- Corpora - ELRA lists

Digital lexicography and lexical computing workshop, Málaga, Spain
by Ondřej Matuška 12 Apr '24

12 Apr '24

*<Lexicom/>* a workshop in digital lexicography and lexical computing *Registration open* *Málaga, Spain*16 – 20 September 2024 Your 5 days to get up-to-date with the latest developments in *corpus-driven lexicography* and to activate and enhance your *corpus building and corpus query skills* with some of the top experts in the field. For the programme, lecturers, invited speakers, fees and registration, visit this website *lexicom.courses <https://lexicom.courses/lexicom-2024-malaga-spain-lexicography-workshop/>* I hope to meet you in Málaga in September! Ondřej *Ondřej Matuška* Brno, CZ | Brighton, UK sketchengine.eu <http://www.sketchengine.eu> | Facebook <https://www.facebook.com/SketchEngine/> | LinkedIn <https://www.linkedin.com/in/ondrejmatuska> | Twitter <https://twitter.com/SketchEngine> Become a Sketch Engine *expert*! Check our training options» <https://mailchi.mp/sketchengine/learn-with-sketch-engine>

1 0

Lectures on Computational Linguistics, June 19-21 2024, BARI (IT)
by Elisabetta Jezek 12 Apr '24

12 Apr '24

Dear Colleagues, We are pleased to announce that the 2024 edition of the *Lectures on Computational Linguistics*, a series of lectures dedicated to central topics in Computational Linguistics and Natural Language Processing, will be held in Bari from June 19 to 21. The programme and all information are available on this <https://www.ai-lc.it/en/lectures-2/lectures-2024/> site. The 2024 edition is organized by the Italian Association of Computational Linguistics/Associazione Italiana di Linguistica Computazionale (AILC) with the Department of Computer Science and the Department of Humanistic Research and Innovation of the University of Bari 'Aldo Moro'. The interdisciplinary nature of the school crosses several areas, particularly the Humanities, Computer Science and Artificial Intelligence. The program includes tutorials, labs, evening lectures, and two student presentation sessions. The 2024 edition features a four-hour tutorial dedicated to introducing Large Language Models to a broad audience. *Programme* *Wednesday, June 19, 2024* 9:00–9:30: Welcome and opening 9.30 – 11.30: Tutorial 1 (part 1) – Introduction to Large Language Models – Andrey Kutuzov, Language Technology Group, University of Oslo 11.30 – 12.00: BREAK 12:00 – 13:30: Student session 1.30pm – 3.00pm: LUNCH 3.00pm – 5.00pm: Tutorial 1 (part 2) – Introduction to Large Language Models – Andrey Kutuzov, Language Technology Group, University of Oslo 5.00pm – 5.30pm: BREAK 5.30pm – 6.30pm: Evening lecture 7.30pm: Welcome drink *Thursday, June 20, 2024* 9:00 – 11:00: Tutorial 2 – Computational methods for lexical semantic change detection – Nina Tahmasebi, University of Gothenburg 11:00 – 11:30: BREAK 11.30 – 13.30: Lab. 1 (part 1) – Hands-on Large Language Models – Marco Polignano & Lucia Siciliani, University of Bari Aldo Moro 1.30pm – 3.00pm: LUNCH 3.00pm – 5.00pm: Lab. 1 (part 2) – Hands-on Large Language Models – Marco Polignano & Lucia Siciliani, University of Bari Aldo Moro 5.00pm – 5.30pm: BREAK 5.30pm – 6.30pm: Evening