- Corpora - ELRA lists

2nd Call for Papers: Workshop on RESOURCEs and representations For Under-resourced Languages and domains (RESOURCEFUL-2023)
by Adam 01 Mar '23

01 Mar '23

[Apologies for cross-posting] The second workshop on resources and representations for under-resourced language and domains (RESOURCEFUL-2023, https://resourceful-workshop.github.io/resourceful-2023/index.html) explores the role of the kind and the quality of resources that are available to us and challenges and directions for constructing new resources in light of the latest trends in natural language processing. The workshop is co-located with NoDaLiDa2023 (https://www.nodalida2023.fo/) at Tórshavn, Faroe Islands on May 22nd-24th, 2023. Data-driven machine-learning techniques in natural language processing have achieved remarkable performance (e.g., BERT, GPT, ChatGPT) but in order to do so large quantities of quality data (which is mostly text) is required. Interpretability studies of large language models in both text-only and multi-modal setups have revealed that even in cases where large text datasets are available, the models still do not cover all the contexts of human social activity and are prone to capturing unwanted bias where data is focused towards only some contexts. A question has also been raised whether textual data is enough to capture semantics of natural language processing and other modalities such as visual representations or a situated context of a robot might be required. Annotator-based resources have been constructed over years based on theoretical work in linguistics, psychology and related fields and a large amount of work has been done both theoretically and practically. The purpose of the workshop is to initiate a discussion between the two communities involved in building resources (data vs annotation-based) and exploring their synergies for the new challenges in natural language processing. We encourage contributions in the areas of resource creation, representation learning and interpretability in data-driven and expert-driven machine learning setups and both uni-modal and multi-modal scenarios. In particular we would like to open a forum by bringing together students, researchers, and experts to address and discuss the following questions: - What is relevant linguistic knowledge the models should capture and how can this knowledge be sampled and extracted in practice? - What kind of linguistic knowledge do we want and can capture in different contexts and tasks? - To what degree are resources that have been traditionally aimed at rule-based natural language processing approaches relevant today both for machine learning techniques and hybrid approaches? - How can they be adapted for data-driven approaches? - To what degree data-driven approaches can be used to facilitate expert-driven annotation? - What are current challenges for expert-based annotation? - How can crowd-sourcing and citizen science be used in building resources? - How can we evaluate and reduce unwanted biases? Intended participants are researchers, PhD students and practitioners from diverse backgrounds (linguistics, psychology, computational linguistics, speech, computer science, machine learning, computer vision etc). We foresee an interactive workshop with plenty of time for discussion, complemented with invited talks and presentations of on-going or completed research. This workshop is a continuation of the first workshop on resources and representations for under-resourced languages and domains held together with the SLTC 2020, https://gu-clasp.github.io/resourceful-2020/. ** Important dates: - Submission deadline for archival papers: 28th March 2023 - Submission deadline for non-archival papers: 4 April 2023 - Notification of acceptance: 25th April 2023 - Camera-ready version: 9th May 2023 - Workshop date: 22nd May 2023 All deadlines are 11:59PM UTC-12:00 ("anywhere on Earth"). ** Submission We invite submissions of long papers (8 pages), short papers (4 pages), and extended abstracts describing work in progress (2 pages). Submissions can report negative results and be opinion pieces. Both papers and extended abstracts can include any number of pages for references. All submissions must follow the NoDaLida template, available in both LaTeX and MS Word, the templates are available at the official conference website, https://www.nodalida2023.fo/authorkit-nodalida23 Submissions must be anonymous and submitted in the PDF format through OpenReview. We also invite submissions of non-archival papers related to our theme already presented or published at other venues. These can be submitted in their original formatting. They will be reviewed by the workshop organisers and the accepted ones will be posted on the workshop website. Authors may be asked to contribute peer-reviews of papers. ** Workshop organisers Dana Dannélls, Språkbanken Text, University of Gothenburg Simon Dobnik, CLASP, University of Gothenburg Adam Ek, CLASP, University of Gothenburg Stella Frank, University of Copenhagen Nikolai Ilinykh, CLASP, University of Gothenburg Beáta Megyesi, Uppsala University Felix Morger, Språkbanken Text, University of Gothenburg Joakim Nivre, RISE and Uppsala University Magnus Sahlgren, AI Sweden Sara Stymne, Uppsala University Jörg Tiedemann, University of Helsinki Lilja Øvrelid, University of Oslo

