- Corpora - ELRA lists

NLM SPARK Challenges
by ddemner＠mail.nih.gov 17 Sep '26

17 Sep '26

Dear all, NLM prize competitions intend to advance AI-enabled discovery across PubMed/PubMed Central® and dbGaP: Please see details here: https://www.nih.gov/challenges/semantic-precision-ai-retrieval-knowledge-sp… https://www.nih.gov/challenges/semantic-precision-ai-retrieval-knowledge-sp… Questions can be directed to the following email mailboxes for these challenges: NLMSPRKCHLG_PBMD-PMC(a)mail.nih.gov. NLMSPRKCHLG_DBGAP(a)mail.nih.gov.

1 0

Assistant Professor of Applied Linguistics position at TAMU-CC
by Fitzsimmons-Doolan, Shannon 17 Sep '26

17 Sep '26

Colleagues, Apologies in advance for cross-posting. We are hiring for a T-T Asst Prof of Applied Ling here at Texas A&M University—Corpus Christi (link and text of job announcement below). Please feel free to share. If anyone has questions about the application process, they can feel free to contact Dr. Stephen Doolan (Stephen.Doolan(a)tamucc.edu<mailto:Stephen.Doolan@tamucc.edu>). Best, Shannon Fitzsimmons-Doolan https://tamus.wd1.myworkdayjobs.com/en-US/TAMUCC_External/details/Assistant… Job Title Assistant Professor of English, Applied Linguistics Agency Texas A&M University - Corpus Christi Department College Of Liberal Arts Proposed Minimum Salary Commensurate Job Location Corpus Christi, Texas Job Type Faculty Job Description The Department of English at Texas A&M University–Corpus Christi invites applications for a 9-month, tenure-track position at the rank of Assistant Professor of English, with a concentration in Applied Linguistics, beginning in Fall 2027. The position entails a 3/3 teaching load and has commensurate research and service expectations. Summer and online teaching opportunities may be available. The Department of English allows English majors to pursue undergraduate coursework with either a Writing or Literary Studies emphasis. The department additionally offers curricula for secondary English certification; certificates in Writing for Non-Profits, social media, and TESOL; and minors in Technical and Professional Writing, Creative Writing, and Literary Studies. The graduate program provides an interdisciplinary educational experience by requiring coursework in Literary Studies, Writing Studies, and Applied Linguistics. The Applied Linguistics faculty coordinate and teach the courses for two undergraduate TESOL certificates. In addition, they teach courses in the ENGL BA, ENGL BA with secondary English teaching certification, ENGL MA, Elementary Education BS, and BIEM ESL Minor. The TESOL certificates are pursued by students from across the university with an enrollment of 50+ students. Texas A&M University–Corpus Christi is a vibrant, Hispanic-Serving Doctoral Research Institution that proudly provides a solid academic reputation, renowned faculty, and highly rated degree programs since 1947. The University has a heritage of teaching excellence with innovation in research and community engagement as part of the distinguished Texas A&M System. With palm tree-lined pathways throughout the campus, nearby natural wetlands, a scenic hike-and-bike trail, and a university beach, Texas A&M University–Corpus Christi is the only university in the nation located on its own island, at the heart of the Texas Gulf Coast. Required Qualifications: * A PhD in Applied Linguistics or related field. Advanced ABD will be considered; degree must be conferred at the time of appointment.  * Demonstrated a successful research agenda specializing in at least two of the following areas: TESOL methods, technology-assisted language learning/teaching, corpus linguistics, or an area of sociolinguistics. Preferred qualifications: * Demonstrated commitment to teaching a broad range of applied linguistics courses at the undergraduate level. * Experience teaching language learners. * Experience working with first-generation students and historically underserved communities. TO APPLY: https://www.tamucc.edu/human-resources/careers/index.php All required documentation must be submitted to be considered for the position. A completed application will include: * A letter of interest consisting of three distinct parts: * (Part 1) Directly addressing the job description; * (Part 2) Explicitly presenting a teaching philosophy; and * (Part 3) Providing a research statement. * A current curriculum vitae * Unofficial copies of graduate transcripts * Three letters of recommendations Application deadline: Friday, October 23rd, 2026 Position start date: Fall 2027 For questions about the position, please contact Dr. Christopher Andrews, Department Chair, at christopher.andrews(a)tamucc.edu<mailto:christopher.andrews@tamucc.edu>. Dr. Shannon Fitzsimmons-Doolan, Applied Linguist Professor, English Dept, Texas A&M Corpus Christi Harte Research Institute Fellow Shannon.Fitzsimmons-Doolan(a)tamucc.edu 361-825-3607

