August 2024 - Corpora

Shared Task on Quality Estimation at WMT'24
by Fred Blain 22 Aug '24

22 Aug '24

Dear all, the QE shared task 2024 is ON! You can now submit and test your quality estimation system(s) on a set of different languages and tasks: to predict translation quality at sentence level, to detect error spans, or even to correct translations! For information on how to access the test data and the submission platforms, visit the shared task's webpage: https://www2.statmt.org/wmt24/qe-task.html Deadline to participate is July 31 (AoE). Looking forward to receiving your predictions! -- Best wishes, on behalf of the organisers. Dear all, we are happy to invite you to participate in the Shared Task on Quality Estimation at WMT'24. The details of the task can be found at: https://www2.statmt.org/wmt24/qe-task.html New this year: * We introduce a new language pair (zero-shot): English-Spanish * Continuing from the previous edition, we will also analyse the robustness of submitted QE systems to a set of different phenomena which will span from hallucinations and biases to localized errors, which can significantly impact real-world applications. * We also introduce a new task, seeking not only to detect but also to correct errors: Quality-aware Automatic Post-Editing! We invite participants to submit systems capable of automatically generating QE predictions for machine-translated text and the corresponding output corrections. 2024 QE Tasks: Task 1 -- Sentence-level quality estimation This task follows the same format as last year but with fresh test sets and a new language pair: English-Spanish. We will test the following language pairs: * English to German (MQM) * English to Spanish (MQM) * English to Hindi (MQM & DA) * English to Gujarati (DA) * English to Telugu (DA) * English to Tamil (DA) More details: https://www2.statmt.org/wmt24/qe-subtask1.html Task 2 -- Fine-grained error span detection Sequence labelling task: predict the error spans in each translation and the associated error severity: Major or Minor. We will test the following language pairs: * English to German (MQM) * English to Spanish (MQM) * English to Hindi (MQM) More details: https://www2.statmt.org/wmt24/qe-subtask2.html Task 3 -- Quality-aware Automatic Post-editing We expect submissions of post edits correcting detected error spans of the original translation. Although the task is focused on quality-informed APE, we also allow participants to submit APE output without QE predictions to understand the impact of their QE system. Submissions w/o QE predictions will also be considered official. We will test the following language pairs: * English to Hindi * English to Tamil More details: https://www2.statmt.org/wmt24/qe-subtask3.html Important dates: 1. Test sets will be released on July 15th. 2. Participants can submit their systems by July 23rd on codalab. 3. System paper submissions are due by 20th August [aligned with WMT deadlines]. Note: Like last year, we aligned with the General MT and Metrics shared tasks to facilitate cross-submission on the common language pairs: English-German, English-Spanish, and English-Hindi (MQM). We look forward to your submissions and feel free to contact us if you have any more questions! Best wishes, on behalf of the organisers.

2 1

First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS 2024) - Call for Participation
by Ranasinghe, Tharindu 22 Aug '24

22 Aug '24

First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS 2024) Lancaster, UK, 29-30 July 2024 Call for Participation We are pleased to share the NLPAICS 2024 conference programme, which you can view by clicking here - https://nlpaics.com/programme-2/. To register, please visit https://nlpaics.com/registration/. We very much hope to welcome you to NLPAICS 2024 at Lancaster! The conference Recent advances in Natural Language Processing (NLP), Deep Learning and Large Language Models (LLMs) have resulted in improved performance of applications. In particular, there has been a growing interest in employing AI methods in different Cyber Security applications. In today's digital world, Cyber Security has emerged as a heightened priority for both individual users and organisations. As the volume of online information grows exponentially, traditional security approaches often struggle to identify and prevent evolving security threats. The inadequacy of conventional security frameworks highlights the need for innovative solutions that can effectively navigate the complex digital landscape for ensuring robust security. NLP and AI in Cyber Security have vast potential to significantly enhance threat detection and mitigation by fostering the development of advanced security systems for autonomous identification, assessment, and response to security threats in real-time. Recognising this challenge and the capabilities of NLP and AI approaches to fortify Cyber Security systems, the First International Conference on Natural Language Processing (NLP) and Artificial Intelligence (AI) for Cyber Security (NLPAICS’2024) serves as a gathering place for researchers in NLP and AI methods for Cyber Security. We invite contributions that present the latest NLP and AI solutions for mitigating risks in processing digital information. Venue The First International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS’2024) will take place at Lancaster University and is organised by the Lancaster University UCREL NLP research group. Keynote speakers We are delighted to announce the NLPAICS’2024 keynote speakers - Iva Gumnishka (Humans in the Loop) - Sevil Şen (Hacettepe University) - Paolo Rosso (Universitat Politècnica de València) - Jacques Klein (University of Luxembourg) Sponsors We are proud to announce the conference sponsors: CodeAgent – Collaborative Agents for Software Engineering Further information and contact details The conference website is https://nlpaics.com/ and will be updated on a regular basis. The conference updates will also be available on social media (X - https://x.com/nlpaics, LinkedIn - https://linkedin.com/company/nlpaics/ ) Regards Tharindu Ranasinghe