1 0

Call for Task Participation: WASSA 2023 Shared Task on Emotion Classification on Code-Mixed Text Messages within ACL 2023
by Iqra Ameer 01 Mar '23

01 Mar '23

We invite you to participate in the shared task on Multi-Label and Multi-Class Emotion Classification on Code-Mixed Text Messages, organized as part of WASSA 2023 <https://wassa-workshop.github.io/>at ACL 2023 <https://2023.aclweb.org/>. This task aims to develop models that can predict emotion based on code-mixed (Roman Urdu and English) text messages. *Task Description* The shared task has two Tracks: *Track 1 - Multi-Label Emotion Classification (MLEC):* Given a code-mixed SMS message, classify it as 'neutral or no emotion' or as one, or more, of eleven given emotions that best represent the mental state of the author. *Track 2 - Multi-Class Emotion Classification (MCEC):* Given a code-mixed SMS message, classify it as 'neutral or no emotion' or as one of eleven given emotions that best represent the mental state of the author. *Note: *You are free to participate in any or both tracks. *For participation, please check:* https://codalab.lisn.upsaclay.fr/competitions/10864 *Important Dates* - February 28th, 2023: Initial training data release - February 28th, 2023: Codalab competition website goes online, and development data released - April 15th, 2023: Evaluation phase begins: development labels test data released - April 18th, 2023: Deadline submission of final result on Codalab - April 24th, 2023: Deadline system description paper (max. 4p) - May 22nd, 2023: Notification of acceptance - June 6th, 2023: Camera-ready papers due *Task Organizers* - Iqra Ameer - School of Biomedical Informatics, University of Texas, Health Science Center Houston, USA - ‪Necva Bölücü - Commonwealth Scientific and Industrial Research Organisation, Australia - Ali Al Bataineh - Department of Electrical and Computer Engineering Norwich University, USA - Hua Xu - Section of Biomedical Informatics and Data Science, School of Medicine, Yale University, USA *Contact* wassa23codemixed [at] gmail [dot] com *Join Google Group* wassa23codemixed(a)googlegroups.com -- *Regards,* Dr. Iqra Ameer (Ph.D.)

1 0

CxGs+NLP at GURT/SyntaxFest 2023: Call for participation
by Harish Tayyar Madabushi 01 Mar '23

01 Mar '23

CALL FOR PARTICIPATION The First Construction Grammars and NLP (CxGs+NLP) Workshop will take place as part of the Georgetown University Round Table on Linguistics & SyntaxFest (GURT/SyntaxFest 2023) between the 9 and 12 March, 2023. https://gurt.georgetown.edu Location: Washington, DC Date: March 9-12, 2023 The detailed conference program is now online here: https://gurt.georgetown.edu/gurt-2023/program/ GURT/SyntaxFest is an in-person event with a modest registration fee. For a discounted rate, register by Feb. 28 at https://gurt.georgetown.edu/gurt-2023/registration-gurt-2023. Our aim is to bring together theoretical and computational researchers interested in CxG approaches and encourage topics examining how theoretical research can inform computational approaches and applications, whether existing or needed in the future. Thus, we invite original research papers from a range of topics, including but not limited to: - Theory and Linguistics - Formalisms for construction grammar - Natural Language Understanding (NLU) - Opinion pieces on the interplay between CxGs and NLP - Constructions and Language Models (BERTology) - Constructicons and corpora annotated for construction grammar - Construction grammar learning and adaptation - Applications We will have an invited speaker, Jonathan Dunn discussing the relation between Construction Grammars and NLP. The workshop will also include a discussion consisting of experts from both fields discussing possible synergies between the two fields. We look forward to seeing you in Washington DC! The CxGs+NLP organisers

1 0

CFP: Mediate - News Media and Computational Journalism Workshop
by Elena Kochkina 28 Feb '23

