June 2023 - Corpora - ELRA lists

Position available at NLP & IR Research Group UNED
by JORGE AMANDO CARRILLO DE ALBORNOZ CUADRADO 26 Jun '23

26 Jun '23

Full time position The UNED IR & NLP group has an open position. The successful candidate is expected to work as part of the joint research project FAIRTRANSNLP-DIAGNOSIS: Measuring and quantifying bias and fairness in NLP pipelines, together with colleagues from the Universidad de Barcelona and Universidad Politécnica de Valencia. The project focuses on developing methodologies and metrics for measuring bias, fairness and transparency in NLP systems. The detection of bias, their types and sources, is essential for developing unbiased datasets for training fair systems in NLP. Within the FAIRTRANSNLP project, the candidate will work in the formalization of the detection of bias, fairness, and transparency of NLP pipelines from three different angles: (i) bias embedded in the dataset; (ii) degree of fairness in ML algorithms; and (iii) transparency techniques used in ML to achieve explainability in NLP. The candidate will also participate in the compilation and annotation of datasets. * Candidate profile * * Academic background (university degree, preferably master) in computer science or related discipline. * Knowledge of natural language processing and machine learning. * Excellent programming skills. * Ability to research and work as part of a team. * Fluent in English. * Terms and conditions * One year position with a possible extension to two years (1+1) after a positive evaluation. * Application * The position is open until filled. Follow instructions in the official call: https://www2.uned.es/bici/Curso2022-2023/32306266/36-1.htm#9.-_____Convocat… Please send an email to lplaza(a)lsi.uned.es and jcalbornoz(a)lsi.uned.es for more info. * More about us * The UNED NLP & IR group is a leading group in Information Retrieval and Natural Language Processing. Our team consists of more than 30 people. https://sites.google.com/view/nlp-uned/home AVISO LEGAL. Este mensaje puede contener información reservada y confidencial. Si usted no es el destinatario no está autorizado a copiar, reproducir o distribuir este mensaje ni su contenido. Si ha recibido este mensaje por error, le rogamos que lo notifique al remitente. Le informamos de que sus datos personales, que puedan constar en este mensaje, serán tratados en calidad de responsable de tratamiento por la UNIVERSIDAD NACIONAL DE EDUCACIÓN A DISTANCIA (UNED) c/ Bravo Murillo, 38, 28015-MADRID-, con la finalidad de mantener el contacto con usted. La base jurídica que legitima este tratamiento, será su consentimiento, el interés legítimo o la necesidad para gestionar una relación contractual o similar. En cualquier momento podrá ejercer sus derechos de acceso, rectificación, supresión, oposición, limitación al tratamiento o portabilidad de los datos, ante la UNED, Departamento de Política Jurídica de Seguridad de la Información<https://www.uned.es/dpj>, o a través de la Sede electrónica<https://sede.uned.es/> de la Universidad. Para más información visite nuestra Política de Privacidad<https://descargas.uned.es/publico/pdf/Politica_privacidad_UNED.pdf>.

2 7

10th International Conference on Behavioural and Social Computing (BESC 2023): Fifth Call for Papers
by georgeangelos60＠gmail.com 26 Jun '23