1 0

[2nd call] Postdoc in Mechanistic Understanding of AI Reasoning at University of Copenhagen
by Isabelle Augenstein 16 Sep '26

16 Sep '26

We are seeking to recruit a postdoctoral researcher to work on understanding the mechanisms of AI reasoning. Their core duty will be to advance our understanding of how LLMs acquire, integrate and reason over evolving, pluralistic knowledge using mechanistic interpretability methods. This can involve the development of novel conceptual frameworks, methods, or empirical studies. The postdoc’s duties will also to a small degree include teaching or supervision. The position is offered in the context of the context of an ERC Starting Grant held by Isabelle Augenstein on ‘Explainable and Robust Automatic Fact Checking (ExplainYourself<https://cordis.europa.eu/project/id/101077481>)’, as well the Pioneer Centre for AI. The position will be offered from 1 February 2027 or as close to this date as possible, for a period of two years, with the possibility of extension contingent on funding availability. Apply here by 30 September 2026, 23:59 CET to be considered: https://candidate.hr-manager.net/ApplicationInit.aspx/?cid=3010&departmentI… Who are we looking for? Applicants should hold a PhD degree or equivalent in Computer Science or a related field, and have good written and oral English skills. The assessment of qualifications will also be made based on previous scientific publications and relevant work experience. The ideal candidate would have an educational background, prior research or work experience on Natural Language Processing, Machine Learning, and/or Explainable AI. Our group and research -- and what do we offer? The successful candidate will join the CopeNLU group<http://www.copenlu.com/> at the University of Copenhagen. CopeNLU is a vibrant and collaborative research group led by Isabelle Augenstein and Pepa Atanasova with a focus on fair and accountable NLP. We are interested in core methodology research on interpretability, explainability and bias detection; as well as applications to tasks such as fact checking and cross-cultural learning. With a strong focus on both foundational and applied research, we provide a platform for exploring cutting-edge topics in NLP, while also emphasising the importance of transparent and responsible AI development. We are affiliated with the Pioneer Centre for AI<https://www.aicentre.dk/> at the Department of Computer Science<https://di.ku.dk/english/>, Faculty of SCIENCE, University of Copenhagen, located in central Copenhagen. The Pioneer Centre focuses on fundamental AI research, and within an interdisciplinary framework, develops platforms, methods, and practices that address society’s greatest challenges. It consists of seven AI research themes, with one being Speech and Language. The Natural Language Processing research environment at the University of Copenhagen is internationally leading, as e.g. evidenced by it being ranked second in Europe according to CSRankings. Isabelle Augenstein, Dr. Scient., Ph.D. Professor and Deputy Head of Department for Research Department of Computer Science University of Copenhagen Østervold Observatory Øster Voldgade 3 1350 Copenhagen augenstein(a)di.ku.dk<mailto:augenstein@di.ku.dk> http://isabelleaugenstein.github.io/

1 0

Open PhD studentship (GW4BioMed3) on "AI scientists for understanding dementia modifiable risk factors" at the University of Exeter
by h.dong2＠exeter.ac.uk 15 Sep '26