2 1

NLP for Positive Impact Workshop EMNLP 2024: Second Call for Papers
by Daryna Dementieva 22 Aug '24

22 Aug '24

Second Call for Papers NLP for Positive Impact Workshop Miami, USA November 15 or 16, 2024 (co-located with EMNLP 2024 <https://2024.emnlp.org/>) https://sites.google.com/view/nlp4positiveimpact *Submission* Direct submission via ARR*: *link <https://openreview.net/group?id=EMNLP/2024/Workshop/NLP4PI_Direct_Submission> Deadline: August, 15th For papers submitted to June (or earlier) ARR cycle: Commitment deadline to the Workshop: August 20, 2024 Commit to the workshop: via this link <https://openreview.net/group?id=EMNLP/2024/Workshop/NLP4PI_ARR_Commitment> Notification of Acceptance: September 20, 2024 Camera-Ready Papers Due: October 3, 2024 Workshop Date: either November 15 or 16 All deadlines are 11:59 PM (Anywhere on Earth <https://www.timeanddate.com/time/zones/aoe>) *Submission Information* We are using the EMNLP Submission Guidelines <https://2024.emnlp.org/calls/main_conference_papers/#paper-submission-detai…> for the workshop. Authors are invited to submit a full paper of up to 8 pages of content with unlimited pages for references. We also invite short papers of up to 4 pages of content, including unlimited pages for references. Final camera ready versions of accepted papers will be given an additional page of content to address reviewer comments. Summary The widespread and indispensable use of language-oriented AI systems presents new opportunities to have a positive social impact. NLP technologies are starting to mature to the point where they could have an even broader impact, supporting the UN sustainability goals <https://sdgs.un.org/goals> by helping to address big problems such as poverty, hunger, healthcare, education, inequality, COVID-19 and climate change. Our workshop aims to promote innovative NLP research that will positively impact society, focusing on responsible methods and new applications. We will encourage submissions from areas including (but not limited to): - Work that grounds the impact of NLP: Beyond developing a better-performing NLP model, can we make a step further to connect the model to actual social impact? Example directions include: case studies of real-world deployments; or improving the deployment and maintenance of NLP models in practice. - In addition to commonly recognized NLP for social good areas such as NLP for healthcare, mental well-being, and many others, we also call for work on neglected areas such as NLP for poverty, hunger, energy, climate change, among others. - We also highly value work that builds on interdisciplinary expertise, and encourages submissions of case studies or worked examples that seek to expand the social impact of NLP through collaboration with other fields (e.g., philanthropy, social science, political science, economics, HCI). Special theme: This year, we would like to encourage submission providing solutions or concepts to address digital violence. Digital violence encompasses various forms of violence that utilize digital tools and media, such as cell phones, apps, internet applications, and emails, and occurs within digital spaces like online portals and social platforms. We aim to explore how modern NLP and AI technologies can contribute to enhancing safety in digital environments. At the workshop, you will have an opportunity to connect and share your results with NGO representatives from this field! Submission types: Thus, we would appreciate to see various types of works on this (but not only) topic like: - automatic identification of various social needs, their corresponding sizes and demographics of people affected; - position papers to propose promising new tasks or directions that the field should pursue; - literature review of a subfield; - philosophical discussions of what how positive impact can be achieved with NLP methods; - approaches to interdisciplinary collaboration; - user study designs, user surveys; - ethical considerations, and other related topics. Note that we want submissions to our workshop to have some distinctive features of social good implications, beyond a general paper on NLP. We will require each submission to discuss the ethical and societal implications of their work, and encourage a discussion of what "positive impact" means in the work. Organizers Zhijing Jin (Max Planck Institute & ETH Zurich) Daryna Dementieva (Technical University of Munich) Giorgio Piatti (ETH Zürich) Steven Wilson (Oakland University) Oana Ignat (Santa Clara University) Jieyu Zhao (University of Maryland, College Park) Joel Tetreault (Dataminr, Inc.) Rada Michaela (University of Michigan) Contact Email - nlp4pi.workshop(a)gmail.com

