- Corpora - ELRA lists

Open Positions: NLP PostDocs / PhDs at UTN and University of Mannheim
by Steffen Eger 27 May '25

27 May '25

The Natural Language Learning & Generation (NLLG) Lab at University of Technology Nuremberg (UTN) (https://nl2g.github.io/), headed by Prof. Steffen Eger, and the group of Prof. Simone Ponzetto (http://dws.informatik.uni-mannheim.de) have two fully funded PostDoc or PhD positions (up to 3 years) in Natural Language Processing (NLP). Application Deadlines: 25.06.2025, 11:59pm CET Topics: The topics of the position involve detection and analysis of social biases (e.g., relating to gender and migration status) over time (1950s-2020s) and across different languages (German, Italian, Czech, English). To do so, innovative large language model (LLM) based techniques will be leveraged. The students will perform data analysis, data preprocessing and fine-grained human and LLM-based annotation and further explore embedding based approaches to cross-lingual cross-temporal bias detection. The positions are within the DFG funded project “HistoBias”, which involves three PIs: Prof. Daniela Grunow (University of Frankfurt), Prof. Simone Ponzetto (Univ. of Mannheim), Prof. Steffen Eger (UTN). Application format: one single PDF including: * A personal statement that explains why you are well-suited for this research topic (limited to one page) * A complete, chronological, tabular curriculum vitae (CV) in English * Certificates of your university degrees (M.Sc. degree and B.Sc. degree) or other equivalent qualification * Transcript of records, diploma supplements, or overview of courses from your university degrees (M.Sc. degree and B.Sc. degree) * Master and/or dissertation thesis To apply, send an email to jobs(a)informatik.uni-mannheim.de<mailto:jobs@informatik.uni-mannheim.de> with reference number CSAI-NLP/SB-25-05 containing one PDF document with the information above. Additionally, apply here via the portal: https://jobs.utn.de/jobposting/676b07a933aad609d552175535a63c8fe645e5340 A selected number of candidates will be invited for an interview and a small coding/discussion project. Please direct all inquiries regarding scientific content to steffen.eger(a)utn.de<mailto:steffen.eger@utn.de> and ponzetto(a)uni-mannheim.de<mailto:ponzetto@uni-mannheim.de>. Further information information with requirements are available from: <https://nl2g.github.io/positions> * https://nl2g.github.io/positions --------------------------------------------- Prof. Dr. Steffen Eger Heisenberg Professor Natural Language Learning & Generation (NLLG) University of Technology Nuremberg (UTN) https://nl2g.github.io/ <https://nl2g.github.io/>https://www.utn.de/en/person/prof-dr-steffen-eger/<https://www.utn.de/person/prof-dr-steffen-eger/> https://www.utn.de/en/departments/department-engineering/nllg-lab/ <https://nl2g.github.io/> Ulmenstraße 52i 90443 Nürnberg

1 0

CFP: GlobalNLP 2025 @ RANLP – NLP for All Languages in the Era of LLMs
by Shamsuddeen Muhammad 27 May '25