lecture 7.00pm: Tour of the Old Town and dinner with typical food *Friday, June 21, 2024* 9:00 – 11:00: Tutorial 3 – Dissociating language and thought in Large Language Models – Anna Ivanova, School of Psychology, Georgia Tech 11:00 – 11:30: BREAK 11.30am – 1.00pm: Student session 1.00pm – 2.00pm: LUNCH 2.00pm – 4.00pm: Lab 2 – Lab. Computational methods for lexical semantic change detection – Pierluigi Cassotti, University of Gothenburg *Registration* The school is mainly aimed at Doctoral and Master's degree students, although a minimum qualification is not required for access. Participation is free but subject to registration, and places are limited to 200. Students wishing to present aspects of their work in the "Student Presentations" sessions are asked to send a 500-word abstract to ailc.lectures(a)gmail.com by May 10, 2024. Notifications of acceptance will be sent by May 31. Scientific Committee Pierpaolo Basile (University of Bari Aldo Moro) Raffaella Bernardi (University of Trento) Tommaso Caselli (University of Groningen) Felice Dell'Orletta (Institute of Computational Linguistics CNR – Pisa) Elisabetta Jezek (University of Pavia) Local Organizing Committee Pierpaolo Basile (Department of Computer Science, University of Bari Aldo Moro) Marco de Gemmis (Department of Computer Science, University of Bari Aldo Moro) Maristella Gatto (Department of Humanistic Research and Innovation, University of Bari Aldo Moro) Olimpia Imperio (Coordinator of the Doctorate in Letters, Languages and Arts, Department of Humanistic Research and Innovation, University of Bari Aldo Moro) Secretariat Lucia Siciliani (Department of Computer Science, University of Bari Aldo Moro) Contacts: ailc.lectures(a)gmail.com -- *Linguistica computazionale. Introduzione all'analisi automatica dei testi <https://www.mulino.it/isbn/9788815290359>.* Bologna, Il Mulino, in libreria dal 3 marzo 2023 -- [image: LOGO-UNIPV] Elisabetta Jezek Dipartimento di Studi Umanistici Professore Associato di Glottologia e Linguistica Corso Strada Nuova 65 - 27100 Pavia (Italia) <http://maps.google.com/?q=Corso+Strada+Nuova+65+27100+Pavia+%28Italia%29> T. 0382984391 https://studiumanistici.unipv.it/?pagina=docenti&id=13 <https://studiumanistici.unipv.it/?pagina=docenti&id=135>5 Elisabetta Jezek's Personal Meeting Room https://us02web.zoom.us/j/7814331810 -- 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. <http://lettere.unipv.it/diplinguistica/docenti.php> -- [image: LOGO-UNIPV] PhD ELISABETTA JEZEK Dipartimento di Studi Umanistici PROFESSORE ASSOCIATO IN LINGUISTICA E GLOTTOLOGIA Presidente del corso di laurea magistrale internazionale in European Languages, Cultures and Societies in Contact Membro del Consiglio Direttivo dell'Associazione Italiana di Linguistica Computazionale <https://firmamail.unipv.it/index.php/firme/genera> https://unipv.unifind.cineca.it/resource/person/659960 Elisabetta Jezek's Personal Meeting Room https://us02web.zoom.us/j/7814331810 -- 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. <http://lettere.unipv.it/diplinguistica/docenti.php>

1 0

2nd CfP for CMCL at ACL 2024: Workshop on Cognitive Modeling and Computational Linguistics
by Ece Takmaz 11 Apr '24