2 1

AIRiAL 2024 Conference Registration
by Voss, Erik 22 Aug '24

22 Aug '24

**Apologies for cross-posting!** Registration for Artificial Intelligence Research in Applied Linguistics (AIRiAL) 2024 Conference <https://sites.google.com/tc.columbia.edu/airialconference/airial-2024> is open. Register here <https://sites.google.com/tc.columbia.edu/airialconference/airial-2024/regis…> for the conference. Early registration ends on July 31, 2024, so don't delay! Please note that banquet seating is limited to 50 guests. Contact use for information about sponsorship opportunities. We look forward to seeing you in New York in September! Best regards, The AIRiAL 2024 Conference Organizing Committee -- Erik Voss, Ph.D. Assistant Professor, Applied Linguistics & TESOL program Language & Technology Specialization Department of Arts & Humanities Teachers College, Columbia University TC Faculty Profile <https://www.tc.columbia.edu/faculty/ev2449/>, Linkedin Profile <https://www.linkedin.com/in/erik-voss-ph-d-941a3ab9>, Google Scholar <https://scholar.google.com/citations?user=FMnVdjcAAAAJ&hl=en> ALTESOL Language & Technology Research Group <https://sites.google.com/tc.columbia.edu/al-tesol-language-technology/home> Editor-in-Chief of NYS TESOL Journal Associate Editor of Language Assessment Quarterly *Latest Publications* TC Interview: How New Artificial Intelligence Tools Will Keep Changing Education <https://youtu.be/Zh1RB7DLRMI?si=vDIvowSnzrWy480P>(7:28 mins.) Voss, E. et al. (2023). The Use of Assistive Technologies Including Generative AI by Test Takers in Language Assessment: A Debate of Theory and Practice. <https://doi.org/10.1080/15434303.2023.2288256> LAQ Journal Voss, E. (2024) Duolingo Webinar: Current Applications of Artificial Intelligence in Language Assessment <https://youtu.be/b-mjLmvXLBU?si=nmph76-lizkfzi1J> (1 hour)

2 1

The 22nd International Workshop on Treebanks and Linguistic Theories – SECOND CALL FOR PAPERS
by Zinsmeister, Heike 22 Aug '24