27 May '25

Dear colleagues, We are pleased to announce the Call for Papers for GlobalNLP 2025, a workshop titled: “Beyond English: Natural Language Processing for All Languages in an Era of Large Language Models” 📍 11–13 September 2025 | Varna, Bulgaria 🌐 https://globalnlp2025.github.io/ 📅 In conjunction with RANLP 2025 It's time we give every language the attention it deserves—because language diversity is at the heart of global inclusivity in NLP. Brief Technical Description Natural Language Processing (NLP) has seen remarkable progress with the rise of Large Language Models (LLMs) and Generative AI, significantly advancing capabilities in text generation, machine translation, and knowledge retrieval, particularly for high-resource languages such as English, Chinese, German, Spanish, and French. However, a vast majority of the world's languages, ranging from low-resource (e.g., Indigenous, African, Indian languages), under-resourced (e.g., Irish), to medium-resource (e.g., Baltic, South Asian, and Slavic languages), still face barriers due to data scarcity, linguistic complexity, and limited computational resources. This workshop is committed to advancing NLP for all languages, from high- to low-resource, by fostering an inclusive, multidisciplinary environment that addresses the technical and linguistic needs of every language community. We welcome both technical and non-technical papers, including experimental, theoretical, and methodological contributions, as well as interdisciplinary and participatory approaches. Topics include, but are not limited to: • Data-Efficient NLP: Transfer learning, few-/zero-shot techniques to overcome data limitations • Multilingual and Cross-Lingual Models: For morphologically rich, agglutinative, and typologically diverse languages • Semantic-Based Approaches: Ontology-driven information extraction, semantic similarity, entity linking • Linked Data and Knowledge Graphs: For machine translation, retrieval, and reasoning in underrepresented languages • Practical Applications: In education, healthcare, climate action, governance, and multilingual content creation • Corpus Creation & Linguistic Tools: For building datasets, model development, and evaluation • Reusability of Linguistic Resources: For POS tagging, parsing, MT, and more • Digital Humanities & Cultural Heritage: Computational approaches for historical texts, preservation, and interdisciplinary studies Important Dates 📄 Paper submission deadline: 6 July 2025 📬 Notification of acceptance: 31 July 2025 📝 Camera-ready deadline: 30 August 2025 📦 Proceedings ready: 8 September 2025 🗓 Workshop dates: 11–13 September 2025 📍 All deadlines are 11:59 PM AoE (Anywhere on Earth) Submission Details Authors must submit original research papers via the official RANLP 2025 submission portal. All submissions should follow the RANLP formatting guidelines. Both long and short papers are welcome. Full details are available at: 🔗 https://globalnlp2025.github.io Organizing Committee Sudhansu Bala Das (University of Galway, Ireland) Pruthwik Mishra (SVNIT Surat, India) Alok Singh (University of Oxford, UK) Shamsuddeen Hassan Muhammad (Imperial College London) Asif Ekbal (IIT Jodhpur, India) Program Committee (alphabetical order) Alexander Gelbukh (Instituto Politécnico Nacional, Mexico) Bidyut Kumar Patra (IIT BHU, India) Clarence Teo (Nanyang Technological University, Singapore) Gaurish Thakkar (University of Zagreb, Croatia) Helena Moniz (Universidade de Lisboa, Portugal) Juri Opitz (University of Zurich, Switzerland) Luan Thanh Nguyen (Vietnam National University HCMC, Vietnam) Marie-Aude Lefer (UCLouvain, Belgium) Mohammed Hasanuzzaman (Queen’s University Belfast, UK) Moritz Schaeffer (Johannes Gutenberg University Mainz, Germany) Muslim Jameel Sayed (Atlantic Technological University, Ireland) Pádraic Moran (University of Galway, Ireland) Paolo Rosso (Valencia Polytechnic University, Spain) Paul Buitelaar (University of Galway, Ireland) Soumik Mandal (NYU Tandon School of Engineering, USA) Surangika Ranathunga (Massey University, New Zealand) Uthayasanker Thayasivam (University of Moratuwa, Sri Lanka) Idris Abdulmumin (DSFSI, University of Pretoria) Ibrahim Said Ahmad (Northeastern University) We look forward to your submissions and to welcoming you in Varna for a rich and impactful exchange on the future of global, inclusive NLP. 📧 For inquiries, please contact: globalnlp2025(a)gmail.com<mailto:globalnlp2025@gmail.com> Warm regards, The GlobalNLP 2025 Organizing Committee

1 0

CfP (Extended Deadline): The EPIA Track of Natural Language, Text Mining and Applications (NLP-TeMA 2025)
by Joaquim Silva 26 May '25