11 Apr '24

*** CMCL – 2nd Call for Papers*** The 13th edition of the Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2024) will be co-located with the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024). Webpage: https://cmclorg.github.io/ Direct submission page: https://openreview.net/group?id=aclweb.org/ACL/2024/Workshop/CMCL ARR commitment page: https://openreview.net/group?id=aclweb.org/ACL/2024/Workshop/CMCL_ARR_Commi… *Workshop Description* CMCL 2024 is a one-day workshop held in conjunction with ACL 2024. CMCL invites papers on cognitive modeling, cognitively-inspired natural language processing, and, more broadly, the alignment of language models with human cognition/perception. The 2024 workshop follows in the tradition of earlier meetings at ACL 2010, ACL 2011, NAACL-HLT 2012, ACL 2013, ACL 2014, NAACL 2015, EACL 2017, LSA 2018, NAACL 2019, EMNLP 2020, NAACL 2021, and ACL 2022. *Scope and Topics* The research interests/questions include, but are not limited to: - Human-like language acquisition/learning: How is language acquisition of language models (LMs) (dis)similar to humans, and why? - Contrasting/aligning NLP models with human behavior data: What do humans compute during language comprehension/production, and how/why? - Linguistic probing of NLP models: How well do current language models understand/represent/generalize language behaviorally/internally? - Linguistically-motivated data modeling/analysis: How can one quantify a particular aspect of language? - Emergent communication/language: What are the sufficient conditions for the emergence of language? A more formal description of the workshop scope is: - Stochastic models of factors influencing a speaker's production or comprehension decisions. - Models of semantic interpretation, including psychologically realistic notions of word and phrase meaning and composition. - Incremental parsers for diverse grammar formalisms and their psychological plausibility. - Models of speaker-specific linguistic adaptation and/or generalization. - Models of first and second language acquisition and bilingual language processing. - Behavioral tasks for better understanding neural models of linguistic representation. - Models and empirical analysis of the relationship between mechanistic psycholinguistic principles and pragmatics or semantics. - Models of lexical acquisition, including phonology, morphology, and semantics. - Psychologically motivated models of grammar induction. - Psychologically plausible models of lexical or conceptual representations. - Models of language disorders, such as aphasia, dyslexia, or dysgraphia. - Behavioral datasets or resources for modeling language processing or production in languages other than English. - Models of language comprehension difficulty. - Models of language learning and generalization. - Models of linguistic information propagation and language evolution in communities. - Cognitively-motivated models of discourse and dialogue. *Invited Speakers* Aida Nematzadeh (Google DeepMind) Frank Keller (University of Edinburgh) *Important Dates* - May 17, 2024: Paper submission/commitment deadline (cf. May 15, 2024: notification of ACL 2024) - June 17, 2024: Notification of acceptance - July 1, 2024: Camera-ready paper due - August 15, 2024: Workshop dates Deadlines are at 11:59 pm AOE. *Workshop submissions* CMCL accepts direct submissions through the OpenReview site: https://openreview.net/group?id=aclweb.org/ACL/2024/Workshop/CMCL We also receive papers already reviewed in ACL Rolling Review (ARR) February or earlier: https://openreview.net/group?id=aclweb.org/ACL/2024/Workshop/CMCL_ARR_Commi… There is no need that the CMCL is mentioned as a preferred venue in the original ARR submission. Detiailed submission flow/schedule is shown in our workshop webpage: https://cmclorg.github.io/ *Submission types* We invite three types of submissions: (1) Archival regular workshop submissions that present original research in either long (8 pages + references) or short (4 pages + references) paper format. (2) Non-archival submissions of extended abstracts that present preliminary results (from 2 to 4 pages + references). (3) Non-archival cross-submission of long/short papers that present relevant research submitted/published elsewhere (including ACL "Findings of..." papers). - Only regular workshop papers submitted via (1) will be included in the proceedings, but all types of papers will have a presentation opportunity in the workshop. - Submissions must be formatted using the ACL style template (https://github.com/acl-org/acl-style-files) and be submitted as a PDF file. - We adhere to the ACL anonymity policy: https://www.aclweb.org/adminwiki/index.php/ACL_Anonymity_Policy - This year, we don't host a shared task. *Workshop Organizers* Tatsuki Kuribayashi (MBZUAI, tatsuki.kuribayashi(a)mbzuai.ac.ae) Giulia Rambelli (University of Bologna, giulia.rambelli4(a)unibo.it) Ece Takmaz (University of Amsterdam, ece.takmaz(a)uva.nl) Philipp Wicke (Ludwig Maximilian University LMU, pwicke(a)cis.lmu.de) Yohei Oseki (University of Tokyo, oseki(a)g.ecc.u-tokyo.ac.jp) *Program Committee* Abdellah Fourtassi (Aix-Marseille University) Adina Williams (FAIR) Afra Alishahi (Tilburg University) Aniello De Santo (University of Utah) Carina Kauf (MIT) Cassandra Jacobs (University of Buffalo) Christos Christodoulopoulos (Amazon) Cory Shain (MIT) Ethan Wilcox (ETH Zurich) Frances Yung (Saarland University) Fred Mailhot (Dialpad) Gianluca Lebani (University Ca' Foscari Venezia) James Michaelov (The University of California San Diego) John Hale (University of Georgia) Laurent Prévot (Aix-Marseille University) Lisa Beinborn (VU Amsterdam) Ludovica Pannitto (University of Trento) Micha Elsner (Ohio State University) Nora Hollenstein (University of Copenhagen) Rachel Ryskin (University of California Merced) Raquel Garrido Alhama (Tilburg University) Richard Futrell (UC Irvine Language Science) Robert Frank (Yale University) Ryo Yoshida (The University of Tokyo) Samar Husain (IIT Delhi) Sandra Kuebler (Indiana University) Tal Linzen (New York University) Ted Briscoe (MBZUAI) Tiago Pimentel (ETH Zurich) Tim Hunter (UCLA) Vera Demberg (Saarland University) William Schuler (Ohio State University) Yao Yao (Hong Kong Polytechnic University) *Website* https://cmclorg.github.io/ *Sponsoring Institutions* Japan Society for the Promotion of Science *Contact* cmclorganizers2024(a)gmail.com