22 Aug '24

[With apologies for cross-posting] We are excited to announce the 22nd International Workshop on Treebanks and Linguistic Theories (TLT 2024), which will bring together developers and users of linguistically annotated natural language corpora. The workshop is endorsed by ACL SIGPARSE and will be hosted by Universität Hamburg in Germany on December 5th-6th, 2024. ----------------------------- VENUE ----------------------------- TLT 2024 will take place at the guest house of Universität Hamburg. In order to support rich discussions and networking, TLT 2024 will primarily be an in-person event; we will, however, accommodate a limited number of live / synchronous remote presentations, prioritizing those with circumstances that prevent travel. Universität Hamburg and its guest house are conveniently located near the Dammtor train station / metro station Stephansplatz which are well-connected with many parts of the city and beyond, providing an easy commute for attendees. Hamburg is a vibrant city known for its rich maritime history as one of the leading cities in the medieval Hanseatic League, as well as its modern cultural diversity, including events at the world-famous Elbphilharmonie Concert Hall. The city is easily accessible by train or plane (Hamburg Airport (HAM); about 1 to 1.5 hours train ride: Bremen Airport (BRE) and Hannover Airport (HAJ)). ----------------------------- SUBMISSION INFORMATION ----------------------------- TLT addresses all aspects of treebank design, development, and use. As ‘treebanks’ we consider any pairing of natural language data (spoken, signed, or written) with annotations of linguistic structure at various levels of analysis, including, e.g., morpho-phonology, syntax, semantics, and discourse. Annotations can take any form (including trees or general graphs), but they should be encoded in a way that enables computational processing. Reflections on the design of linguistic annotations, methodology studies, resource announcements or updates, annotation or conversion tool development, or reports on treebank usage including probing the leakage of treebanks into large language models are but some examples of the types of papers we anticipate for TLT. Papers should describe original work; they should emphasize completed work rather than intended work, and should indicate clearly the state of completion of the reported results. Submissions will be judged on correctness, originality, technical strength, significance and relevance to the conference, and interest to the attendees. We invite paper submissions in two distinct tracks: * regular papers on substantial and original research, including empirical evaluation results, where appropriate; * short papers on smaller, focused contributions, work in progress, negative results, surveys, or opinion pieces. Submissions (in both tracks) may either be archival—in case of unpublished work—or non-archival, based on the wish of the authors. All archival papers accepted for presentation at the workshop will be included in the TLT 2024 proceedings volume, which will be part of the ACL Anthology. Non-archival papers must have been published or accepted for publication at another CL conference. Long papers may consist of up to 8 pages of content (excluding references and appendices). Short papers may consist of up to 4 pages of content (excluding references and appendices). Accepted papers will be given an additional page to address reviewer comments. All submissions should follow the two-column format and the ACL style guidelines. We strongly recommend the use of the LaTeX style files, OpenDocument, or Microsoft Word templates created for ACL: https://github.com/acl-org/acl-style-files Submissions will be reviewed double-blind, and all full and short papers must be anonymous, i.e. not reveal author(s) on the title page or through self-references. So e.g., “We previously showed (Smith, 2020) …”, should be avoided. Instead, use citations such as “Smith (2020) previously showed …. Papers must be submitted digitally, in PDF, and uploaded through the on-line conference system (link forthcoming). Submissions that violate these requirements will be rejected without review. ----------------------------- IMPORTANT DATES ----------------------------- * Long and short paper submission deadlines: August 15th, 2024 * Reviews Due: September 26th, 2024 * Notification of acceptance: October 6th, 2024 * Final version of papers due: November 6th, 2024 * TLT2024: December 5th-6th, 2024 in Hamburg ----------------------------- TLT2024 WORKSHOP CHAIRS ----------------------------- Daniel Dakota, Indiana University Sandra Kübler, Indiana University Heike Zinsmeister, Universität Hamburg ----------------------------- TLT2024 COMMUNICATION CHAIR ----------------------------- Sarah Jablotschkin, Universität Hamburg Contact: tlt2024.gw(a)uni-hamburg.de Website: https://www.korpuslab.uni-hamburg.de/en/tlt2024.html --------------------------- Prof. Dr. Heike Zinsmeister (sie/ihr) Linguistik des Deutschen / Korpuslinguistik Universität Hamburg, Institut für Germanistik, Raum C7012 Von-Melle-Park 6, Postfach #15, D-20146 Hamburg Tel.: 040 42838-7119 heike.zinsmeister(a)uni-hamburg.de http://www.slm.uni-hamburg.de/germanistik/personen/zinsmeister.html

2 1

Eugene Charniak Memorial (Save the Date)
by ACL Announcements 22 Aug '24

22 Aug '24

Friday, November 8 - Saturday, November 9 Brown Computer Science Department, Providence, RI https://cs.brown.edu/people/in-memorium/eugene_charniak/ Brown University invites you to attend an academic memorial event to commemorate the research and legacy of Eugene Charniak. Eugene, an ACL Lifetime Achievement Award winner and ACL fellow, passed away in June 2023. His colleagues and students have organized a two-day workshop of invited presentations of cutting-edge research with an emphasis on the themes which defined Eugene's career: the legacy of classic statistical NLP/ML, the sometimes-surprising effectiveness of simple baselines, clever tricks for dealing with data sparsity such as self-training or distant supervision, and unsupervised learning. A full program will be posted later this summer. Mark Johnson will give a keynote presentation, along with research talks by Regina Barzilay, Michael Collins, Jason Eisner, Lillian Lee, Ani Nenkova, Ellie Pavlick, Brian Roark, Chris Tanner and Byron Wallace. There will also be opportunities to remember Eugene in a social setting, and a panel discussion of the workshop's research themes. The event will take place at the Brown Computer Science Department in Providence, RI; attendees are responsible for finding their own accommodations. Instructions for travel to Providence are available here: https://cs.brown.edu/about/directions/. The program will begin at 9am on Friday the 8th, and conclude at 1:30pm on Saturday the 9th. All members of the ACL community are welcome, whether you knew Eugene well or not. Please mark your calendars now! To stay in the loop about the event, please fill out this form: https://docs.google.com/forms/d/e/1FAIpQLSe_7LZBSjP3Ur2XCTtsDtwnL_Jbxgh5Wfi… If you have questions about the event, contact the organizers, Micha Elsner (melsner0(a)gmail.com) and David McClosky (david.mcclosky(a)gmail.com).