15 Sep '26

We have an exciting digital health PhD studentship available (starting Oct 2027) for application under the GW4BioMed3 scheme, at the Department of Computer Science @ University of Exeter and Exeter Medical School. AI scientists for understanding dementia modifiable risk factors - https://gw4biomed.ac.uk/ai-scientists-for-understanding-dementia-modifiable… Summary: Early dementia prediction is an urgent problem to improve the clinical pathway for individuals who are at risk of dementia due to well established risks such as cognitive decline, lifestyle, medical or genetic factors. This project aims to design an AI system that integrates scientific knowledge for early dementia modelling, based on large language models and causal inference. The project has two stages: first, to construct a causal knowledge graph from scientific papers and cognitive test questionnaire data, and second, to integrate the graph with transformer-based large language models and causal learning. This offers an explainable understanding of personalised risk factors. (Detailed summary available to download at the link above) We welcome applications and will be happy to meet with candidates after shortlisting and before interview. Applications close on Wednesday 21st October 2026.

1 0

Public talks (25 September 2026) by Prof Robert Berwick, MIT, and Soyoung Oh, University of Saarlandes (NLP Day 2026 at the University of Exeter)
by h.dong2＠exeter.ac.uk 15 Sep '26

15 Sep '26

We welcome you to the public talks at NLP Day 2026 at the University of Exeter. Talk 1 Zoom scheduled: Friday 25 September 2026 at 10:00 to 11:00, UK/London time - Check you local time at https://zonestamp.toolforge.org/1790326800 Location: https://Universityofexeter.zoom.us/j/93589650456?pwd=HwnKKCkjYa3Dpa8TkPX72W… (Meeting ID: 935 8965 0456 Password: 514707) Title: How do LLMs use context? Abstract: Understanding language requires more than processing words, it involves interpreting words in context and keeping track of a changing context. How do large language models perform these operations internally? In this talk, I explore this question through the lens of mechanistic interpretability: (1) resolving literal and figurative meanings in idioms (2) tracking entities as their state changes. These settings allow us to investigate how context shapes internal representations and how models access relevant information in infererence time. Short Bio: Soyoung Oh is a PhD student supervised by Prof. Vera Demberg at Saarland University. Her research focuses on understanding internal mechanisms of LLMs in reasoning. Talk 2 Zoom scheduled: Friday 25 September 2026 at 13:30 to 14:30, UK/London time - Check you local time at https://zonestamp.toolforge.org/1790339400 Location: https://Universityofexeter.zoom.us/j/93589650456?pwd=HwnKKCkjYa3Dpa8TkPX72W… (Meeting ID: 935 8965 0456 Password: 514707) Title: The (Algebraic) Nature of Natural Language Short Bio: Professor Robert C. Berwick is Professor of Computational Linguistics and Engineering in the Department of Electrical Engineering and Computer Science. Professor Berwick received his A.B. degree from Harvard University in Applied Mathematics and his S.M. and Ph.D. degrees from the Massachusetts Institute of Technology in Computer Science and Artificial Intelligence. He has been a member of the MIT faculty for nearly forty years. He was one of the founders and co-Director of the MIT Center for Biological and Computational Learning. He has received numerous awards, including a Guggenheim Fellowship, as well as MIT’s highest award for junior faculty, the Edgerton Faculty Achievement award, and one of the Vatican’s notable honors, the Pontifical Council for Culture Award. Professor Berwick’s research has spanned several disciplines, from natural language processing to learning theory and to bioinformatics and evolutionary biology, to the interplay between deep learning and human language. He is the author of nearly a dozen books and numerous articles in the area of human language, learning, language processing, neurobiology and evolution, and cognition, including, Why Only Us (MIT Press, 2016), on the evolution of human language, co-written with Professor Noam Chomsky. His most recent book, The Mathematical Structure of Syntactic Merge, co-authored with Profs Matilde Marcolli and Noam Chomsky, focuses on a new mathematical approach to the formalization of generative grammar.