26 May '25

*CALL FOR PAPERS - Deadline Extension* *Important dates* *- Abstract submission deadline: May 27, 2025 (AoE) (NEW)* - Notification of paper acceptance: July 4, 2025 - Camera-ready papers: July 14, 2025 (AoE) - Conference dates: October 1-3, 2025 *Natural Language Processing, Text Mining and Applications (PLN-TEMA’25) Track of EPIA’25* PLN-TEMA’25 will be held at the 24th Portuguese Conference on Artificial Intelligence (EPIA 2025) taking place in Universidade do Algarve, Faro, Portugal, between October 1st-3rd 2025. This track is organized under the auspices of the Portuguese Association for Artificial Intelligence (APPIA). EPIA 2025 . URL https://epia2025.ualg.pt/ This announcement contains the following: [1] Track description; [2] Topics of interest; [3] Important dates; [4] Paper submission; [5] Track fees; [6] Organizing Committee; [7] Contacts. [1] *Track Description* The Track of Natural Language, Text Mining and Applications (NLP-TeMA 2025) is a forum for researchers working in Human Language Technologies, i.e. Natural Language Processing (NLP), Computational Linguistics (CL), Natural Language Engineering (NLE), Text Mining (TM), Information Retrieval (IR), and related areas. The most natural form of sharing knowledge is indeed through textual documents. Especially on the Web, a huge amount of textual information is openly published every day, on many different topics and written in natural language, thus offering new insights and many opportunities for innovative applications of Human Language Technologies. Following advances in general AI sub-fields such as NLP, Machine Learning (ML) and Deep Learning (DL), text mining is now even more valuable as tool for bridging the gap between language theories and effective use of natural language contents, for harnessing the power of semi-structured and unstructured data, and to enable important applications in real-world heterogeneous environments. Both hidden and new knowledge can be discovered by using NLP and Text Mining methods, at multiple levels and in multiple dimensions, and often with high commercial value. Authors are invited to submit their papers on any of the issues identified in section [2]. Revision of the papers will be double-blind at least by three members of the Program Committee. All accepted papers will be published by Springer in a volume of Springer’s Lecture Notes in Artificial Intelligence (LNAI) corresponding to the proceedings of the 24th EPIA Conference on Artificial Intelligence, provided that at least one author is registered in EPIA 2025 by the early registration deadline. [2] *Topics of Interest* Theories, Algorithms and Models - Language and Cognitive Modeling - Tagging, Chunking and Parsing - Morphology and Word Segmentation - Natural Language Generation - Discourse and Pragmatics - Semantics and Text Inference - Language Resources: Acquisition and Usage. Lexical Knowledge Acquisition - Entailment and Paraphrases - Entity Recognition and Word Sense Disambiguation - Natural language understanding - Language modeling - Mathematical Properties of Language - NLP for Low-Resource Languages Text Mining and NLP Applications - Text Clustering, Classification and Summarization - Sentiment Analysis and Argument Mining - Computational Social Science - Multi-Word Units - Machine Learning for NLP and Text Mining - Spatio-Temporal and Big Text Mining - Machine Translation and Cross-Lingual Approaches - Algorithms and Data Structures for Text Mining - Information Retrieval and Information Extraction - Question-Answering and Dialogue Systems - Text-Based Prediction and Forecasting - Web Content Annotation - Health/Biomedical/Legal and other Text Mining Applications - Offensive Speech Detection and Analysis [3] *Important dates* - Abstract submission deadline: May 27, 2025 (New) - Notification of paper acceptance: July 4, 2025 - Camera-ready papers: July 14, 2025 (AoE) - Conference dates: October 1-3, 2025 [4] *Paper submission* Submissions must be full technical papers on substantial, original, and previously unpublished research. Papers should be prepared according to the Springer LNAI format, using either a LaTeX or Word template, with a maximum od 12 pages, including references. EPIA 2025 will not accept any paper that, at the time of submission, is under review for, has already been published in or has already been accepted for publication in a journal or another venue with formally published proceedings. Authors of EPIA 2025 submissions are not permitted to submit their paper to a journal or another venue during the EPIA 2025 review period. It is the responsibility of the authors to remove names and affiliations from the submitted papers, and to take reasonable care to assure anonymity during the review process. Authors should also follow the standards as set out in the Springer Nature code of conduct. [5] *Track Fees:* Track participants must register at the main EPIA 2025 conference. [6] *Organizing Committee:* Joaquim Silva, DI – FCT/UNL Pablo Gamallo, CiTIUS, Universidade de Santiago de Compostela Paulo Quaresma, DI – Uviversidade de Évora Irene Rodrigues, DI – Uviversidade de Évora Alípio Jorge, Dep. Ciência de Computadores, Fac. Ciências, Universidade do Porto [7] *Contacts:* Joaquim Francisco Ferreira da Silva, DI/FCT/UNL, Quinta da Torre, 2829‐516, Caparica, Portugal. Tel: +351 21 294 8536 (ext. 10732) ‐ Fax: +351 21 294 8541 ‐ E‐mail: jfs [at]fct [dot] unl [dot] pt