28 Feb '23

Mediate 2023: Mediate - News Media and Computational Journalism Workshop co-located with ICWSM 2023 Limassol, Cyprus, June 5, 2023 https://digitalmediasig.github.io/Mediate2023/ Submission link: https://easychair.org/conferences/?conf=mediate2023 Papers due: March 27, 2023 -------------------------------------------------------------------------- The fourth MEDIATE workshop will be held on June 5, as part of the International AAAI Conference on Web and Social Media (ICWSM). The main goal of the workshop is to bring together media practitioners and technologists to discuss new opportunities and obstacles that arise in the modern era of information diffusion. This year's theme is: Misinformation: automated journalism, explainable and multi-modal verification and content moderation. Topics of interest include, but are not limited to: - Automated journalism: novel automated and human-in-the-loop solutions for rumour detection/verification, fact-checking, stance classification, evaluation of existing solutions and novel relevant applications. Submitted papers should describe how their advantages would lead to being adopted in practice by journalists and the public (e.g. improved generalisability, ability to provide explanations, reduced bias) and address ethical considerations. - Explainable and Multi-modal verification: explainable rumour verification systems, evidence-based solutions, uncertainty and prediction explainability and general interpretable and transparent AI-systems, as well as multi-modal rumour verification/fact-checking models, sources and data, non-textual and multi-modal features. - Content Moderation: novel content moderation systems for inhibiting misinformation spreading, domain-specific content moderation solutions as well as content moderation systems that showcase generalisability and are interpretable. We invite submissions of technical papers and talk proposals: - Technical papers must be up to 4 pages (short papers) or up to 8 pages (long papers). Technical papers must contain novel, previously-unpublished material related to the topics of the workshop. Accepted papers will be presented orally and will appear in the workshop proceedings. - Talk proposals must be up to 2 pages describing the content of a short talk (the actual length will be determined based on program constraints). Papers must adhere to the ICWSM guidelines ( https://www.icwsm.org/2023/index.html/call_for_submissions.html#guidelines) and be submitted through easychair ( https://easychair.org/conferences/?conf=mediate2023). Organizing committee Talia Tseriotou, Queen Mary University of London Dina Pisarevskaya, Queen Mary University of London Elena Kochkina, Alan Turing Institute Marya Bazzi, Alan Turing Institute & University of Warwick Maria Liakata, Alan Turing Institute & Queen Mary University of London Arkaitz Zubiaga, Queen Mary University of London All questions about submissions should be emailed to t.tseriotou(a)qmul.ac.uk<mailto:t.tseriotou@qmul.ac.uk>, d.pisarevskaya(a)qmul.ac.uk<mailto:d.pisarevskaya@qmul.ac.uk> and mbazzi(a)turing.ac.uk<mailto:mbazzi@turing.ac.uk>

1 0

Call for papers DMR 2023: The Fourth International Workshop on Designing Meaning Representation June 20, 2023
by Kristine.stenzel＠colorado.edu 28 Feb '23