26 Jun '23

*** Fifth Call for Papers *** 10th International Conference on Behavioural and Social Computing (BESC 2023) October 30 - November 1, 2023, 5* Golden Bay Beach Hotel, Larnaca, Cyprus http://besc-conf.org/2023/ The International Conference on Behavioural and Social Computing (BESC) is a major international forum that brings together academic researchers and industry practitioners from artificial intelligence, computational social sciences, natural language processing, business and marketing, and behavioural and psychological sciences to present updated research efforts and progresses on foundational and emerging interdisciplinary topics of BESC, exchange new ideas and identify future research directions. The BESC series of conferences are technically sponsored by IEEE SMC (Systems, Man and Cybernetics) Society as well as IEEE CIS (Computational Intelligence Society) and the proceedings are published by IEEE BESC 2023 invites submissions of original, high-quality research papers addressing cutting-edge developments from all areas of behavioural and social computing. The conference aims to bring together researchers and practitioners from academia and industry to share their knowledge, experience, and perspectives on the latest trends, challenges, and opportunities in this rapidly evolving field. Topics of interest include, but are not limited to: Social Computing, Computational Social Science and Applications • Computational models of social phenomena • Social behaviour • Social network analysis • Semantic web • Collective intelligence • Security, privacy, trust in social contexts • Social recommendation • Social influence and social contagions • Quantifying offline phenomena through online data • Forecasting of social phenomena • Science and technology studies approaches to computational social science • Social media and health behaviours • Social psychology and personality • New theories, methods, and objectives in computational social science Digital Humanities • Digital media • Digital humanities • Digital games and learning • Digital footprints and privacy • Crowd dynamics • Digital arts • Digital healthcare • Activity streams and experience design • Virtual communities (e.g., open-source, multiplayer gaming, etc.) Information Management and Information Systems (IS) • Decision analytics • E-Business • Decision analytics • Computational finance • Societal impacts of IS • Human behaviour and IS • IS in healthcare • IS security and privacy • IS strategy, structure and organizational impacts • Service science and IS Natural Language Processing • Web mining and its social interpretations • Sentiment Analysis, Stylistic Analysis, and Argument Mining • Opinion mining and social media analytics • Credibility of online content • Computational Linguistics • Mining big social data • Cognitive Modelling and Psycholinguistics Behaviour and User Modelling, Privacy, and Ethics • Behaviour change • Positive technology • Personalization for individuals, groups and populations • Large scale personalization, adaptation and recommendation • Web dynamics and personalization • Privacy, perceived security and trust • Technology and Wellbeing • Ethics of computational research on human behaviour Technology Enhanced Learning (TEL) • E-Learning and M-Learning • Open and Distance Learning • User modeling and personalization in TEL • TEL in secondary and in higher education • New tools for TEL BESC 2023 will also host the following Special Sessions. Papers accepted in any of the Special Sessions will be included in the same IEEE conference proceedings with the papers accepted for the general technical program. ● Computational Social Psychology in Post Covid-19 Period ● Artificial Intelligence for Mental Health, Mental Illness, Psychiatic Diagnosis, and Prediction ● Intelligent E-Learning at Post Covid-19 Era ● Big Data and AI-Powered Decision Support Systems in Business ● Understanding the Citizen's Behavior in Cognitive Cities ● Nudges and Behavioural Computing Models for a Sustainable and Equitable Development SUBMISSION INSTRUCTIONS The paper submission system is using Easy Chair and the submission link is: https://easychair.org/conferences/?conf=besc2023 . All papers will be reviewed by the Program Committee on the basis of technical quality, relevance to BESC 2023, originality, significance and clarity. Please note: • All submissions should use IEEE two-column style. Templates are available here: https://www.ieee.org/conferences/publishing/templates.html • All papers must be submitted electronically through the paper submission system in PDF format only. BESC 2023 accepts research papers (6 pages), special session papers (6 pages) and Doctoral Symposium papers (4 pages). • The page count above excludes the references (but includes any appendices). • Paper review will be double-blind, and submissions not properly anonymized will be desk-rejected without review. • Submitted papers must not substantially overlap with papers that have been published or that are simultaneously submitted to a journal or a conference with proceedings. • Papers must be clearly submitted in English and will be selected based on their originality, timeliness, significance, relevance, and clarity of presentation. • Submission of a paper should be regarded as a commitment that, should the paper be accepted, at least one of the authors will register and attend the conference to present the work. • The use of artificial intelligence (AI)–generated text in an article shall be disclosed in the acknowledgements section of any paper submitted to an IEEE Conference or Periodical. The sections of the paper that use AI-generated text shall have a citation to the AI system used to generate the text. • All accepted papers will be included in IEEE Xplore and indexed by EI. Top quality papers after presented in the conference will be selected for extension and publication in several special issues of international journals, e.g., World Wide Web Journal (Springer), Web Intelligence (IOS Press), and Social Network Analysis and Mining (Springer), Human-Centric Intelligent Systems (Springer), Information Discovery and Delivery (Emerald Publishing). IMPORTANT DATES • Submission of all papers: 15 July 2023 • Notification of acceptance for submitted papers: 15 September 2023 • Camera-Ready Submission: 1 October 2023 • Author Registration: 1 October 2023 ORGANISATION Steering Committee Chair • Guandong Xu, University of Technology Sydney, Australia General Chair • George A. Papadopoulos, University of Cyprus, Cyprus Program Chairs • Georgia Kapitsaki, University of Cyprus, Cyprus • Ji Zhang, University of Southern Queensland, Australia Special Session Chairs • Taotao Cai, University of Southern Queensland, Australia • Ting Yu, Zhejiang Lab, China Doctoral Symposium Chair • Barbara Caci, University of Palermo, Italy Panel and Tutorial Chair • Philippe Fournier-Viger, Shenzhen University, China Proceedings Chair • Md Rafiqul Islam, University of Technology Sydney, Australia Publicity Chairs • Chandan Gautam, Institute for Infocomm Research (I2R), A*STAR, Singapore • Thanveer Shaik, University of Southern Queensland, Australia • Sanjay Sonbhadra, ITER, Siksha 'O' Anusandhan, India Webmaster • Shiqing Wu, University of Technology Sydney, Australia