1 0

CfP (Extended Deadline): The EPIA Track of Natural Language, Text Mining and Applications (NLP-TeMA 2025)
by Joaquim Silva 26 May '25

26 May '25

*CALL FOR PAPERS - Deadline Extension* *Important dates* *- Abstract submission deadline: May 27, 2025 (AoE) (NEW)* - Notification of paper acceptance: July 4, 2025 - Camera-ready papers: July 14, 2025 (AoE) - Conference dates: October 1-3, 2025 *Natural Language Processing, Text Mining and Applications (PLN-TEMA’25) Track of EPIA’25* PLN-TEMA’25 will be held at the 24th Portuguese Conference on Artificial Intelligence (EPIA 2025) taking place in Universidade do Algarve, Faro, Portugal, between October 1st-3rd 2025. This track is organized under the auspices of the Portuguese Association for Artificial Intelligence (APPIA). EPIA 2025 . URL https://epia2025.ualg.pt/ This announcement contains the following: [1] Track description; [2] Topics of interest; [3] Important dates; [4] Paper submission; [5] Track fees; [6] Organizing Committee; [7] Contacts. [1] *Track Description* The Track of Natural Language, Text Mining and Applications (NLP-TeMA 2025) is a forum for researchers working in Human Language Technologies, i.e. Natural Language Processing (NLP), Computational Linguistics (CL), Natural Language Engineering (NLE), Text Mining (TM), Information Retrieval (IR), and related areas. The most natural form of sharing knowledge is indeed through textual documents. Especially on the Web, a huge amount of textual information is openly published every day, on many different topics and written in natural language, thus offering new insights and many opportunities for innovative applications of Human Language Technologies. Following advances in general AI sub-fields such as NLP, Machine Learning (ML) and Deep Learning (DL), text mining is now even more valuable as tool for bridging the gap between language theories and effective use of natural language contents, for harnessing the power of semi-structured and unstructured data, and to enable important applications in real-world heterogeneous environments. Both hidden and new knowledge can be discovered by using NLP and Text Mining methods, at multiple levels and in multiple dimensions, and often with high commercial value. Authors are invited to submit their papers on any of the issues identified in section [2]. Revision of the papers will be double-blind at least by three members of the Program Committee. All accepted papers will be published by Springer in a volume of Springer’s Lecture Notes in Artificial Intelligence (LNAI) corresponding to the proceedings of the 24th EPIA Conference on Artificial Intelligence, provided that at least one author is registered in EPIA 2025 by the early registration deadline. [2] *Topics of Interest* Theories, Algorithms and Models - Language and Cognitive Modeling - Tagging, Chunking and Parsing - Morphology and Word Segmentation - Natural Language Generation - Discourse and Pragmatics - Semantics and Text Inference - Language Resources: Acquisition and Usage. Lexical Knowledge Acquisition - Entailment and Paraphrases - Entity Recognition and Word Sense Disambiguation - Natural language understanding - Language modeling - Mathematical Properties of Language - NLP for Low-Resource Languages Text Mining and NLP Applications - Text Clustering, Classification and Summarization - Sentiment Analysis and Argument Mining - Computational Social Science - Multi-Word Units - Machine Learning for NLP and Text Mining - Spatio-Temporal and Big Text Mining - Machine Translation and Cross-Lingual Approaches - Algorithms and Data Structures for Text Mining - Information Retrieval and Information Extraction - Question-Answering and Dialogue Systems - Text-Based Prediction and Forecasting - Web Content Annotation - Health/Biomedical/Legal and other Text Mining Applications - Offensive Speech Detection and Analysis [3] *Important dates* - Abstract submission deadline: May 23, 2025 (AoE) - Paper submission deadline: May 27, 2025 (AoE) (NEW) - Notification of paper acceptance: July 4, 2025 - Camera-ready papers: July 14, 2025 (AoE) - Conference dates: October 1-3, 2025 [4] *Paper submission* Submissions must be full technical papers on substantial, original, and previously unpublished research. Papers should be prepared according to the Springer LNAI format, using either a LaTeX or Word template, with a maximum od 12 pages, including references. EPIA 2025 will not accept any paper that, at the time of submission, is under review for, has already been published in or has already been accepted for publication in a journal or another venue with formally published proceedings. Authors of EPIA 2025 submissions are not permitted to submit their paper to a journal or another venue during the EPIA 2025 review period. It is the responsibility of the authors to remove names and affiliations from the submitted papers, and to take reasonable care to assure anonymity during the review process. Authors should also follow the standards as set out in the Springer Nature code of conduct. [5] *Track Fees:* Track participants must register at the main EPIA 2025 conference. [6] *Organizing Committee:* Joaquim Silva, DI – FCT/UNL Pablo Gamallo, CiTIUS, Universidade de Santiago de Compostela Paulo Quaresma, DI – Uviversidade de Évora Irene Rodrigues, DI – Uviversidade de Évora Alípio Jorge, Dep. Ciência de Computadores, Fac. Ciências, Universidade do Porto [7] *Contacts:* Joaquim Francisco Ferreira da Silva, DI/FCT/UNL, Quinta da Torre, 2829‐516, Caparica, Portugal. Tel: +351 21 294 8536 (ext. 10732) ‐ Fax: +351 21 294 8541 ‐ E‐mail: jfs [at]fct [dot] unl [dot] pt