28 Feb '23

**apologies for cross-postings** Call for papers DMR 2023: The Fourth International Workshop on Designing Meaning Representation workshop site: dmr2023.github.io Co-located with IWCS 2023 the 15th International Conference on Computational Semantics, 20-23th June 2023, Université de Lorraine, Nancy, France. IWCS site: https://iwcs2023.loria.fr/ While deep learning methods have led to many breakthroughs in practical natural language applications, most notably in Machine Translation, Machine Reading, Question Answering, Recognizing Textual Entailment, and so on, there is still a sense among many NLP researchers that we have a long way to go before we can develop systems that can actually “understand” human language and explain the decisions they make. Indeed, “understanding” natural language entails many different human-like capabilities, and they include but are not limited to the ability to track entities in a text, understand the relations between these entities, track events and their participants described in a text, understand how events unfold in time, and distinguish events that have actually happened from events that are planned or intended, are uncertain, or did not happen at all. We believe a critical step in achieving natural language understanding is to design meaning representations for text that have the necessary meaning “ingredients” that help us achieve these capabilities. Such meaning representations can also potentially be used to evaluate the compositional generalization capacity of deep learning models. There has been a growing body of research devoted to the design, annotation, and parsing of meaning representations in recent years. The meaning representations that have been used for semantic parsing research are developed with different linguistic perspectives and practical goals in mind and have different formal properties. Formal meaning representation frameworks such as Minimal Recursion Semantics (MRS) and Discourse Representation Theory (as exemplified in the Parallel Meaning Bank) are developed with the goal of supporting logical inference in reasoning-based AI systems and are therefore easily translatable into first-order logic, requiring proper representation of semantic components such as quantification, negation, tense, and modality. Other meaning representation frameworks such as Abstract Meaning Representation (AMR), Tecto-grammatical Representation (TR) in Prague Dependency Treebanks and the Universal Conceptual Cognitive Annotation (UCCA), put more emphasis on the representation of core predicate-argument structure, lexical semantic information such as semantic roles and word senses, or named entities and relations. There is also a more recent effort in developing a Uniform Meaning Representation (UMR) that is based on AMR but extends it to cross-linguistic settings and enhances it to represent document-level semantic content. The automatic parsing of natural language text into these meaning representations and the generation of natural language text from these meaning representations are also very active areas of research, and a wide range of technical approaches and learning methods have been applied to these problems. This workshop will bring together researchers who are producers and consumers of meaning representations, and through their interaction develop a deeper understanding of the key elements of meaning representations that are the most valuable to the NLP community. The workshop will also provide an opportunity for meaning representation researchers to critically examine existing frameworks with the goal of using their findings to inform the design of next-generation meaning representations. A third goal of the workshop is to explore opportunities and identify challenges in the design and use of meaning representations in multilingual settings. A final goal of the workshop is to understand the relationship between distributed meaning representations trained on large data sets using network models, and the symbolic meaning representations that are carefully designed and annotated by NLP researchers and gain a deeper understanding of areas where each type of meaning representation is the most effective. The workshop solicits papers that address one or more of the following topics: • Design and annotation of meaning representations; • Cross-framework comparison of meaning representations; • Challenges and techniques in automatic parsing of meaning representations; • Challenges and techniques in automatically generating text from meaning representations; • Meaning representation evaluation metrics; • Lexical resources, ontologies, and grounding in relation to meaning representations; • Real-world applications of meaning representations; • Issues in applying meaning representations to multilingual settings and lower-resourced languages; • The relationship between symbolic meaning representations and distributed semantic representations; • Formal properties of meaning representations; • Any other topics that address the design, processing, and use of meaning representations. === SUBMISSION INFORMATION === Submissions should report original and unpublished research on topics of interest to the workshop. Accepted papers are expected to be presented at the workshop and will be published in the workshop proceedings on the ACL Anthology. They should emphasize obtained results rather than intended work and should clearly indicate the state of completion of the reported results. A paper accepted for presentation at the workshop must not be or have been presented at any other meeting with publicly available proceedings. Submission is electronic, using the Softconf START conference management system. Link to the DMR submission site: https://softconf.com/iwcs2023/dmr2023/ Submissions must adhere to the two-column format of ACL venues. Please use our specific style-files or the Overleaf template taken from ACL 2021: https://www.overleaf.com/latex/templates/instructions-for-iwcs-2021-proceed… Initial submissions should be fully anonymous to ensure double-blind reviewing. Long papers must not exceed eight (8) pages of content. Short papers and demonstration papers must not exceed four (4) pages of content. If a paper is accepted, it will be given an additional page to address reviewers’ comments in the final version. References and appendices do not count against these limits. Reviewing of papers will be double-blind. Therefore, the paper must not include the authors’ names and affiliations or self-references that reveal any author’s identity–e.g., “We previously showed (Smith, 1991) …” should be replaced with citations such as “Smith (1991) previously showed …”. Papers that do not conform to these requirements will be rejected without review. Authors of papers that have been or will be submitted to other meetings or publications must provide this information to the workshop organizers dmr2023-chairs(a)googlegroups.com. Authors of accepted papers must notify the program chairs within 10 days of acceptance if the paper is withdrawn for any reason. ** DMR 2023 does not have an anonymity period. However, we ask you to be reasonable and not publicly advertise your preprint during (or right before) review. === IMPORTANT DATES === Submissions due April 3, 2023 Notification of acceptance May 1, 2023 Camera-ready deadline June 1, 2023 Workshop date June 20, 2023 IWCS conference June 20-23, 2023

1 0

CFP: [ICWSM 2023] TRUEHEALTH 2023: Workshop on Combating Health Misinformation for Social Wellbeing
by r.upadhyay＠campus.unimib.it 28 Feb '23