1 0

Counting multiple long (9+) n-grams in corpora: request for approaches
by beauchampd＠uni.coventry.ac.uk 23 Jun '23

23 Jun '23

Hi all, I'm doing analysis on a corpus on tweets from institutions. Regarding analysis of n-grams, it is quite unusual in that there are many repeated exact tweets, or very similar tweets, leading to long super strings of often 9 or 10 or more words together. Naturally this makes accurate counting and classifying difficult due to the overlapping substrings. Does anyone know of any approaches or software which can count and classify n-grams in such circumstances? I am aware of approaches outlined by Buerki (2017) and O'Donnell (2011), but these do not seem practical due to the excessive length of the n-grams in the corpus. Does anyone know of any accessible methods or packages? Any input much appreciated.

1 0

CL2023 - FREE online attendance
by Brezina, Vaclav 23 Jun '23

23 Jun '23

Dear all, There is a last chance to register for FREE to watch live streaming of sessions from the International Corpus Linguistics Conference 2023 (CL2023) from Lancaster University, UK 3rd - 6th July. If you can't be in Lancaster in person, you can still sign up to watch our live online broadcasts - for free! https://www.lancaster.ac.uk/cl2023/registration/ Best, Vaclav Professor Vaclav Brezina Professor in Corpus Linguistics Department of Linguistics and English Language ESRC Centre for Corpus Approaches to Social Science Faculty of Arts and Social Sciences, Lancaster University Lancaster, LA1 4YD Office: County South, room C05 T: +44 (0)1524 510828 [8ED5AC37]@vaclavbrezina [B213DA5D]<http://www.lancaster.ac.uk/arts-and-social-sciences/about-us/people/vaclav-…>

1 0

CLASSLA web corpora of Croatian, Serbian and Slovenian
by Taja Kuzman 23 Jun '23

23 Jun '23

** *Dear all,* ** ** * The CLASSLA Knowledge centre for South Slavic languages (https://www.clarin.si/info/k-centre/ <https://www.clarin.si/info/k-centre/>) is delighted to announce the release of the pilot versions (v0.1) of the CLASSLA web corpora for Croatian (2.3 billion words), Serbian (2.4 billion words) and Slovenian (1.9 billion words). They are available for querying via the CLARIN.SI concordancers (https://www.clarin.si/ske/#open <https://www.clarin.si/ske/#open>). The main features of the newly released corpora, aside from their large size and recency (crawled in 2022) is their automatic enrichment with genre information (https://huggingface.co/classla/xlm-roberta-base-multilingual-text-genre-cla… <https://huggingface.co/classla/xlm-roberta-base-multilingual-text-genre-cla…>) and their linguistic processing with the improved CLASSLA-Stanza annotation pipeline (https://pypi.org/project/classla/ <https://pypi.org/project/classla/>). The pilot versions of these corpora are intended to gather valuable user feedback, while the official release (v1.0) of the three existing corpora, along with web corpora for Bosnian, Montenegrin, Macedonian, and Bulgarian, is scheduled for later this year. We warmly welcome you to explore our corpora and feel free to reach out to us at helpdesk.classla(a)clarin.si <mailto:helpdesk.classla@clarin.si>with any ideas for improvements. You are also invited to read our blog post on the use of CLASSLA web corpora via the open CLARIN.SI concordancers: https://www.clarin.si/info/k-centre/classla-web-bigger-and-better-web-corpo… <https://www.clarin.si/info/k-centre/classla-web-bigger-and-better-web-corpo…>. If you are interested in South Slavic resources and technologies, we also invite you to join the CLASSLA mailing list (https://mailman.ijs.si/mailman/listinfo/classla <https://mailman.ijs.si/mailman/listinfo/classla>) and to follow the CLARIN.SI infrastructure on Twitter (https://twitter.com/ClarinSlovenia <https://twitter.com/ClarinSlovenia>).* Best regards, Taja Kuzman, Nikola Ljubešić and many other CLASSLAers