3 3

a postdoc in text and data mining (newspapers) at Uni Tartu
by Peeter Tinits 22 Aug '24

22 Aug '24

Hi all, I have a postdoc job to share, see below. Thank you for sharing the offer in potentially interested circles. Best, Peeter ---- Post doc job(s) available for text and data mining and social history / sustainability transitions. The project “The Crisis and Transformation of Industrial Modernity, 1900-2055”, is a five-year project at the University of Tartu. It is based on the Deep Transitions framework which theorizes industrialization as a long-term co-evolution of various socio-technical systems. Website: https://www.deeptransitions.ut.ee/. Job description: https://www.deeptransitions.ut.ee/jobs/ Job call PDF: http://tiny.cc/dt_postdoc_call_2024<http://tiny.cc/dt_postdoc_call_2024> 1,5 FTE available for jobs. Some flexibility in workload and work location based on the exact focus. Contact laur.kanger(a)ut.ee<mailto:laur.kanger@ut.ee> for more details.

2 1

ELRA Catalogue of Language Resources - Update
by info＠elda.org 22 Aug '24

22 Aug '24

2 1

COLING 2025 : [CFT] International Conference on Computational Linguistics - Last Call for Tutorials
by Sakhar AlKhereyf 22 Aug '24

22 Aug '24

** Apologies for cross-posting ** Dear Colleagues, This is the last call for tutorial proposals for COLING 2025. Due: July, 31, 2024 CFT: The 2025 International Conference on Computational Linguistics (COLING 2025) invites proposals for tutorials to be held in conjunction with the conference. We seek proposals in all areas of natural language processing and computation, language resources (LRs) and evaluation, including spoken language, sign language, and multimodal interaction. We invite proposals for three types of tutorials, and we especially encourage submissions from early-career researchers: Cutting-edge: tutorials that cover advances in newly emerging areas. The tutorials are expected to give a brief introduction to the topic, but participants are assumed to have some prior knowledge of the topic. The focus of the class will be on discussing the most recent developments in the field, and it will spend a considerable amount of time pointing out open research questions and important novel research directions. Introductory to computational linguistics/NLP topics: tutorials that provide introductions to topics that are established in the COLING communities. The lecturers provide an overview of the development of the field from the beginning until now. Attendees are not expected to come with prior knowledge. They acquire sufficient understanding of the topic to understand the most recent research in the field. Introduction to Key Concepts in Linguistics including Semantics, Syntax, Psycholinguistics, Neurolinguistics, and Sociolinguistics: tutorials that provide introductions to topics that are established or emerging in areas adjacent to CL/NLP. The lecturers provide an overview of the development of the field from the beginning until now. Attendees are not expected to come with prior knowledge. They acquire a sufficient understanding of the topic to understand the most recent research in the field and the relevance for the CL/NLP domains. Each of these types of tutorials can either be half-day (4h long including a coffee break (30m long)) or full-day (8h long including two coffee breaks (1h long in total) but excluding a lunch break). In all cases, the aim of a tutorial is primarily to help understand a scientific problem, its tractability, and its theoretical and practical implications. Presentations of particular technological solutions or systems are welcome, provided that they serve as illustrations of broader scientific considerations. None of the tutorial types are expected to be “self-invited” long talks – the content should be a good balance between research from multiple groups and perspectives, not only fromof the teachers of the tutorial. The tutorials will be held at COLING 2025 in Abu Dhabi, UAE, on 19 and 20 January, 2025. Important Dates All deadlines are 11:59PM UTC-12:00 (“anywhere on Earth”). Proposal submission due July 31, 2024 Notification of acceptance August 31, 2024 COLIING2025 tutorials January 19-20, 2025 COLING2025 conference January 21-24, 2025 Diversity and Inclusion We particularly encourage submissions of underrepresented groups in computational linguistics, researchers from any demographic or geographic minority, with disabilities, or others. In the evaluation of the proposal, we will take these aspects into account to create a varied and balanced set of tutorials. This includes several aspects of diversity, namely (1) how the topic of the tutorial contributes to improved diversity and increased fairness in the field, (2) if the topic is particularly relevant for a specific underrepresented group of potential participants, (3), if the presenters are from an underrepresented group. Submission Details