1 0

PhD position on AI/NLP/IR at the University of Amsterdam
by Jaap Kamps 10 Apr '24

10 Apr '24

The University of Amsterdam has a fully funded PhD position on AI/NLP/IR for information access. We seek an ambitious PhD student with a background in artificial intelligence, natural language processing and information retrieval. Your focus will be on large language models (LLMs) for information access. How can we search specific collections, including full text, metadata, and multimodal content? How can we support complex search tasks and practices, such as scholarly research on cultural data, and the research and workflow of investigative journalism? The PhD position is part of four PhD vacancies as part of digital Humanities, Artificial Intelligence, Cultural Heritage (HAICu) project, a large national science agenda project funded by the Netherlands Organization for Scientific Research. We are one of the best European and global places to study AI, and you will work together with other AI and Digital Humanities researchers, and a range of external partners on scientific breakthroughs. HAICu deploys artificial intelligence (AI) to make digital heritage collections more accessible, and the extraordinary challenges of cultural heritage provide a unique opportunity to push the boundaries of AI. The PhD position is fully funded and you will be employed by the University of Amsterdam for four years (full-time, with all employment benefits) and are expected to complete a PhD thesis within this period. Are you interested? Strong candidates with an AI/NLP/IR background are encouraged to apply by May 15. Details are in: https://vacatures.uva.nl/UvA/job/4PhDs/792167402/ (Project #1). Feel free to reach out with questions or comments! Jaap Kamps

1 0

Second CfP: The First Workshop on Data Contamination (CONDA) @ ACL 2024
by Eneko Agirre 10 Apr '24