1 0

Call for Abstracts: Computational Linguistics poster session at DGfS
by Tatjana Scheffler 22 Jun '23

22 Jun '23

CALL FOR ABSTRACTS We would like to invite the submission of abstracts for the Computational Linguistics poster session at the 46th Annual Meeting of the German Linguistic Society (DGfS), hosted by the Ruhr University Bochum. This conference brings together linguists from all subfields in Germany and beyond, and the poster session offers an opportunity to share computational approaches to language within the broader community. We invite submissions from all areas of computational linguistics and natural language processing. We especially encourage students and junior researchers to participate. The poster session is organized by the Special Interest Group on Computational Linguistics of the DGfS (dgfs.de/cl). Conference homepage: https://www.dgfs2024.ruhr-uni-bochum.de/ DATES - Abstract submission due: September 30, 2023 - Notification of acceptance: October 13, 2023 - Conference dates: February 28-March 1, 2024 SUBMISSION One page abstract (A4) in PDF format (12pt). Submissions can be in German or English and do not need to be anonymous. Please submit your abstract via email to: tatjana.scheffler(a)rub.de CONTACT Tatjana Scheffler, Ruhr University Bochum, tatjana.scheffler(a)rub.de Annette Hautli-Janisz, University of Passau --- Jun.-Prof. Dr. Tatjana Scheffler (she/her) GB 5/157 Ruhr-Universität Bochum Fakultät für Philologie, Germanistik Universitätsstraße 150 44801 Bochum Germany Mail: tatjana.scheffler(a)rub.de Web: http://staff.germanistik.rub.de/digitale-forensische-linguistik/ Tel.: +49 234 32-21471