They should contain: A title that helps the potential attendees to understand what the tutorial will be about. An abstract that summarizes the topics, goals, target audience, and type (see above) of the tutorial (this abstract will also be on the LREC-COLING website). A section called “Introduction” that explains the topic and summarizes the starting point and relevance for our community and in general. A section called “Target Audience” that explains for whom the tutorial will be developed and what the expected prior knowledge is. Clearly specify what attendees should know and be able to practically do to get the most out of your tutorial. Examples of what to specify include prior mathematical knowledge, knowledge of specific modeling approaches and methods, programming skills, or adjacent areas like computer vision. Also specify the number of expected participants. A section called “Outline” in which the various topics are explained. This can be a list of bullet points or a set of paragraphs explaining the content. Explain what you intend and how long the tutorial will be. A section called “Diversity Considerations”, discussing each of the three aspects of diversity mentioned above or others. A section called “Reading List”: What are introductory papers or books that potential attendees can read to get a first impression of the tutorial content? What do you expect them to have read before attending? What does provide further information beyond the content of the tutorial? A section called “Presenters” in which each tutorial presenter is briefly introduced in one paragraph, including their research interests, their areas of expertise for the tutorial topic, and their experience in teaching a diverse and international audience. A section called “Other Information” which should include information on how many people are expected to participate and how you came to this estimate. You can also explain any other aspects that you find important, including special equipment that you would need. A section called “Ethics Statement” which discusses ethical considerations related to the topics of the tutorial. The proposals should be submitted no later than 31 July, 2024, 11:59 PM Samoa Standard Time (SST) (UTC/GMT-11, “anywhere on Earth”). Submission is electronic. Please submit the proposals using the START system at this URL: https://softconf.com/coling2025/tutorialsCL25 <https://softconf.com/coling2025/tutorialsCL25> Please note that tutorials should either be 100% in-person or 100% virtual; hybrid formats will not be allowed. For in-person tutorials, at least one tutorial organiser should be physically present to run the tutorial at COLING. Evaluation Criteria The tutorial proposals will be evaluated according to their originality and impact, the expected interest level of participants, as well as the quality of the organizing team and Program Committee and their contribution to the diversity of the conference. Each tutorial will be evaluated regarding its clarity and preparedness, novelty or timely character of the topic, the instructor’s experience, the audience interest, and the potential to increase diversity in our community. Instructor Responsibilities Accepted tutorial presenters will be notified by the date mentioned above. They must then provide abstracts of their tutorials for inclusion in the conference registration material by the specific deadlines. The abstract needs to be provided in ASCII format. The summary will be submitted in PDF format and can be updated from the version submitted for review. The instructors will make their material available in an appropriate way, for instance, by setting up a website. They will be invited to submit their slides to the ACL Anthology. Tutorial Chairs Email: coling25tutorialchairs(a)gmail.com The tutorial chairs are: Djamé Seddah, Senior Researcher, INRIA, Paris, Frace (on leave from Sorbonne University) Shaonan Wang, Associate Professor at the Institute of Automation, Chinese Academy of Sciences, Beijing, China

2 1

Saarland University - Postdoc in NLP/Computational Linguistics
by Alexander Koller 22 Aug '24

22 Aug '24

Hello everyone, I have an open postdoc position at Saarland University (initially two years, with the possibility of extension). I would like to fill it around the end of the year, in October or later. The position offers a lot of flexibility in developing your own research agenda and scientific network. It is also flexible with respect to topic. Current topics of interest in our group include accurate reasoning and planning with LLMs (including tool use); dialogue systems (in particular user adaptation and joint problem solving); and neurosymbolic models for NLP. If you are interested, please see the website for details: https://www.coli.uni-saarland.de/groups/AK/jobs/ I look forward to hearing from you! Best, Alexander Koller.

2 1

2024

2023

2022

Corpora August 2024