SEPLN – CEDI 2024: 40th INTERNATIONAL CONFERENCE OF THE SPANISH SOCIETY FOR NATURAL LANGUAGE PROCESSING - VII CONGRESO ESPAÑOL DE INFORMÁTICA
A Coruña, Spain
June 20, 2024
The Spanish Society for Natural Language Processing (SEPLN) is pleased to invite you to participate in the Special SEPLN – CEDI Seminar 2024. The Seminar will take place on 20 June 2024 in A Coruña (Spain) co-located with the VII Congreso Español de Informática.
The SEPLN-CEDI 2024 Seminar intends to be an appropriate forum for helping new professionals to become active members in this field. In this respect, its main aim is to give the possibility to present real NLP applications (demos) and R&D projects.
Topics of interest
Topics related to NLP, including but not limited to:
Linguistic, mathematical and psycholinguistic models of language.
Machine learning in NLP.
Computational lexicography and terminology.
Corpus linguistics.
Development of linguistic resources and tools.
Morphological and syntactic analysis.
Semantics, pragmatics and discourse.
Word sense disambiguation.
Monolingual and multilingual text generation.
Machine translation.
Knowledge and common sense.
Multimodality.
Spoken language processing.
Dialogue systems and interactive systems / Conversational assistants.
Multimedia indexing and retrieval.
Monolingual and multilingual information extraction and retrieval.
Question answering systems.
Evaluation of NLP systems.
Automatic textual content analysis.
Sentiment analysis and argument mining.
Plagiarism detection.
Negation and speculation processing.
Text mining in social media.
Text summarization.
Text simplification.
NLP in the biomedical domain.
NLP-based generation of teaching resources.
NLP for languages with limited resources.
NLP industrial applications.
Low-resource NLP tasks, data augmentation.
Ethics and NLP.
Interpretability and Analysis of Models for NLP.
Structure of the Conference
The SEPLN-CEDI 2024 Seminar will be a one-day event and will include sessions to present ongoing research projects and prototype or product demos related to the topics of the conference.
Paper types and author guidelines
The SEPLN-CEDI 2024 Seinar will accept two kinds of papers: (1) research project summaries and (2) system demonstration papers.
Research project summaries. They are summaries of ongoing research projects. This kind of papers must include the following information:
Project title.
Author name, affiliation and contact information. The review of this kind of paper is not blind review.
Funding institutions.
Research Groups participating in the project.
Language: English. We will not accept research project summaries in Spanish or other languages.
An abstract of a maximum of 150 words and a list of keywords.
Minimum length: 5 A4-size pages.
Maximum length: 6 A4-size pages (including references).
In the submission platform you have to choose “Projects and Demos” as main topic.
System demonstration papers. These papers must be related to NLP applications, and they must describe the technical details and the NLP components used or developed. The paper must be written in English, the minimum length of the paper must be 5 A4-size pages and the maximum length is 6 A4-size pages of content with the references included.
In the submission platform you have to choose “Projects and Demos” as main topic.
The research project summaries and the system demonstration papers will be published in CEUR Workshop Proceedings platform, which is widely known by the computer science research community. Accordingly, the paper format must be in accordance with the CEUR template. We have adapted the CEUR Latex Template to SEPLN 2023 and you can download it (Latex, Word).
Submission Information. The papers must be submitted by February 16th, 2024. All submissions must be in PDF format and submitted electronically using the MyReview system available.
Submitted papers will be subjected to a blind review by at least three members of the SEPLN advisory council.
Camera ready - the final version of the paper should be submitted together with a cover letter explaining how the suggestions of the reviewers were implemented in the final version. This cover letter will be considered in order to accept or finally reject the selected paper.
Preprint policy – The CEUR proceedings allows the publication of preprints (non-refereed paper posted online, such as ArXiv) anytime, but during the review period the preprint must indicate that the paper is “under review” in the CEUR Proceedings. Likewise, if the paper is accepted, the preprint must be updated with the DOI, name of the Journal and the bibliographic information of the paper.
Important dates
Deadline for the submission of projects and demos: Febraury 16th, 2024.
Notification of acceptance: March 16th, 2024.
Deadline Authors Registration: April 8th, 2024
Camera Ready: May 8th, 2024.
Conference: June 20th, 2024.
Organizing Committee
Rafael Muñoz Guillena University of Alicante (Spain).
Elena Lloret Pastor University of Alicante (Spain).
Eugenio Martínez Cámara University of Granada (Spain).
Alba Bonet University of Alicante (Spain)
Robiert Sepúlveda University of Alicante (Spain)
Alvaro Rodrigo Yuste UNED (Spain)
Contact
All information related to the conference can be found at: https://seplncedi2024.gplsi.es
For all general enquiries, please contact: seplncedi2024(a)googlegroups.com
-------------------------------------------------------------------------
Rafael Muñoz Guillena
Universidad de Alicante
-------------------------------------------------------------------------
‘Language in the Human-Machine Era’ (https://lithme.eu/) welcomes everyone interested in the impact of new and emerging language technologies that integrate with human senses. Whether you are a tech developer who wants to learn more about linguistics, or a linguist who wants to know more about tech, we want to hear from you! You can find out more about our themes of interest from our published forecast report (https://doi.org/10.17011/jyx/reports/20210518/1) and our animations (https://lithme.eu/animations). Funding is available to people in European countries and in countries neighbouring Europe (see https://www.cost.eu/about/strategy/cost-global-networking/). Self-funded applicants from any country are also welcome, with no registration fee.