1 0

CFP: ALTA 2023
by Diego Molla-Aliod 22 Jun '23

22 Jun '23

ALTA 2023 Call for Papers https://alta2023.alta.asn.au/ IMPORTANT DATES * Submission Deadline for short/long papers, presentation abstracts and industry demonstrations: 5 September 2023 (11:59pm Anywhere on Earth UTC-12) * Author Notification: 14 October 2023 * Camera-Ready Deadline: 28 October 2023 (11:59pm Anywhere on Earth UTC-12) * Tutorials: 29 November 2023 * Main Conference: 30 November and 1 December 2023 OVERVIEW The 21st Annual Workshop of the Australasian Language Technology Association will be held in a hybrid format at Melbourne Connect, Melbourne, from the 29th November to 1st December 2023 The hybrid format gives participants a valuable opportunity to attend either in-person or online. The ALTA 2023 workshop is the key local forum for socialising research results in natural language processing and computational linguistics, with presentations, posters and demonstrations from students, industry, and academic researchers. Like previous years, we would also like to encourage submissions and participation from industry and government researchers and developers. Note that ALTA is listed in the CORE 2021 Conference Rankings as Australasian B. See details from CORE Rankings Portal. TOPICS ALTA invites the submission of papers and presentations on all aspects of natural language processing, including, but not limited to: ● Commonsense Reasoning ● Computational Social Science and Cultural Analytics ● Dialogue and Interactive Systems ● Discourse and Pragmatics ● Efficient Methods for NLP ● Ethics in NLP ● Information Extraction ● Information Retrieval and Text Mining ● Interpretability, Interactivity and Analysis of Models for NLP ● Language Grounding to Vision, Robotics and Beyond ● Language Modeling and Analysis of Language Models ● Linguistic Theories, Cognitive Modeling and Psycholinguistics ● Machine Learning for NLP ● Machine Translation ● Multilinguality and Linguistic Diversity ● Natural Language Generation ● NLP Applications ● Phonology, Morphology and Word Segmentation ● Question Answering ● Resources and Evaluation ● Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc. ● Sentiment Analysis, Stylistic Analysis, and Argument Mining ● Speech and Multimodality ● Summarization ● Syntax, Parsing and their Applications We particularly encourage submissions that broaden the scope of our community through the consideration of practical applications of language technology and through multi-disciplinary research. We also specifically encourage submissions from industry. FORMAT We invite submissions of three different formats: (1) Original Research Papers; (2) Abstract-based Presentations; and (3) Industry Demonstrations. (1) Original Research Papers We invite the submission of papers on original and unpublished research on all aspects of natural language processing. Long papers should be 7-8 pages and short papers should be 3-4 pages. Accepted papers will either be delivered as an oral presentation or as a poster presentation. We only accept poster presentations for participants who are presenting on site. Both short and long papers may include unlimited pages of references in addition to the page count requirements. Note that the review process is double-blind, and accordingly submitted papers should not include the identity of author(s) and the text should be suitably anonymised, e.g. using third person wording for self-citations, not providing URLs to your personal website, etc. Original research papers will be included in the workshop proceedings, which will be published online in the ACL anthology and the ALTA website. Long papers will be distinguished from short papers in the proceedings. (2) Abstract-based Presentations To encourage broader participation and facilitate local socialisation of international results, we invite 1-2 page presentation abstracts. The organisers may offer the opportunity to give an oral presentation or a poster presentation. We only accept poster presentations for participants who are presenting on site. Submissions should include presentation title and abstract, name of the presenter, any publications relating to the work, and any information on collaboration with the local ALTA community. Abstracts will not be published in the proceedings, but simply reviewed by the ALTA executive committee to ensure that they are on topic, coherent and likely to be of interest to the ALTA community. Abstracts on work in progress and work published or submitted elsewhere are encouraged. ALTA invites submissions of all manner interesting research, not limited to, but including: ● established academics giving an overview of an exciting paper or paper/s published in international venues; ● completing research students giving an overview of their thesis work; ● early candidature research students presenting their work-in-progress and ideas, which may not have been published. Presentation abstracts should not be anonymised, any publications relating to the work should be cited in the submission, and the person who will give the presentation should be clearly stated. (3) Industry Demonstrations To encourage industry participation and networking opportunities, we are thrilled to announce a track for industry demonstrations, which provides an exciting opportunity for industry researchers to showcase their NLP applications. You should submit a proposal that is 1-2 pages long, containing: (1) a description of the software, tools or applications that will be presented and how NLP techniques are used to address a specific problem; and (2) a brief introduction of your organisation. The proposals will be reviewed by the ALTA executive committee to select demonstrations that best align with the interest of the ALTA community. MULTIPLE SUBMISSION POLICY Original research papers that are under review for other publication venues or that you intend to submit elsewhere may be submitted in parallel to ALTA. We require that you declare at submission that your paper is submitted to another venue, and identify the venue. Should your paper be accepted to both ALTA and another venue, we allow you to decide whether the paper should be published in the ALTA proceedings, or if it should be treated as a Presentation (without archival publication). In this case you would still be able to present a research talk at the ALTA workshop. This is to encourage more internationally leading research to be presented at the workshop. INSTRUCTIONS FOR AUTHORS PAPER SUBMISSION Authors should submit their papers via OpenReview: https://openreview.net/group?id=ALTA.asn.au/2023/Workshop (using the “ALTA 2023 Workshop Submission” button) Formatting Guidelines Submissions must follow the two-column ACL format. We therefore strongly recommend you use LaTeX style files or Microsoft Word template from: https://github.com/acl-org/acl-style-files Paper Length Long papers should be 7-8 pages (excluding references) Short papers should be 3-4 pages (excluding references) Abstracts ideally should be a few paragraphs and no more than 2 pages Industry demonstration proposals should be 1-2 pages Anonymisation Short and long papers must be anonymised. Abstracts are NOT to be anonymised and must include the author's/authors' affiliation

1 0

[CfP] SEMANTiCS 2023 EU - Call for Workshop Papers
by Anisa Rula & Jennifer D'Souza 21 Jun '23