10 Apr '24

We invite you to participate and submit your work to the First Workshop on Data Contamination (CONDA) co-located with ACL 2024 in Bangkok, Thailand. 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. 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. The scale of internet data makes it difficult to prevent this contamination from happening, or even detect when it has happened. 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. This poses a challenge for fair and unbiased evaluation of models, as their performance may not accurately reflect their generalization capabilities. Although a growing number of papers and state-of-the-art models mention issues of data contamination, there is no agreed-upon definition or standard methodology to ensure that a model does not report results on contaminated benchmarks. Addressing data contamination is a shared responsibility among researchers, developers, and the broader community. By adopting best practices, increasing transparency, documenting vulnerabilities, and conducting thorough evaluations, we can work towards minimizing the impact of data contamination and ensuring fair and reliable evaluations. We welcome paper submissions on all topics related to data contamination, including but not limited to: * Definitions, taxonomies, and gradings of contamination * Contamination detection (both manual and automatic) * Community efforts to discover, report, and organize contamination events * Documentation frameworks for datasets or models * Methods to avoid data contamination * Methods to forget contaminated data * Scaling laws and contamination * Memorization and contamination * Policies to avoid impact of contamination in publication venues and open source communities * Reproducing and attributing results from previous work to data contamination * Survey work on data contamination research * Data contamination in other modalities *Submission Instructions* We welcome two types of papers: regular workshop papers and non-archival submissions. Regular workshop papers will be included in the workshop proceedings. All submissions must be in PDF format and made through OpenReview. * Regular workshop papers: Authors can submit papers up to 8 pages, with unlimited pages for references. Authors may submit up to 100 MB of supplementary materials separately and their code for reproducibility. All submissions undergo a double-blind single-track review. Best Paper Award(s) will be given based on nomination by the reviewers. Accepted papers will be presented as posters with the possibility of oral presentations. * Non-archival submissions: Cross-submissions are welcome. Accepted papers will be presented at the workshop but not included in the workshop proceedings. Papers must be in PDF format and will be reviewed in a double-blind fashion by workshop reviewers. We also welcome extended abstracts (up to 2 pages) of papers that are work in progress, under review or to be submitted to other venues. Papers in this category need to follow the ACL format. In addition to papers submitted directly to the workshop, which will be reviewed by our Programme Committee. We also accept papers reviewed through ACL Rolling Review and committed to the workshop. Please, check the relevant dates for each type of submission. *Important dates* * Relevant deadlines to consider when submitting your paper are: * Paper submission deadline: May 17 (Friday), 2024 * ARR pre-reviewed commitment deadline: TBD, 2024 * Notification of acceptance: June 17 (Monday), 2024 * Camera-ready paper due: July 1 (Monday), 2024 * Workshop date: August 16, 2024 *Sponsors* * AWS AI and Amazon Bedrock * HuggingFace * Google *Contact* * Website: https://conda-workshop.github.io/ * Email: conda-workshop(a)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 -- Eneko Agirre HiTZ Hizkuntza Teknologiako Zentroa - Ixa Taldea Centro Vasco de Tecnología de la Lengua - Grupo Ixa Basque Center for Language Technology - Ixa NLP Group University of the Basque Country (UPV/EHU) hitz.ehu.eus/eneko <https://hitz.ehu.eus/eneko>

1 0

Postdoc opening at the University of Vienna
by Benjamin Roth 10 Apr '24

10 Apr '24

The research group Data Mining and Machine Learning at the University of Vienna is looking for a Postdoctoral Researcher in Natural Language Processing. Possible research topics are: - Analysis, explainability and interpretability of large language models - Linguistic capabilities of large language models - Extraction of structured information from text, linking knowledge graphs and language - Weak supervision of natural language processing models - Multimodal and multilingual deep learning For more details see: https://jobs.univie.ac.at/job/Postdoctoral-Researcher-in-Natural-Language-P… -- Univ.-Prof. Dr. Benjamin Roth Digitale Textwissenschaften Universität Wien Kolingasse 14 Raum 5.17 1090 Wien email: benjamin.roth(a)univie.ac.at tel: +43 14277 79513 virtual coffee (Tuesday 2pm CEST): https://www.benjaminroth.net/virtual_coffee video call: https://univienna.zoom.us/j/93796507934?pwd=VFg5dW9JbStPUml6WFVtOWJXV3phQT09 web: https://dm.cs.univie.ac.at/team/person/112089/

1 0

CALL FOR PAPERS: Conference on metaphor and political discourse, November 2024 in Liege Belgium
by Raymond Echitchi 10 Apr '24