1 0

VinNLP - NLP Bridges Talk Series
by El-Haj, Mo 26 May '25

26 May '25

Dear colleagues, I’m happy to introduce NLP Bridges, a talk series launched by the VinNLP Group at VinUniversity, Hanoi, to connect global NLP experts with researchers, students, and communities working on low-resource languages. All talks are free, online, and recorded, with the aim of supporting inclusive and accessible NLP research. To learn more or register for upcoming talks, please visit: https://vinnlp.com/nlp_bridges.html Best regards, Mo ————— Dr Mo El-Haj Director of the VinNLP Research Group https://vinnlp.com/ Associate Professor (Reader) in NLP CECS, VinUniversity, Hanoi, Vietnam https://vinuni.edu.vn/people/mo-el-haj/ NLP Visiting Research Scholar SCC, Lancaster University, UK https://www.lancaster.ac.uk/dsi/about-us/members/mahmoud-el-haj Natural Language Engineering (NLE) Journal Editorial Board https://www.cambridge.org/core/journals/natural-language-engineering

1 0

Autumn School 2025 - Information Retrieval and Information Foraging in Dagstuhl - Registration extended
by Thomas Mandl 25 May '25

25 May '25

Registration is extended until end of May: *ASIRF 2025 - Autumn School 2025 - Information Retrieval and Information Foraging in Dagstuhl *https://fg-retrieval.gi.de/veranstaltung/asirf2025 Great learning opportunity for grad/PhD students and everyone interested in IR, NLP or related fields! ASIRF provides a holistic perspective and shows how Information Retrieval and Information Foraging interact. In addition to conceptual and methodological knowledge from both fields, ASIRF is highly interdisciplinary. The autumn school will provide different tutorials, from foundations of Information Retrieval and Information Foraging to recent research topics such as using large language models for information retrieval tasks or applications of IR techniques in application domains. The autumn school will take place at the best computer science venue ever Schloss Dagstuhl – Leibniz-Zentrum für Informatik (LZI) between 24 and 29 August 2025. The program includes the following lectures and tutorials: - Foundations of Interactive IR (Norbert Fuhr, U Duisburg-Essen) - Deep Learning for IR (Avishek Anand, TU Delft) - Conversational Search (Ralf Schenkel, U Trier) - Fairness and Bias (Andrea Horbach, U Kiel) - Multimodal retrieval and data analysis (Henning Müller, HES-SO) - User Experiments and Interactive IR (Thomas Mandl, U Hildesheim) - Complex Casual Leisure Information Needs (Vivien Petras, HU Berlin) - User Simulations for IR (Philipp Schaer, TH Köln) For more information on the schedule, program, or registration: https://fg-retrieval.gi.de/veranstaltung/asirf2025 See you in Dagstuhl! ASIRF 2025 organizers Philipp Schaer, Ralf Schenkel, and Thomas Mandl