1 0

September 2026 Newsletter - LDC
by Penn LDC 15 Sep '26

15 Sep '26

In this newsletter: LDC data and commercial technology development New publications: CALLHOME Mandarin Chinese Second Edition<https://catalog.ldc.upenn.edu/LDC2026S11> CALLHOME Mandarin Chinese Lexicon Second Edition<https://catalog.ldc.upenn.edu/LDC2026L06> MATERIAL Lithuanian-English Language Pack<https://catalog.ldc.upenn.edu/LDC2026S12> ________________________________ LDC data and commercial technology development For-profit organizations are reminded that an LDC membership is a pre-requisite for obtaining a commercial license to almost all LDC databases. Non-member organizations, including non-member for-profit organizations, cannot use LDC data to develop or test products for commercialization, nor can they use LDC data in any commercial product or for any commercial purpose. LDC data users should consult corpus-specific license agreements for limitations on the use of certain corpora. Visit the Licensing<https://www.ldc.upenn.edu/data-management/using/licensing> page for further information. ________________________________ New publications: CALLHOME Mandarin Chinese Second Edition<https://catalog.ldc.upenn.edu/LDC2026S11> was developed by LDC and contains 38 hours of speech from 120 unscripted telephone conversations between native Mandarin Chinese speakers. This publication is a re-release of the original CALLHOME Mandarin Chinese collection, combining CALLHOME Mandarin Chinese Speech (LDC96S34)<https://catalog.ldc.upenn.edu/LDC96S34> and CALLHOME Mandarin Chinese Transcripts (LDC96T16)<https://catalog.ldc.upenn.edu/LDC96T16>, with additional transcription and updated directory structure, file formats, and documentation. This release contains the 120 telephone conversations published in CALLHOME Mandarin Chinese Speech (LDC96S34)<https://catalog.ldc.upenn.edu/LDC96S34> which represented training and development data and a subset of evaluation data. Participants spoke on topics of their choice in a single telephone call lasting up to 30 minutes. Calls were manually audited for gender, language, recording quality, channel characteristics, dialect, and accent. For this second edition, all audio was converted from SPHERE files to FLAC format, and the original training/development/evaluation partitioning was removed. This release also features revised transcripts conforming to updated LDC transcription guidelines that addressed normalization of annotation formats, standardization of speaker-produced and background noises, application of foreign-language marking, whitespace cleanup, and corrections and consistency fixes. The CALLHOME series consists of telephone conversations and transcripts developed by LDC and Rutgers, The State University of New Jersey, in support of research in speaker identification, language identification and related technologies. Languages in the series include American English, Egyptian Arabic, German, Japanese, Mandarin Chinese, and Spanish. 2026 members can access this corpus through their LDC accounts. Non-members may license this data for a fee. * CALLHOME Mandarin Chinese Lexicon Second Edition<https://catalog.ldc.upenn.edu/LDC2026L06> was developed by LDC and contains 44,404 Mandarin Chinese words with morphological, phonological and frequency information. This second edition updates file formats, directory structure and documentation. The first edition is available as CALLHOME Mandarin Chinese Lexicon (LDC96L15)<https://catalog.ldc.upenn.edu/LDC96L15>. The words in the lexicon were derived from transcripts representing unscripted telephone conversations between native Mandarin Chinese speakers contained in CALLHOME Mandarin Chinese Second Edition (LDC2026S11) <https://catalog.ldc.upenn.edu/LDC2026S11> and from Chinese news text. The lexicon contains seven tab-separated information fields: (1) headword: orthographic representation of the word in hanzi (e.g., 没有); (2) pinyin: headword transcribed in pinyin (e.g., mei2 you3); (3) tone: tone sequence for headword (e.g., 2 3); (4) pron: pronunciation of headword without tone information (e.g., mey yow); (5) pos: part-of-speech tag for the headword; (6) xinhua_freq: frequency of the headword in newswire text; and (7) train_freq: frequency of the headword in the CALLHOME transcripts. It is presented as a tab-delimited TSV file encoded in UTF-8 format and includes a pronunciation dictionary derived from the lexicon in UTF-8 encoded CMUdict<https://stdlib.io/docs/api/latest/@stdlib/datasets/cmudict> format. 2026 members can access this corpus through their LDC accounts provided they have submitted a completed copy of the special license agreement. Non-members may license this data for a fee. * MATERIAL Lithuanian-English Language Pack<https://catalog.ldc.upenn.edu/LDC2026S12> was developed by Appen<http://www.appen.com/> for the IARPA MATERIAL<https://www.iarpa.gov/index.php/research-programs/material> program and contains 64 hours of Lithuanian conversational telephone speech, transcripts, English translations, annotations, and queries. Calls were made using different telephones (e.g., mobile, landline) from a variety of environments. Transcripts cover approximately 100% of the speech files, 6% of which were translated into English. This release also includes domain annotations, English queries, and their relevance annotations. The MATERIAL program focused on underserved languages with the ultimate goal to build cross language information retrieval systems to find speech and text content using English search queries. 2026 members can access this corpus through their LDC accounts provided they have submitted a completed copy of the special license agreement. Non-members may license this data for a fee. To unsubscribe from this newsletter, log in to your LDC account<https://catalog.ldc.upenn.edu/login> and uncheck the box next to “Receive Newsletter” under Account Options or contact LDC for assistance. Membership Coordinator Linguistic Data Consortium<ldc.upenn.edu> University of Pennsylvania T: +1-215-573-1275 E: ldc(a)ldc.upenn.edu<mailto:ldc@ldc.upenn.edu> M: 3600 Market St. Suite 810 Philadelphia, PA 19104