28 Feb '23

TrueHealth 2023: Combating Health Misinformation for Social Wellbeing Workshop @ ICWSM 2023, the 17th International Conference on Web and Social Media June 5th – 8th 2023, Limassol, Cyprus https://truehealth.disco.unimib.it/ Scope and topics: In recent years, people have increasingly referred to the Web and social media as sources of information about health-related problems and solutions, as confirmed by the U.S. Pew Research Center, and other European and international studies. Although, on the one hand, these platforms favor easier and more direct access to information sources by users without the intermediation of experts, on the other hand, it is precisely such democratization of health information that constitutes a potential danger for people. As we have seen especially in the last period, linked to the pandemic, the proliferation of false information, conspiracy theories, and unreliable remedies risk compromising the health not only of individuals but that of the community as a whole. From this perspective, it becomes necessary to study and propose technological solutions to help users come into contact with genuine information, especially in a critical domain such as health, for social well-being. To this end, it is essential to promote research of an interdisciplinary nature, involving computer scientists, physicians, lawyers, and communication experts who can address the problem of health misinformation from different points of view by combining their expertise. The topics of interest of the TrueHealth 2023 Workshop at ICWSM include, but are not limited to: Assessing the genuineness of Online Health Information (OHI); Consumer Health Search (CHS) and genuine information access; Debunking health misinformation; Fake news/rumors and healthcare; Measures, evaluation methods, and datasets for health misinformation detection; Health misinformation detection; Health literacy and information genuineness; Fact-checking in Online Health Information (OHI); Misinformation and public opinion on health; Relationship between access to non-genuine information and danger to public health; Relationship between psychological characteristics and perceptions of health misinformation; Techniques for accessing and retrieving genuine Online Health Information (OHI). Submission Instructions We welcome both 2-page abstracts, as well as Long (8 pages) and Short (4 pages) papers – excluding references (11 pages max with references and ethics statement). Abstracts are ideal as Demo or Position papers, Short papers as presentations of ongoing research with preliminary results or summaries of previous work, and Long papers as presentations of novel research and results. Long and Short papers will be published in ICWSM Workshop Proceedings (http://workshop-proceedings.icwsm.org/). All submissions should be double-blind. Papers have to follow the AAAI format, as outlined here: https://www.overleaf.com/latex/templates/aaai-2023-author-kit/wxnmhzcrjbpc Submit here: https://easychair.org/conferences/?conf=truehealth2023 Other ICWSM submission instructions: https://www.icwsm.org/2023/index.html/call_for_submissions.html Important Dates Workshop Papers Submissions: March 27, 2023 Workshop Paper Acceptance Notification: April 10, 2023 Workshop Final Camera-Ready Paper Due: May 6, 2023 ICWSM-2023 Workshops Day: June 5, 2023 Organizers Gabriella Pasi (Full Professor), University of Milano-Bicocca, Milan, Italy Rishabh Upadhyay (Research Fellow), University of Milano-Bicocca, Milan, Italy Marco Viviani (Associate Professor), University of Milano-Bicocca, Milan, Italy Program Committee Lorraine Goeuriot, Université Grenoble Alpes, France Sanda Harabagiu, The University of Texas at Dallas, USA Liadh Kelly, Maynooth University, Ireland Dongwon Lee, Penn State: The Pennsylvania State University, USA Yelena Mejova, ISI Foundation, Italy Michael Sirivianos, Cyprus University of Technology, Cyprus Xingyi Song, University of Sheffield, UK Angelo Spognardi, Sapienza University of Rome, Italy Bei Yu, Syracuse University, USA Arkaitz Zubiaga, Queen Mary University of London, UK Other members are going to be added in the coming days