10 Apr '24

Dear all Please, find below more information about a conference we are organising. The conference, which will take place on 21-22 November 2024 at the University of Liège (Belgium), is meant for researchers interested in metaphor and national identity discourse from different perspectives (linguistics, cognitive science, etc.). Regards, _____________ CALL FOR PAPERS METAPOL3: DISCOURSE, IDEOLOGIES AND SUB-STATE NATIONALISM 21-22 November 2024, University of Liège, Belgium Despite attempts to discourage sub-state nationalism and keep the political map of the world in its present form, the struggle for separate identities still remains a serious issue in modern-day countries. Sub-state nationalism has led to violent conflicts in postcolonial Africa, the former Yugoslavia and Soviet Union, and has been one of the main causes of political upheaval in Belgium, Britain, Spain, China, etc. As Anderson (1983) indicates, nations are imagined communities whose formation involves the spread of discourses aimed at establishing a clear difference between in-groups and out-groups. While national identity has attracted a fair amount of scholarly interest in the field of political science, it is only in the early 90s that studies emphasizing the discursive manifestations of nationalism started being conducted (Wodak & Matouschek, 1993; Wodak & Reisigl, 1999; Wodak et al. 1999). These last two decades, the study of political discourse has been consolidated by metaphor analysis (Musolff, 2006; 2016; Saric & Stanojevic, 2019), and even though great strides have indeed been made in political discourse analysis, research on sub-state nationalism remains scant. It is thus in an attempt to fill this gap that we are organizing this conference which will hopefully bring together researchers from different fields (linguistics, sociology, political science, cognitive science), interested in discourse, metaphor and nationalist ideologies. Topics of interest include, but are not limited to, - The discursive construction of (sub-state) national identity - Characteristics of separatist discourse - Conceptualisations of the body politic - Metaphor scenarios in national identity discourse - Visual metaphor in (sub-state) nationalist discourse - Gender and metaphor in (sub-state) nationalist discourse - ... KEYNOTE SPEAKER Professor Martin Reisigl, University of Vienna SUBMISSION OF PROPOSALS The conference will be held in person at the University of Liège, Belgium. Each presentation will last 20 minutes, followed by 10 minutes of Q&A. Conference proposals should include: - A title (max. 15 words) - Key words (max. 5 words) - An abstract (300 words, excluding references) Guide for submitting a proposal To submit a proposal, you must create a user account on sciencesconf.org and log in as a registered user. It is possible to create an account either directly on the SciencesConf portal or by clicking on the Login button on top right of the conference website (https://metapol3.sciencesconf.org/). Once connected, access "My submissions" and then go to New submission > Submit an abstract. Individual and co-authored papers in English or French are welcome. All abstracts will go through double-blind peer review. IMPORTANT DATES Submission deadline: 15/05/24 Notification of acceptance: 15/07/24 CONTACT AND MORE INFORMATION For more information, please visit our website (https://metapol3.sciencesconf.org/), and if necessary, do not hesitate to email us at metapol3(a)sciencesconf.org.

1 0

Vacancy: Research Fellow in Clinical Natural Language Processing
by Bea Alex 10 Apr '24

10 Apr '24

The following Research Fellow position is available as part of the Edinburgh Clinical NLP Group and the Advanced Care Research Centre at the University of Edinburgh. The deadline is 19th of April 2024. https://www.jobs.ac.uk/job/DGS698/research-fellow-in-clinical-natural-langu… ---------------------------------------------------------------- Dr. Beatrice Alex Senior Lecturer and Chancellor’s Fellow University of Edinburgh Head of the Edinburgh Language Technology Group Co-lead of the Edinburgh Clinical NLP Group The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. Is e buidheann carthannais a th’ ann an Oilthigh Dhùn Èideann, clàraichte an Alba, àireamh clàraidh SC005336.

