 2024. https://jobs.helsinki.fi/job/Helsinki-University-Lecturer-in-Humanities-Dat… Due date: April 25, 2024 The position relates to the application of computational and/or statistical methods in the humanities. The application areas are to be interpreted broadly, from area studies to cognitive science, linguistics to history, phonetics to literature. Application, on the other hand, is to be understood primarily from the viewpoint of end-use across this plethora of humanistic research, e.g. through matching approaches to research questions and data, and not as a focus on methodological development itself. The lecturer will be attached to the Liberal Arts and Sciences bachelor’s programme currently under preparation at the university. —————————————— Jörg Tiedemann University of Helsinki https://blogs.helsinki.fi/language-technology/

1 0

[CFP] 2024 SIGIR First Workshop on Large Language Models (LLMs) for Evaluation in Information Retrieval
by Guglielmo Faggioli 12 Apr '24

12 Apr '24

The first workshop on evaluating IR systems with Large Language Models (LLMs) is accepting submissions that describe original research findings, preliminary research results, proposals for new work, and recent relevant studies already published in high-quality venues. Topics of interest We welcome both full papers and extended abstract submissions on the following topics, including but not limited to: - LLM-based evaluation metrics for traditional IR and generative IR. - Agreement between human and LLM labels. - Effectiveness and/or efficiency of LLMs to produce robust relevance labels. - Investigating LLM-based relevance estimators for potential systemic biases. - Automated evaluation of text generation systems. - End-to-end evaluation of Retrieval Augmented Generation systems. - Trustworthiness in the world of LLMs evaluation. - Prompt engineering in LLMs evaluation. - Effectiveness and/or efficiency of LLMs as ranking models. - LLMs in specific IR tasks such as personalized search, conversational search, and multimodal retrieval. - Challenges and future directions in LLM-based IR evaluation. Submission guidelines We welcome the following submissions: - Previously unpublished manuscripts will be accepted as extended abstracts and full papers (any length between 1 - 9 pages) with unlimited references, formatted according to the latest ACM SIG proceedings template available at http://www.acm.org/publications/proceedings-template. - Published manuscripts can be submitted in their original format. All submissions should be made through Easychair: https://easychair.org/conferences/?conf=llm4eval All papers will be peer-reviewed (single-blind) by the program committee and judged by their relevance to the workshop, especially to the main themes identified above, and their potential to generate discussion. For already published studies, the paper can be submitted in the original format. These submissions will be reviewed for their relevance to this workshop. All submissions must be in English (PDF format). All accepted papers will have a poster presentation with a few selected for spotlight talks. Accepted papers may be uploaded to arXiv.org, allowing submission elsewhere as they will be considered non-archival. The workshop’s website will maintain a link to the arXiv versions of the papers. Important Dates - Submission Deadline: April 25th, 2024 (AoE time) - Acceptance Notifications: May 31st, 2024 (AoE time) - Workshop date: July 18, 2024 Website For more information, visit the workshop website: https://llm4eval.github.io/ Contact For any questions about paper submission, you may contact the workshop organizers at llm4eval(a)easychair.org

1 0

PhD Position on Resource-efficient Foundation Models for Automatic Translation at Fondazione Bruno Kessler - Application deadline: *7th of May 2024*
by Matteo Negri 12 Apr '24

12 Apr '24

-- Apologies for cross-posting. -- Have you recently completed or expect very soon an MSc or equivalent degree in computer science, artificial intelligence, computational linguistics, engineering, or a related area? Are you interested in carrying out research on automatic translation during the next few years? Are you excited to spend a part of your life in a pleasant city in the heart of the Italian Alps? WE ARE LOOKING FOR YOU!!! The Machine Translation <https://mt.fbk.eu/> (MT) group at Fondazione Bruno Kessler (Trento, Italy) in conjunction with the ICT International Doctorate School of the University of Trento <https://iecs.unitn.it/> is pleased to announce the availability of the following fully-funded PhD position: TITLE: Resource-efficient Foundation Models for Automatic Translation DESCRIPTION: The advent of foundation models has led to impressive advancements in all areas of natural language processing. However, their huge size poses limitations due to the significant computational costs associated with their use or adaptation. When applying them to specific tasks, fundamental questions arise: do we actually need all the architectural complexity of large and - by design - general-purpose foundation models? Can we optimize them to achieve higher efficiency? These questions spark interest in research aimed at reducing models’ size, or deploying efficient decoding strategies, so as to accomplish the same tasks while maintaining or even improving performance. Success in this direction would lead to significant practical and economic benefits (e.g., lower adaptation costs, the possibility of local deployment on small-sized hardware devices), as well as advantages from an environmental impact perspective towards sustainable AI. Focusing on automatic translation, this PhD aims to understand the functioning dynamics of general-purpose massive foundation models and explore possibilities to streamline them for specific tasks. Possible areas of interest range from textual and speech translation (e.g., how to streamline a massively multilingual model to best handle a subset of languages?) to scenarios where the latency is a critical factor, such as in simultaneous/streaming translation (e.g., how to streamline the model to reduce latency?), to automatic subtitling of audiovisual content (e.g., how to streamline the model without losing its ability to generate compact outputs suitable for subtitling?). CONTACTS: Matteo Negri (negri(a)fbk.eu), Luisa Bentivogli (bentivo(a)fbk.eu) COMPLETE DETAILS AVAILABLE AT: https://iecs.unitn.it/education/admission/call-for-application IMPORTANT DATES: The deadline for application is May 7th, 2024, hrs. 04:00 PM (CEST) Prospective candidates are strongly invited to contact us in advance for preliminary interviews. Precedence for interviews will be given to short-listed candidates that will send us a complete CV via email ( negri(a)fbk.eu, bentivo(a)fbk.eu) by April 22, 2024. Candidate profile The ideal candidate must have recently completed or expect very soon an MSc or equivalent degree in computer science, artificial intelligence, computational linguistics, engineering, or a closely related area. In addition, the applicant should: - Have an interest in Machine and Speech Translation - Have experience in deep learning and machine learning, in general - Have good programming skills in Python and experience in PyTorch - Enjoy working with real-world problems and large data sets - Have good knowledge of written and spoken English - Enjoy working in a closely collaborating team Working Environment The doctoral student will be employed at the MT group at Fondazione Bruno Kessler, Trento, Italy. The group (about 10 people including staff and students) has a long tradition in research on machine and speech translation and is currently involved in several projects. Former students are nowadays employed in leading IT companies in the world. Benefits Fondazione Bruno Kessler offers an attractive benefits package, including a flexible work week, full reimbursement for conferences and summer schools, a competitive salary, an excellent team of supervisors and mentors, help with housing, full health insurance, the possibility of Italian courses, and sporting facilities. Further Information For preliminary interviews, and should you need further information about the position, please contact Matteo Negri (negri(a)fbk.eu) and Luisa Bentivogli (bentivo(a)fbk.eu). Best Regards, Matteo Negri -- -- Le informazioni contenute nella presente comunicazione sono di natura privata e come tali sono da considerarsi riservate ed indirizzate esclusivamente ai destinatari indicati e per le finalità strettamente legate al relativo contenuto. Se avete ricevuto questo messaggio per errore, vi preghiamo di eliminarlo e di inviare una comunicazione all’indirizzo e-mail del mittente. -- The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you received this in error, please contact the sender and delete the material.

1 0