1 0

2023 Law & Corpus Linguistics Conference
by Brett Hashimoto 28 Feb '23

28 Feb '23

Hello, We're writing with an updated call for proposals for the Law and Corpus Linguistics Conference to be held on Friday, October 13, 2023, with pre-conference workshops on Thursday, October 12. The conference will be held at Brigham Young University's J. Reuben Clark Law School in Provo, Utah. We're pleased to announce that the keynote address at this year's conference will be given by D. Gordon Smith, Dean of the J. Reuben Clark Law School at Brigham Young University. Gordon has made tremendous contributions to the field of law and corpus linguistics, and we're excited to have him as this year's keynote speaker. Proposals are invited for individual papers and panels. We're open to submissions on a broad range of topics, including but not limited to: * applications of corpus linguistics to the constitutional, statutory, contract, patent, trademark, probate, administrative, and criminal law in any state or nation; * philosophical, normative, and pragmatic commentary on the use of corpus linguistics in the law; * triangulation between corpus linguistics and other empirical methods in legal interpretation; * corpus linguistic analysis of the law of countries other than the United States; * the relationship between corpus linguistics and pragmatics (e.g. implicature, presupposition, sociolinguistic context); * corpus-based analysis of legal discourse or topics; * best practices in corpus design and corpus linguistic methods in legal settings. We have a new proposal deadline of May 31, 2023. Proposals should include an abstract of no more than 750 words and complete contact information for presenters. Please send proposals to byulawcorpus(a)law.byu.edu<mailto:byulawcorpus@law.byu.edu>. Best, BYU LCL 2023 Conference Organizing Committee (Thomas Lee, Jesse Egbert, Brett Hashimoto, James Heilpern and James Phillips) ------------------------------ Assistant Professor of Linguistics Brigham Young University https://sites.google.com/site/brettjameshashimoto/ https://orcid.org/0000-0002-9871-5092

1 0

Vacancy for Research Associate in Natural Language Processing (KTP Associate)
by Paul Thompson 28 Feb '23

28 Feb '23

This is an exciting opportunity at the cutting edge of innovation in the legal and financial sectors for an ambitious graduate with the ability and confidence to undertake a ground-breaking natural language processing project. The University of Manchester and 10BE5 are looking for a driven and accomplished candidate to undertake a 30-month project that aims to automate fact-checking and verification of disclosure documents. The successful candidate will have the unique distinction of also being: - a member of the University of Manchester's prestigious and world-leading National Centre for Text Mining; and - a part of the diverse and dynamic team at 10BE5, an award-winning and fast-growing legal tech company that affords opportunities of interacting with many of the world's largest corporations and firms. The successful candidate will conduct novel to work research in fact-checking and verification, as well as claim mining from legal and financial documents. He/she will also work on the development of labelled data using active and proactive generative approaches and the use of knowledge graphs. Candidates will require a PhD in Natural Language Processing and work experience in related domains. The post is partly funded through a Knowledge Transfer Partnership (KTP) award, the UK Government's flagship scheme intended to promote sustained and mutually beneficial relationships between research organizations and industry. The contractual place of work will be 10BE5 Ltd., 107-111 Fleet Street, London, EC4A 2AB. This role, however, follows a hybrid working pattern that will see the candidate alternating between working from home and at the business location plus occasional visits the University campus in Manchester. The successful candidate will work with supervisors from both the University of Manchester and 10BE5 and will use the facilities and resources of both organisations. Salary: £34,308 to £42,155 per annum depending on experience This position also qualifies for a London Weighting allowance of £3,000 per annum due to 10BE5's London location and includes access to a ring-fenced £5,000 personal development budget Closing date: 14/03/2023 Contract Duration: Available For 30 Months From Start Date For further information and to apply, please visit: https://www.jobs.manchester.ac.uk/displayjob.aspx?jobid=24920 -- Paul Thompson Research Fellow Department of Computer Science National Centre for Text Mining Manchester Institute of Biotechnology University of Manchester 131 Princess Street Manchester M1 7DN UK Tel: 0161 306 3091 http://personalpages.manchester.ac.uk/staff/Paul.Thompson/

1 0

Fully Funded PhD Position: "Emergent Behavior in Large Language Models: Social, Cultural and Psychological Dimensions ».
by Thierry Poibeau 28 Feb '23