1 0

3rd CfP and deadline extension: Methods Fair at the IDS Annual Conference 2027 "Language and Literature"
by Roman Schneider 15 Sep '26

15 Sep '26

Apologies for cross-posting. The Call for Papers below is in German, as it concerns a German-language conference dedicated to methods and resources for research on the German language. Please feel free to forward it to colleagues who may be interested. ------------ Methodenmesse auf der IDS-Jahrestagung 2027: "Sprache und Literatur" Die 63. Jahrestagung des Leibniz-Instituts für Deutsche Sprache (IDS) in Mannheim steht unter dem Motto "Sprache und Literatur" und zielt darauf ab, Phänomene literarischer Sprache aus der Perspektive linguistischer Fragestellungen und Methoden zu beleuchten. Wir rufen zur Einreichung von Beiträgen für die Methodenmesse auf, die am Mittwoch, 10. März 2027, im Rahmen der Tagung stattfindet. Der Fokus der Methodenmesse ist praxisnah und liegt auf Ressourcen, Methoden und Werkzeugen, die idealerweise anhand kurzer Anwendungsstudien demonstriert werden. Die Vorstellung von spezifischen Studien ist ebenfalls möglich, wobei transparente Methodik, Dokumentation und möglichst reproduzierbare Forschungsprozesse im Vordergrund stehen sollten. Wir begrüßen insbesondere Beiträge, die sich mit der deutschen Sprache beschäftigen bzw. auf das Deutsche anwendbare Methoden oder Tools vorstellen. Geplante Themenbereiche sind: • Korpora oder andere Ressourcen für die empirische Arbeit mit literarischen Texten • Tools, Strategien und Workflows für die empirische Untersuchung literarischer Texte mit Bezug auf deren sprachliche Struktur, hierbei auch besonders: o Untersuchungen und kritische Reflexion zum Einsatz von KI-Methoden o Untersuchungen zu multimodalen und neuartigen Literaturformen (z.B. Songs, Graphic Novels, Social-Media-Formate, interaktive Formate, KI-generierte Literatur) • Didaktisch-methodische Konzepte für die Verknüpfung von Sprach- und Literaturwissenschaft in Lehre und Unterricht Weitere Themenbereiche können berücksichtigt werden, sofern der Bezug zum Tagungsthema in der Einreichung klar herausgearbeitet ist. Die Beiträge werden in Form eines Posters und ggf. einer Softwaredemonstration präsentiert. Auf der Tagung wird jeder Beitrag in einem einminütigen Schlaglicht dem Publikum vorgestellt. Anschließend gibt es die Gelegenheit, die Inhalte im Rahmen einer ca. eineinhalbstündigen Poster-Session zu demonstrieren und Fragen zu beantworten. Ausgearbeitete Beiträge sollen im Anschluss an die Tagung bei IDSopen ( https://idsopen.de ) digital nach dem Open-Access-Prinzip publiziert werden. Wenn Sie einen Beitrag zur Methodenmesse beisteuern möchten, bitten wir um ein nicht anonymisiertes Abstract auf Deutsch (ca. 500 Wörter exkl. Literaturangaben; in einem editierbaren Format) bis zum 30.09.2026 (verlängerte Deadline) an folgende Adresse: methodenmesse2027(a)ids-mannheim.de Über die Annahme der Beiträge wird bis zum 15.11.2026 entschieden. Konferenz-Webseite: https://www.ids-mannheim.de/aktuell/veranstaltungen/tagungen/jahrestagung-2… Organisationsteam: Annelen Brunner, Katharina Gloning, Peter Meyer, Roman Schneider -- Prof. Dr. Roman Schneider Leibniz-Institut für Deutsche Sprache, R5 6-13, 68161 Mannheim Tel: +49 621-1581-217 http://www.ids-mannheim.de/gra/personal/schneider.html