1 0

HASOC-meme - Shared task @ FIRE 2025 - Hateful Memes in Bengali, Hindi, Gujarati and Bodo - Registration open
by Thomas Mandl 25 May '25

25 May '25

[Apologies for multiple postings] ************************************************************************************ [CFP] HASOC-meme: Hate Speech and Offensive Content Identification in Memes in Bengali, Hindi, Gujarati and Bodo at FIRE 2025 ************************************************************************************ https://hasocfire.github.io/hasoc/2025/call_for_participation.html <https://hasocfire.github.io/hasoc/2025/call_for_participation.html> We are excited to announce the 7th edition of HASOC, featuring a range of engaging shared tasks. We warmly invite you to participate in this edition. HASOC 2025 will introduce classification tasks on memes, focusing on the identification of abuse, sentiment, sarcasm, vulgarity, and target. The task will primarily include three binary classification tasks, one multi-class classification task, and one multi-label classification task on memes in Bangla, Hindi, Gujarati, and Bodo languages. Track Description: This task involves analyzing multimodal data (image and text) to detect abuse, identify targeted communities, assess vulgarity and sarcasm, and assign sentiment labels. So, the task will be in five parts. Sentiment detection: • Positive - The meme conveys a supportive, humorous, or appreciative tone. • Neutral - The meme is neither overtly positive nor negative in tone. • Negative - The meme expresses hostility, mockery, or criticism. Sarcasm Detection: • Sarcastic - The meme presents statements or visuals that imply the opposite of their literal meaning, often to mock or ridicule. • Non-Sarcastic: The meme directly conveys its message without sarcasm or irony. Vulgarity Detection: • Vulgar - The meme contains explicit or offensive words, gestures, or depictions. • Not Vulgar - The meme does not include any such content. Abuse Detection: • Abusive - The meme includes offensive, harmful, or derogatory language, imagery, or implications targeting an individual or a group. • Non-abusive - The meme does not contain any offensive, harmful, or derogatory content. Target Community Identification: • Gender - Any reference to male, female, non-binary, or transgender identities. • Religion - Mentions or imagery related to any religious belief, deity, or practice. • Individual - Specifically mentions or portrays a particular person. • Political - Targets political ideologies, parties, politicians, or policies. • National Origin - Targets people based on their country or ethnicity. • Social Sub-groups - Groups based on socio-economic status, occupation, cultural identity, or other affiliations. • Others - Any target that does not fall into the above categories. • None - If the meme does not target any specific community, no target label is assigned. Important dates * Registration starts: 15th May, 2025 * Hindi, Marathi and Bodo Training Data Release: 17th May, 2025 * Bangla Training data release: 24th May, 2025 * Release of the test set: 15th June, 2025 * Run submission deadline: 30th June, 2025 * Announcement of results: 15 July, 2025 * Working notes due: 30th August, 2025 * Camera-ready copies of notes and overview paper: 30th September, 2025 Task organizers * Prof. Dr. Thomas Mandl :- University of Hildesheim, Germany * Prof. Dr. Utpal Garain :-Indian Statistical Institute, India * Prof. Dr. Debasis Ganguly :- University of Glasgow, United Kingdom * Prof. Dr. Sandip Modha :- University of Milano-Bicocca, Italy & LDRP-ITR, Gandhinagar, India * Prof. Dr. Animesh Mukherjee :- Indian Institute of Technology, Khargapur, India * Dr. Koyel Ghosh :- University of Hildesheim, Germany * Dr. Mithun Das :- Indian Institute of Technology, Khargapur, India * Shubhankar Barman :- BITS pilani, India * Mwnthai Narzary :- Central Institute of Technology, Kokrajhar, India * Saptarshi Saha :- Indian Statistical Institute, Kolkata, India Website: https://hasocfire.github.io/hasoc/2025/call_for_participation.html <https://hasocfire.github.io/hasoc/2025/call_for_participation.html> In case of query, please send email via hasoc(a)googlegroups.com