28 Feb '23

PhD position available - MSCA COFUND, AI4theSciences (PSL University, France) - "Emergent Behavior in Large Language Models: Social, Cultural and Psychological Dimensions ». Large language models are trained on very large datasets and are known to learn different kinds of associations, certain of them being problematic and leading to biases and stereotypes. But how do these models encode opinions, beliefs and other cultural traits? How should a model deal with this kind of information? This thesis will offer an opportunity to explore these issues. The position is based in Paris (Ecole normale supérieure / PSL), supervised by Thierry Poibeau (https://www.lattice.cnrs.fr/en/members/direction/thierry-poibeau/). It will be co-supervised by Simon Hegelich, from TUM (https://www.hfp.tum.de/politicaldatascience/team/simon-hegelich/) and Saurabh Dhawan (https://www.hfp.tum.de/politicaldatascience/team/saurabh-dhawan/). Candidates should have a strong technical background in AI / NLP (an experience with large language models would be a plus, of course). An additional degree or good knowledge of social sciences is also desirable. Candidates should apply before March, 31. They should not have spent more than 12 months in France in the past 36 months. A more detailed description of the position as well as of the selection procedure is available here: https://euraxess.ec.europa.eu/jobs/67053 (the selection will be done by an independent committee following the MSCA rules. Candidates are however strongly encouraged to contact the PhD supervisor before the application deadline). All the best, Thierry Poibeau

1 0

[CfP] 1st International Workshop on Semantic Methods for Events and Stories (SEMMES 2023)
by Pasquale Lisena 28 Feb '23

28 Feb '23

apologies for cross-posting *************** Semantic Methods for Events and Stories (SEMMES 2023) – Call for Papers *************** Website: https://anr-kflow.github.io/semmes/ CfP: https://easychair.org/cfp/SEMMES2023 Workshop co-located with the Extended Semantic Web Conference (ESWC) Submission deadline: March 9th, 2023 Scope *************** An important part of human history and knowledge is made of events, which can be aggregated and connected to create stories, be they real or fictional. These events as well as the stories created from them can typically be inherently complex, reflect societal or political stances and be perceived differently across the world population. The Semantic Web offers technologies and methods to represent these events and stories, as well as to interpret the knowledge encoded into graphs and use it for different applications, spanning from narrative understanding and generation to fact-checking. The aim of our workshop on Semantic Methods for Events and Stories (SEMMES) is to offer an opportunity to discuss the challenges related to dealing with events and stories, and how we can use semantic methods to tackle them. We welcome approaches which combine data, methods and technologies coming from the Semantic Web with methods from other fields, including machine learning, narratology or information extraction. This workshop wants to bring together researchers working on complementary topics, in order to foster collaboration and sharing of expertise in the context of events and stories. Topics *************** Topics of interest include, but are not limited to: - Ontologies and data models for representing events, event relations, and narratives; - Event extraction, co-reference and linking; - Event Relation extraction and linking (e.g. temporal, causal, modal relationships); - Fake events detection and event verification; - Event-centric question answering; - Event information visualisation; - Event-centric knowledge graphs and vocabularies; - Completion of event-centric knowledge graphs and reasoning; - Event summarisation; - Automatic narrative understanding and generation; - Storytelling Applications/Demos. Submission Guidelines *************** We welcome the following types of contributions. - Long papers (10-15 pages including references) - Short papers (5-9 pages including references) We welcome any types of research, resource and application papers, as well as (short only) demonstration submissions. Submissions must be written in English and formatted using the template for submissions to CEUR Workshop Proceedings (https://www.overleaf.com/latex/templates/template-for-submissions-to-ceur-w…) All papers and abstracts have to be submitted electronically via EasyChair: https://easychair.org/conferences/?conf=semmes2023. Each accepted paper needs to be presented by one of the authors, who agrees to register and participate in SEMMES. Important Dates *************** - Submission deadline: March 9th, 2023 - Notifications: April 13th, 2023 - Camera-ready version: April 20th, 2023 - Workshop day: May 29th, 2023 afternoon All deadlines are 23:59 anywhere on earth (UTC-12). Proceedings *************** The complete set of papers will be published with the CEUR Workshop Proceedings (http://CEUR-WS.org), listed by the DBLP. -- Pasquale Lisena EURECOM, Campus SophiaTech 450 route des Chappes, 06410 Biot, France e-mail: pasquale.lisena(a)eurecom.fr site: http://pasqlisena.github.io/-- Pasquale Lisena EURECOM, Campus SophiaTech 450 route des Chappes, 06410 Biot, France e-mail: pasquale.lisena(a)eurecom.fr site: http://pasqlisena.github.io/

1 0

2025

2024

2023

2022

Corpora