21 Jun '23

* We apologize if you receive multiple copies of this CFP * * For the online version of this call, please visit: https://2023-eu.semantics.cc/page/workshops * SEMANTiCS 2023 (20th-22nd September - Leipzig, Germany) is hosting an enriched collection of three workshops accepting submissions for contributions: Onto4FAIR: 3rd Workshop on Ontologies for FAIR and FAIR Ontologies Organizers: Cassia Trojahn (Institut de Recherche en Informatique de Toulouse, France), Luiz Olavo Bonino da Silva Santos (University of Twente, Leiden University Medical Centre, the Netherlands), Giancarlo Guizzardi (University of Twente, the Netherlands), Clement Jonquet (French National Research Institute for Agriculture, Food and Environment, Mathematics, Informatics and Statistics for Environment and Agronomy research unit, Montpellier, France) https://onto4fair.github.io/2023-semantics.html Sem4Tra: 5th International Workshop On A Semantic Data Space For Transport Organizers: David Chaves Fraga (Senior Researcher, UPM & KULeuven), Mersedeh Sadeghi (Senior Researcher, University of Cologne), Shahrom Sohi (Researcher, WU), Julián Rojas (Postdoc Researcher, imec - IDLab UGent), Pieter Colpaert (Senior Researcher, imec - IDLab UGent) https://sem4tra2023.linkeddata.es/ NLP4KGC: 2nd Workshop on Natural Language Processing for Knowledge Graph Construction Organizers: Edlira Vakaj (Birmingham City University, Bermingham, UK), Sanju Tiwari (Universidad Autónoma de Tamaulipas, Tamaulipas, Mexico), Rizou Stamatia (Singular Logic, Athens, Greece), Nandana Mihindukulasooriya (IBM Research, Dublin, Ireland), Fernando Ortiz-Rodríguez (Universidad Autónoma de Tamaulipas, Tamaulipas, Mexico), Ryan Mcgranaghan (NASA Jet Propulsion Laboratory, California, United States) https://sites.google.com/view/2nd-nlp4kgc/home Looking forward to your submissions! With kind regards, Workshop & Tutorial Chairs