1 0

2nd Call for Papers: International Workshop on Multilingualism in Learner Corpus Research (MLCR27)
by Frey Jennifer-Carmen 15 Sep '26

15 Sep '26

Dear colleagues, we would like to invite you to submit your proposals for the "International Workshop on Multilingualism in Learner Corpus Research (MLCR27)", which will take place on 6–7 May 2027 at Eurac Research in Bolzano, Italy. The workshop aims to bring together researchers working at the intersection of multilingualism and learner corpus research to discuss theoretical, methodological, and empirical issues in this emerging field. We welcome concluded research as well as work-in-progress discussions and poster presentations on topics including (but not limited to): * design, compilation, and annotation of multilingual learner corpora * methodological challenges in capturing multilingual learner profiles * plurilingual competence and repertoire-based approaches * multilingual speaking, writing and translation practices * longitudinal perspectives on multilingual development * pedagogical implications of multilingual learner corpus research * innovative methods and tools for analysing multilingual learner data * multilingual learner corpus data in mixed methods designs For the full call for papers, submission guidelines, and further information, please visit the workshop website: https://www.porta.eurac.edu/mlcr27/ Please submit your anonymised abstracts (max. 300 words, excluding references) via ConfTool<https://conftool.lt.eurac.edu/MLCR27/>. Submission deadline: 15 October 2026 Confirmed keynote speakers * Heike Wiese (Humboldt University of Berlin, Germany) * Hildgunn Dirdal (University of Oslo, Norway) For any further questions, don't hesitate to contact us via porta(a)eurac.edu<mailto:porta@eurac.edu> We look forward to receiving your submissions and to welcoming you to Bolzano in May 2027! Best regards, Aivars Glaznieks and Jennifer-Carmen Frey Eurac Research, Bolzano ___ Jennifer-Carmen Frey, PhD [cid:498ac965-0a22-49b5-8568-d89da750be1f] <https://orcid.org/0000-0002-7008-6394> Eurac Research Institute for Applied Linguistics Drususallee/Viale Druso 1 I-39100 Bozen/Bolzano www.eurac.edu<http://www.eurac.edu/> Facebook<https://facebook.com/eurac.research> | YouTube<https://www.youtube.com/EURACtv> | X<https://twitter.com/eurac> | LinkedIn<https://www.linkedin.com/company/euracresearch> | Instagram<https://www.instagram.com/euracresearch/> [signature_1401579056]<https://www.eurac.edu/en> According to regulation (EU) 2016/679 this transmission is intended only for the use of the addressee and may contain confidential information. If you receive this transmission in error, please notify the sender immediately by email and delete all copies of this message and any attachments.