1 0

CFP: The 1st Workshop on Large Language Models for Cross-Temporal Research at COLM 2025
by wei.zhao＠abdn.ac.uk 25 May '25

25 May '25

We invite you to submit your ongoing, published or pre-reviewed works to our workshop on Large Language Models for Cross-Temporal Research (XTempLLMs) at COLM 2025. Our workshop website is available at https://xtempllms.github.io/2025/ Workshop Description: Large language models (LLMs) have been used for a variety of time-sensitive applications such as temporal reasoning, forecasting and planning. In addition, there has been a growing number of interdisciplinary works that use LLMs for cross-temporal research in several domains, including social science, psychology, cognitive science, environmental science and clinical studies. However, LLMs are hindered in their understanding of time due to many different reasons, including temporal biases and knowledge conflicts in pretraining and RAG data but also a fundamental limitation in LLM tokenization that fragments a date into several meaningless subtokens. Such inadequate understanding of time would lead to inaccurate reasoning, forecasting and planning, and time-sensitive findings that are potentially misleading. Our workshop looks for (i) cross-temporal work in the NLP community and (ii) interdisciplinary work that relies on LLMs for cross-temporal studies. Cross-temporal work in the NLP community: * Novel benchmarks for evaluating the temporal abilities of LLMs across diverse date and time formats, culturally grounded time systems, and generalization to future contexts; * Novel methods (e.g., neuro-symbolic approaches) for developing temporally robust, unbiased, and reliable LLMs; * Data analysis such as the distribution of pretraining data over time and conflicting knowledge in pretraining and RAG data; * Interpretability regarding how temporal information is processed from tokenization to embedding across different layers, and finally to model output; * Temporal applications such as reasoning, forecasting and planning; * Consideration of cross-lingual and cross-cultural perspectives for linguistic and cultural inclusion over time. Interdisciplinary work that relies on LLMs for cross-temporal studies: * Time-sensitive discoveries, such as social biases over time and personality testing over time; * Assessment of time-sensitive discoveries to identify misleading findings if any; * Interdisciplinary evaluation benchmarks for LLMs’ temporal abilities, e.g., psychological time perception and episodic memory evaluation. Submission Modes: * Standard submissions: We invite the submission of papers that will receive up to three double-blind reviews from the XTempLLMs committee, and a final decision of acceptance from the workshop chairs. * Pre-reviewed submissions: We invite unpublished papers that have already been reviewed either through ACL ARR, or recent AACL/EACL/ACL/EMNLP/COLING venues. These papers will not receive new reviews but will be judged together with their reviews via a meta-review from the workshop chairs. * Published papers: We invite papers that have been published recently elsewhere to present at XTempLLMs. Please send the details of your paper (Paper title, authors, publication venue, abstract, and a link to download the paper) directly to xtempllms(a)gmail.com. This allows such papers to gain more visibility from the workshop audience. All deadlines are 11.59 pm UTC -12h (“Anywhere on Earth”): * June 26, 2025: Submission deadline (standard and published papers) * July 18, 2025: Submission deadline for papers with ARR reviews * July 24, 2025: Notification of acceptance * October 10, 2025: Workshop day Invited Speakers: * Jose Camacho Collados, Cardiff University, United Kingdom * Ali Emami, Brock University, Canada * Alexis Huet, Huawei Technologies, France Organizing Committee: * Wei Zhao, University of Aberdeen, United Kingdom * Maxime Peyrard, Université Grenoble Alpes & CNRS, France * Katja Markert, Heidelberg University, Germany

1 0

Human-Computer Question Answering Competition: June 14 (in-person, DC) & June 21 (online)
by Jordan Boyd-Graber Ying 24 May '25