1 0

NER Shared Task (Deadline 10 April)
by Mustafa Jarrar 09 Apr '24

09 Apr '24

Registration Deadline 10 April The 2nd Arabic Named Entity Recognition Shared Task, at ArabicNLP’24 https://dlnlp.ai/st/wojood/ Dataset: Wojood-Fine <https://aclanthology.org/2023.arabicnlp-1.25/> New version: Arabic Fine-Grained Entity Recognition (Wojood + Subtypes of entity types). Subtask-1 (Closed-Track Flat Fine-Grain NER): We provide the Wojood-Fine Flat train (70%) and development (10%) datasets. The final evaluation will be on the test set (20%). External data is not allowed .... (read more <https://dlnlp.ai/st/wojood/>). Subtask-2 (Closed-Track Nested Fine-Grain NER): This subtask is similar to the subtask-1, we provide the Wojood-Fine Nested train (70%) and development (10%) datasets. The final evaluation will be on the test set (20%) .... (read more <https://dlnlp.ai/st/wojood/>). Subtask-3 (Open-Track NER - Gaza War): to allow participants to reflect on the utility of NER in the context of real-world events, allow them to use external resources, and encourage them to use generative models in different ways (fine-tuned, zero-shot learning, in-context learning, etc.). The goal of focusing on generative models in this particular subtask is to help the Arabic NLP research community better understand the capabilities and performance gaps of LLMs in information extraction, an area currently understudied. We provide development and test data related to the current War on Gaza. This is motivated by the assumption that discourse about recent global events will involve mentions from different data distribution. For this subtask, we include data from five different news domains related to the War on Gaza - but we keep the names of the domains hidden. Participants will be given a development dataset (10K tokens, 2K from each of the five domains), and a testing dataset (50K tokens, 10K from each domain). Both development and testing sets are manually annotated with fine-grain named entities using the same annotation guidelines used in Subtask1 and Subtask2 (also described in Liqreina et al., 2023). .... (read more <https://dlnlp.ai/st/wojood/>). BASELINES Two baseline models trained on WojoodFine (flat and nested) are provided (See Liqreina et al., 2023 <https://aclanthology.org/2023.arabicnlp-1.25/>). The code used to produce these baselines is available on GitHub <https://github.com/SinaLab/ArabicNER>. Subtask Precision Recall Average Micro-F1 Flat Fine-Grain NER (Subtask 1) 0.8870 0.8966 0.8917 Nested Fine-Grain NER (Subtask 2) 0.9179 0.9279 0.9229 GOOGLE COLAB NOTEBOOKS To allow you to experiment with the baseline, we authored four Google Colab notebooks that demonstrate how to train and evaluate our baseline models. [1] Train Flat Fine-Grain NER <https://gist.github.com/mohammedkhalilia/72c3261734d7715094089bdf4de74b4a>: This notebook can be used to train our ArabicNER model on the flat Fine-grain NER task using the sample Wojood_Fine data. [2] Evaluate Flat Fine-Grain NER <https://gist.github.com/mohammedkhalilia/c807eb1ccb15416b187c32a362001665>: This notebook will use the trained model saved from the notebook above to perform evaluation on unseen dataset. [3] Train Nested Fine-Grain NER <https://gist.github.com/mohammedkhalilia/a4d83d4e43682d1efcdf299d41beb3da>: This notebook can be used to train our ArabicNER model on the nested Fine-grain task using the sample Wojood data. [4] Evaluate Nested Fine-Grain NER <https://gist.github.com/mohammedkhalilia/9134510aa2684464f57de7934c97138b>: This notebook will use the trained model saved from the notebook above to perform evaluation on unseen dataset. REGISTRATION Participants need to register via this form (NERSharedTask 2024) <https://docs.google.com/forms/d/1ISMILgQYfUug3XuDpxFmuPASXkWaduYOUc3xOZuGwq…>. Participating teams will be provided with common training development datasets. No external manually labelled datasets are allowed. Blind test data set will be used to evaluate the output of the participating teams. Each team is allowed a maximum of 3 submissions. All teams are required to report on the development and test sets (after results are announced) in their write-ups. FAQ For any questions related to this task, please check our Frequently Asked Questions <https://docs.google.com/document/d/1W_13FRpP3NbDx_ALYJWA3-ESXPRVomOjNovUuYf…> IMPORTANT DATES - February 25, 2024: Shared task announcement. - March 1, 2024: Release of training data, development sets, scoring script, and Codalab links. - April 10, 2024: Registration deadline. - April 26, 2024: Test set made available. - May 3, 2024: Codalab Test system submission deadline. - May 10, 2024: Shared task system paper submissions due. - June 17, 2024: Notification of acceptance. - July 1, 2024: Camera-ready version. - August 16, 2024: ArabicNLP 2024 conference in Thailand. CONTACT For any questions related to this task, please contact the organizers directly using the following email address: NERSharedtask(a)gmail.com <mailto:NERSharedtask@gmail.com> .