1 0

DEADLINE EXTENDED — WASP 2026
by ACL Announcements 15 Sep '26

15 Sep '26

==================================================================== DEADLINE EXTENDED -- WASP 2026 4th Workshop on Artificial Intelligence for Scientific Publications Co-located with IJCNLP-AACL 2026 (online) >>> New paper deadline: September 21, 2026 (AoE) <<< ==================================================================== The WASP 2026 submission deadline has moved back one week to September 21 (AoE). This is the final week. WASP 2026 covers information extraction, summarisation, retrieval, evaluation, and the responsible use of LLMs across the scientific publishing pipeline. Long papers up to 8 pages, short papers up to 4 pages, double-blind, with proceedings in the ACL Anthology. Submit (OpenReview): https://openreview.net/group?id=aclweb.org/AACL-IJCNLP/2026/Workshop/WASP [1] Full call and topics: https://ui.adsabs.harvard.edu/WIESP/2026/ [2] SHARED TASK: AstroCLIMB Our multimodal shared task (reconstructing a paper's citation graph from figures and captions) has been extended to the same date. Data is live on Kaggle. Details: https://ui.adsabs.harvard.edu/WIESP/2026/shared_task [3] UPDATED DATES (AoE) - Paper submission (WASP): September 21, 2026 - Shared task registration: September 20, 2026 - Shared task system run + paper: September 21, 2026 - Notification: October 5, 2026 - Camera-ready: October 12, 2026 - Workshop: November 10, 2026 Contact: Atilla Kaan Alkan, atilla.alkan(a)cfa.harvard.edu We look forward to your submissions. Links: ------ [1] https://openreview.net/group?id=aclweb.org/AACL-IJCNLP/2026/Workshop/WASP [2] https://ui.adsabs.harvard.edu/WIESP/2026/ [3] https://ui.adsabs.harvard.edu/WIESP/2026/shared_task

1 0

Call for contribution - Knowledge and Natural Language Processing Track @ ACM SAC 2027
by Patrizio Bellan 14 Sep '26