24 May '25

We’d like to invite you to take part in a machine learning / natural language competition with modest (~$500) prizes. We’re evaluating language models not just on their accuracy at answering questions but also on how well the models communicate their uncertainty not just quantitatively but also qualitatively. The models will be evaluated on accuracy, but this is not the primary metric. The primary metric will be how much the models help users do a better job of answering questions. In other words, a model that has 75% accuracy but is convincingly wrong on the remaining 25% of questions will fare worse than a model that has 66% accuracy but can correctly identify the remaining questions and say “I don’t know”, since the downstream humans will trust the latter model more. The human–computer games will be filmed and posted to YouTube so you can see how players reacted to your models. The system submission process is designed to be beginner-friendly and intuitive. There’s a version that is prompt-based, but also a huggingface upload for complete models. So if you’ve just wrapped up teaching an introductory NLP / AI course, we’d appreciate it if you pass this along! Full information here: https://sites.google.com/view/qanta/2025-competition Please contact qanta(a)googlegroups.com if you have any questions! Best, Jordan -- ---------------------------------------------------------- Jordan Boyd-Graber Professor University of Maryland: CS, iSchool, UMIACS, LSC Voice: 920.524.9464 jbg(a)umiacs.umd.edu http://boydgraber.org ----------------------------------------------------------

1 0

Open call for volume proposals - Phraseology and Multiword Expressions
by Lonneke van der Plas 23 May '25

23 May '25

Phraseology and Multiword Expressions (PMWE) (https://langsci-press.org/catalog/series/pmwe) is a book series at Language Science Press, a born-digital scholar-led open access publisher in linguistics. The series publishes high-quality books about conventionalized, idiosyncratic combinations of words. Within the field of phraseology such word combinations are sometimes called phrasemes, while the computational linguistics community uses the term multiword expressions for them. Various subtypes of such word combinations are of interest, such as multiword compounds, multiword terms, multiword named entities, light-verb constructions, phrasal verbs, idioms, collocations, formulaic speech, proverbs, etc. The series is open to different approaches to create a forum for an interdisciplinary and cross-framework exchange of research results, including but not limited to the following subdisciplines: - Computational linguistics and natural language processing - Computer science - Corpus linguistics - Lexicography - Psycholinguistics - Theoretical linguistics We welcome volume proposals addressing all topics related to theoretical, computational, and empirical approaches to phraseology including: - Linguistic properties and typologies of multiword expressions, especially in multilingual frameworks - Digital lexical resources including multiword expressions - Description and processing of multiword expressions in syntactic and semantic frameworks (e.g., CCG, CxG, HPSG, LFG, TAG, UD) - Identification and annotation of multiword expressions in corpora and treebanks - Multiword expressions in machine translation and other end-user applications - Multiword expressions and lexical innovation - Diachronic studies and semantic change in multiword expressions - Representation and evaluation of multiword expressions in language models (e.g., LLMs) and text generation systems All contributions should be in English. To submit a volume proposal, please follow the guidelines at the series home page: https://langsci-press.org/catalog/series/pmwe Volumes published so far: Voula Giouli, Verginica Barbu Mititelu (eds.) Multiword expressions in lexical resources: Linguistic, lexicographic, and computational perspectives. 2024. Victoria Beatrix Fendel (ed.) Support-verb constructions in the corpora of Greek: Between lexicon and grammar?. 2024. Aleksandar Trklja, Łukasz Grabowski (eds.) Formulaic language: Theories and methods. 2021 Sabine Schulte im Walde, Eva Smolka (eds.) The role of constituents in multiword expressions: An interdisciplinary, cross-lingual perspective. 2020. Yannick Parmentier, Jakub Waszczuk (eds.) Representation and parsing of multiword expressions: Current trends. 2019. Stella Markantonatou, Carlos Ramisch, Agata Savary, Veronika Vincze (eds.) Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop. 2018. Manfred Sailer, Stella Markantonatou (eds.) Multiword expressions: Insights from a multi-lingual perspective. 2018. (see https://langsci-press.org/catalog/series/pmwe for links to the volumes)

1 0

2026

2025

2024

2023

2022

Corpora