3 2

NLP postdoc position at Boston University (first deadline 4/15)
by Najoung Kim 09 Apr '24

09 Apr '24

(Re-sending due to the initial attempt bouncing, apologies in advance if you receive multiple copies!) Professor and co-principal investigator Najoung Kim <https://najoung.kim/>of the Boston University Department of Linguistics <https://ling.bu.edu/> (with active affiliations in Computer Science <https://www.bu.edu/cs/>and Data Science <https://www.bu.edu/cds-faculty/>) is seeking a Postdoctoral Associate to join the Professor's TIN Lab in Fall 2024. The successful applicant will have a background in one of the following disciplines: Artificial Intelligence, Natural Language Processing, Computational Linguistics, Cognitive Science, or other relevant areas. The postdoctoral associate will work closely with the PIs (Najoung Kim, Boston University & Sebastian Schuster, UCL) and will be responsible for co-leading a collaborative research project minimally involving two PhD-level graduate students. *Responsibilities* The postdoctoral associate’s primary responsibility is to lead a research project, the aim of which is to develop detailed evaluation protocols for AI technology applied to a consequential task of real-world complexity—specifically, AI in the domain of academic AI research—and to apply this evaluation to estimate the capacities of the current best models. We expect there to be a substantial system development component (for building the baselines) as well as a substantial human study design component (for a rigorous evaluation of the system outputs), where different expertise can be contributed by different members of the research team (minimally, two PIs, the postdoctoral associate, and two PhD-level graduate students). The postdoctoral associate is also invited to engage with the broader academic community at BU, spanning Linguistics, Computer Science, and the Center for Computing & Data Sciences, and academic communities in Boston and New England. There will also be regular opportunities to connect with the community at UCL. *Qualifications* The postdoctoral associate needs to hold a PhD degree at the start of their appointment. Hands-on experience in either: (1) building systems that use language models as a core component to solve complex tasks, or (2) leading human annotation efforts or human behavioral experiments is required. Publications or prior research experience in one of the following topic areas are desired, but not required: - Compositional generalization - Data-efficient training methods (e.g., BabyLM-scale) - Language model evaluation - General-purpose prompting techniques *Location* The postdoctoral associate will be based in Boston University. They will be physically located in one of the office spaces in 621 Commonwealth Avenue or 665 Commonwealth Avenue, subject to space availabilities. *Duration* This is a one-year position with the base expectation that it will renew for a second year, conditioned on satisfactory progress. *Compensation* The 12-month compensation for this position will be $90K-100K USD, commensurate with experience. *Application* Candidates must submit a CV, two pieces of their most significant research contribution, and contacts of two references at the time of application. We will only contact the reference writers for letters of recommendation when we decide to interview the candidate. Application materials should be uploaded as individual PDF files through Academic Jobs Online at https://academicjobsonline.org/ajo/jobs/27426. We will give full consideration to applications received by April 15, 2024: two weeks from the job posting date. Afterwards, applications will be considered on a rolling basis until the position is filled. Inquiries should be directed to najoung(a)bu.edu and s.schuster(a)ucl.ac.uk. -- Najoung Kim Assistant Professor Department of Linguistics & Computer Science, Boston University https://najoung.kim 🍪

1 0

2025

2024

2023

2022