1 0

FinTOC 2023 Call For Participation
by FinTOC SharedTask 21 Jun '23

21 Jun '23

Please find the FINTOC 2023 Shared Task Call for Participation below. Apologies for cross-posting. With best wishes, FinTOC 2023 Shared Task organizing committee --- Call for participation: FNP-2023 Shared Task: FinTOC - Financial Document Structure Extraction Practical Information: To be held as part of the 5th Financial Narrative Processing Workshop (FNP 2023) <https://wp.lancs.ac.uk/cfie/fnp2023/>during the 2023 IEEE International Conference on Big Data (IEEE BigData 2023) <http://bigdataieee.org/BigData2023/>, Sorrento, Italy, from 15th December to 18th December, 2023. It is a one-day event of which the exact date is to be announced. =================== Shared Task URL: http://wp.lancs.ac.uk/cfie/fintoc2023/ <http://wp.lancs.ac.uk/cfie/fintoc2022/> Workshop URL: https://wp.lancs.ac.uk/cfie/fnp2023/ Participation Form: https://docs.google.com/forms/d/e/1FAIpQLSdqUKy3YGho0Cw2GF__VHilHZZbR75UDG3… ___________________________________________________________ Shared Task Description: A vast and continuously growing volume of financial documents are being created and published in machine-readable formats, predominantly in aPDF format. Unfortunately, these documents often lack comprehensive structural information, presenting a challenge for efficient analysis and interpretation. Nevertheless, these documents play a crucial role in enabling firms to report their activities, financial situation, and investment plans to shareholders, investors, and the financial markets. They serve as corporate annual reports, offering detailed financial and operational information. In certain countries like the United States and France, regulators such as the SEC (Securities and Exchange Commission) and the AMF (Financial Markets Authority) have implemented requirements for firms to adhere to specific reporting templates. These regulations aim to promote standardization and consistency across firms' disclosures. However, in various European countries, management typically possesses more flexibility in determining what, where, and how to report financial information, resulting in a lack of standardization among financial documents published within the same market. Although there has been some research conducted on the recognition of books and document table of contents (TOC), most of the existing work has focused on small-scale, application-dependent and domain-specific datasets. This limited scope poses challenges when dealing with a vast collection of heterogeneous documents and books, where TOCs from different domains exhibit significant variations in visual layout and style. Consequently, recognizing and extracting TOCs becomes an intricate problem. Indeed, in comparison to regular books that are typically provided in a full-text format with limited structural information such as pages and paragraphs, financial documents possess a more complex structure. They consist of various elements, including parts, sections, sub-sections, and even sub-sub-sections, incorporating both textual and non-textual content. Thus, TOC pages are not always present to help readers navigate the document, and when they are, they often only provide access to the main sections. In this shared task, our objective is to undertake the analysis of various types of financial documents, encompassing KIID (Key Investor Information Document), Prospectus (official PDF documents where investment funds meticulously describe their characteristics and investment modalities), Réglement and Financial Annual Reports/Financial Statements (that provide a detailed overview of a company's financial performance and operations over the course of a fiscal year). These documents play a vital role in providing crucial information to investors, stakeholders, and regulatory bodies. While the content they must contain is often prescribed and regulated, their format lacks standardization, leading to a significant degree of variability. The presentation styles range from plain text format to more visually rich and data-driven graphical and tabular representations. Notably, the majority of those documents are published without a table of contents . A TOC is typically essential for readers as it enables easy navigation within the document by providing a clear outline of headers and corresponding page numbers. Additionally, TOCs serve as a valuable resource for legal teams, facilitating the verification of the inclusion of all the required contents. Consequently, the automated analysis of these documents to extract their structure is becoming increasingly useful for numerous firms worldwide. Our primary focus for this edition is to expand the extraction of table of contents to a wider variety of financial documents, and the task will involve developing highly efficient algorithms and methodologies to address the challenges associated with such a dataset. Our aim is to achieve a level of generalization ensuring that the developed system can be applied to different types of financial documents. This broader scope allows us to explore the applicability of our methodologies across a range of financial document categories, such as KIID, Prospectus, Réglement and Financial Annual Reports/Financial Statements. This way, we want to demonstrate the versatility and effectiveness of the ML algorithms used in TOC extraction, enabling a streamlined and consistent approach across various financial document types. In addition, for this edition, we are excited to introduce a dataset that goes beyond textual annotations. Our proposed dataset will include visual (spatial) annotations that capture the coordinates of the titles and hierarchical structure of the documents. This comprehensive approach enables a more holistic analysis and understanding of financial documents. By incorporating visual annotations, we can capture the visual cues and design elements that contribute to the overall structure and organization of the documents. This allows us to delve deeper into the visual representation of the table of contents and extract valuable insights from the visual hierarchy present in these financial documents. The combination of textual and visual annotations provides a richer and more nuanced dataset, making it possible to increase the accuracy and effectiveness of the machine learning algorithms and methodologies employed in TOC extraction. Thanks to the contribution of the Autonomous University of Madrid (UAM, Spain), the fifth edition of the FinTOC Shared Task welcomes a specific track for Spanish documents, continuing from the previous edition. In this edition, systems will be scored based on their performance in both Title detection and TOC generation using more precise evaluation metrics based on visual annotations. Participants are required to register for the Shared Task. Once registered, all participating teams will receive a common training dataset consisting of PDF documents along with the associated TOC annotations. To participate please use the registration form below to add details about your team: https://docs.google.com/forms/d/e/1FAIpQLSdqUKy3YGho0Cw2GF__VHilHZZbR75UDG3… (now open as of 06/01/2023) _____________________________________________ - 1st Call for papers & shared task participants: June 12, 2023 - 2nd Call for papers & shared task participants: July 17, 2023 - Final Call for papers & shared task participants: August 17, 2023 - Training set release: August 21, 2023 - Blind test set release: September 21, 2023 - Systems submission: October 03, 2023 - Release of results: October 09, 2023 - Paper submission deadline: October 18, 2023 (anywhere in the world) - Notification of paper acceptance to authors: November 01, 2023 - Camera-ready of accepted papers: November 15, 2023 - Workshop date (1 day event) : December 15-18, 2023 (exact date to be announced) _____________________________________________ Contact: For any questions on the shared task please contact us on: fin.toc.task(a)gmail.com _____________________________________________ Shared Task Organizers: - Abderrahim Ait Azzi, 3DS Outscale (ex Fortia), France - Sandra Bellato, 3DS Outscale (ex Fortia), France - Blanca Carbajo Coronado, Universidad Autónoma de Madrid - Dr Ismail El Maarouf, Imprevicible - Dr Juyeon Kang, 3DS Outscale (ex Fortia), France - Prof. Ana Gisbert, Universidad Autónoma de Madrid - Prof. Antonio Moreno Sandoval, Universidad Autónoma de Madrid

1 0

ACL 2023 Discounted Virtual Registration
by Nedjma OUSIDHOUM 20 Jun '23

20 Jun '23

Dear corpora list members, ACL is offering discounted registration waivers for researchers who would not attend the event otherwise ( https://2023.aclweb.org/registration/discounted_virtual_registration) . Please fill out this form <https://forms.office.com/Pages/ResponsePage.aspx?id=DQSIkWdsW0yxEjajBLZtrQA…> on on before June 28th. The notifications will be sent on July 5th. Please note that these are different from the D&I subsidies, see https://2023.aclweb.org/registration/ for more detail. Kind regards, The ACL 2023 D&I Chairs.

1 0