14 Sep '26

As Artificial Intelligence systems increasingly rely on both language understanding and structured knowledge, bridging Natural Language Processing and Knowledge Engineering has become a central challenge for the next generation of intelligent systems. The rapid evolution of Large Language Models and knowledge-based AI is creating new opportunities—and new challenges—in how machines acquire, represent, connect, and reason over knowledge. Understanding language alone is no longer enough: modern AI systems must also be able to organize knowledge, integrate it with linguistic information, and use it effectively to support reasoning. As a result, the relationship between language, knowledge, and reasoning has emerged as one of the key research frontiers in contemporary Artificial Intelligence. The Knowledge and Natural Language Processing (KNLP) Track at the ACM Symposium on Applied Computing investigates methods and applications at the intersection of *Knowledge Engineering* and *Natural Language Processing*, with particular emphasis on approaches that combine these two areas. KNLP is an emerging and highly interdisciplinary research field at the core of Artificial Intelligence. It brings together and complements scientific advances in Natural Language Processing, Knowledge Representation and Reasoning, Machine Learning, and related disciplines. *Topics of Interest* Topics of interest include, but are not limited to, the following. *Natural Language Processing* - NLP methods for knowledge extraction - NLP for ontology population and ontology learning - Sentiment analysis and opinion mining for knowledge-based applications - Interplay between natural language and ontologies - NLP for explainable knowledge - Machine translation techniques for multilingual knowledge - NLP for the Web - Bias detection and mitigation in small and large language models - Interaction between small or large language models and knowledge *Knowledge* - Knowledge-enhanced NLP - Knowledge for information retrieval - Knowledge-based sentiment analysis and opinion mining - Combining knowledge and deep learning for NLP - Knowledge technologies for the Web - Knowledge-enhanced agentic reasoning - Agent reasoning over knowledge graphs and ontologies - Knowledge-based agent personalization - Linked Data for NLP - Knowledge-based natural language explainability - Language-model-enhanced ontology and knowledge engineering methodologies and tools - Language-model-based agents for knowledge extraction, reasoning, and management - Ontology evaluation using small and large language models - Ontological knowledge representation and memorization in language models - Knowledge-based techniques for language models, including Retrieval-Augmented Generation, fact-checking, and bias mitigation - Question answering over knowledge graphs using small and large language models *Real-World Applications Exploiting Knowledge and NLP* - Knowledge and NLP systems for Big Data scenarios - Knowledge and NLP technologies supporting a diverse, equitable, and inclusive society - Deployment and evaluation of Knowledge and NLP systems in domains such as: - Digital Humanities and Social Sciences - eGovernment and public administration - Life sciences, healthcare, and medicine - News, media, and data-streaming environments *Paper Submission* We invite original research papers and experience reports addressing the topics listed above. Submissions must not have been previously published or be under consideration for publication elsewhere. Papers must be submitted in PDF format using the official ACM SAC proceedings template. Authors’ names and affiliations must be entered separately in the submission system and must not appear in the submitted manuscript. All submissions will undergo a *double-blind peer-review process* in accordance with ACM SAC regulations. Submissions to the *Student Research Competition (SRC)* are also welcome. Prospective authors should consult the SAC 2027 SRC page for eligibility requirements and submission instructions. *Submission Policy* - All papers must initially be submitted as *regular papers*. There is no separate submission category for poster papers. - Papers will be evaluated according to their originality, technical contribution, presentation quality, and relevance to the Knowledge and Natural Language Processing Track. - Depending on the outcome of the review process and the overall acceptance-rate constraints, technically sound submissions that cannot be accepted as regular papers may be offered acceptance as posters. - Although there is no formal minimum page requirement, submissions shorter than *four full pages* that do not demonstrate a substantial contribution may be desk-rejected without external review. *Submission Links* - *Regular papers and SRC abstracts:* submission links are available through the ACM SAC 2027 website <https://www.sigapp.org/sac/sac2027/> - *Author kit and templates:* formatting instructions and official templates are available through the ACM SAC 2027 website <https://www.sigapp.org/sac/sac2027/> *Important Dates* Please consult the official ACM SAC 2027 website <https://www.sigapp.org/sac/sac2027/#important-dates> for up-to-date deadlines and possible changes. - *October 2, 2026:* Regular paper and SRC abstract submission - *November 13, 2026:* Author notification - *November 28, 2026:* Camera-ready copies of accepted papers and SRC submissions - *December 5, 2026:* Author registration deadline - *April 5–9, 2027:* Knowledge and Natural Language Processing Track at ACM SAC 2027 All deadlines follow the time zone specified on the official conference website. *Further Information* For further information, please visit the Knowledge and Natural Language Processing Track website <https://knlp.fbk.eu/> and the ACM SAC 2027 conference website <https://www.sigapp.org/sac/sac2027/>. Questions may be addressed to the KNLP Track Co-Chairs <knlp(a)fbk.eu>. -- -- Le informazioni contenute nella presente comunicazione sono di natura privata e come tali sono da considerarsi riservate ed indirizzate esclusivamente ai destinatari indicati e per le finalità strettamente legate al relativo contenuto. Se avete ricevuto questo messaggio per errore, vi preghiamo di eliminarlo e di inviare una comunicazione all’indirizzo e-mail del mittente. -- The information transmitted is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. If you received this in error, please contact the sender and delete the material.

1 0

2026

2025

2024

2023

2022

Corpora