LITHME’s overall aim is to prepare for imminent changes in the way we use technology to communicate. From immersive augmented reality to super-intelligent chatbots, in the near future we will be communicating in very different ways. This will present significant challenges for all areas of linguistics and language research; meanwhile, developers need insights from linguistic research to improve the technologies themselves. So we must all adapt.
Our fully funded training school is open to any eligible researcher or practitioner who is interested in exploring these timely topics. We welcome experienced developers, but no technological expertise is required, only an interest in exploring the possible effects of these near-future advances in language technology.
More information about eligibility, and the online application form, can be found at https://lithme.eu/training-school-2024/<https://lithme.eu/training-school/>. The deadline for applications is Tuesday 19 Dec 2023, 12:00 CET.
Please forward this email on to anyone who may be interested, and please repost the announcement here:
https://twitter.com/LgHumanMachine/status/1724750085907484672https://bsky.app/profile/lghumanmachine.bsky.social/post/3ke7xbuozl22k
We hope to see you in Hradec Králové!
Best wishes,
Rui Sousa-Silva (on behalf of the training school organising committee)
Rui Sousa Silva
Faculdade de Letras, Universidade do Porto
Faculty of Arts and Humanities, University of Porto
www.linguisticaforense.pt | https://s.up.pt/qjur
*LaTeCH-CLfL 2024:
The 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural
Heritage, Social Sciences, Humanities and Literature
*
to be held in March 2024 in conjunction with EACL 2024
<https://2024.eacl.org/> in St Julian’s, Malta.
https://sighum.wordpress.com/latech-clfl-2024/
Second Call for Papers (with apologies for cross-posting)
Organisers: Yuri Bizzoni, Stefania Degaetano-Ortlieb, Anna Kazantseva,
Stan Szpakowicz
LaTeCH-CLfL 2024 is the eighth in a series of meetings for NLP
researchers who work with data from the broadly understood arts,
humanities and social sciences, and for specialists in those disciplines
who apply NLP techniques in their work. The workshop continues a long
tradition of annual meetings. The SIGHUM Workshops on Language
Technology for Cultural Heritage, Social Sciences, and Humanities
(LaTeCH) ran ten times in 2007-2016. The five Workshops on Computational
Linguistics for Literature (CLfL) took place in 2012-2016. The first
seven joint workshops (LaTeCH-CLfL) were held in 2017-2023.
*Topics and content*
In the Humanities, Social Sciences, Cultural Heritage and literary
communities, there is increasing interest in, and demand for, NLP
methods for semantic and structural annotation, intelligent linking,
discovery, querying, cleaning and visualization of both primary and
secondary data. This is even true of primarily non-textual collections,
given that text is also the pervasive medium for metadata. Such
applications pose new challenges for NLP research: noisy, non-standard
textual or multi-modal input, historical languages, vague research
concepts, multilingual parts within one document, and so no. Digital
resources often have insufficient coverage; resource-intensive methods
require (semi-)automatic processing tools and domain adaptation, or
intense manual effort (e.g., annotation).
Literary texts bring their own problems, because navigating this form of
creative expression requires more than the typical information-seeking
tools. Examples of advanced tasks include the study of literature of a
certain period, author or sub-genre, recognition of certain literary
devices, or quantitative analysis of poetry.
NLP methods applied in this context not only need to achieve high
performance, but are often applied as a first step in research or
scholarly workflow. That is why it is crucial to interpret model results
properly; model interpretability might be more important than raw
performance scores, depending on the context.
More generally, there is a growing interest in computational models
whose results can be used or interpreted in meaningful ways. It is,
therefore, of mutual benefit that NLP experts, data specialists and
Digital Humanities researchers who work in and across their domains get
involved in the Computational Linguistics community and present their
fundamental or applied research results. It has already been
demonstrated how cross-disciplinary exchange not only supports work in
the Humanities, Social Sciences, and Cultural Heritage communities but
also promotes work in the Computational Linguistics community to build
richer and more effective tools and models.
Topics of interest include, but are not limited to, the following:
• adaptation of NLP tools to Cultural Heritage, Social Sciences,
Humanities and literature;
• automatic error detection and cleaning of textual data;
• complex annotation schemas, tools and interfaces;
• creation (fully- or semi-automatic) of semantic resources;
• creation and analysis of social networks of literary characters;
• discourse and narrative analysis/modelling, notably in literature;
• emotion analysis for the humanities and for literature;
• generation of literary narrative, dialogue or poetry;
• identification and analysis of literary genres;
• interpretability of large language models output for
DH-related tasks (explainable AI);
• linking and retrieving information from different sources,
media, and domains;
• low-resource and historical language processing;
• modelling dialogue literary style for generation;
• modelling of information and knowledge in the Humanities,
Social Sciences, and Cultural Heritage;
• profiling and authorship attribution;
• search for scientific and/or scholarly literature;
• work with linguistic variation and non-standard or historical
use of language.
*Information for authors*
We invite papers on original, unpublished work in the topic areas of the
workshop. In addition to long papers, we will consider short papers and
system descriptions (demos). We also welcome position papers.
• Long papers, presenting completed work, may consist of up to
eight (8) pages of content plus additional pages of references (just two
if possible -:). The final camera-ready versions of accepted long papers
will be given one additional page of content (up to 9 pages) so that
reviewers’ comments can be taken into account.
• A short paper / demo presenting work in progress, or the
description of a system, and may consist of up to four (4) pages of
content plus additional pages of references (one if you can). Upon
acceptance, short papers will be given five (5) content pages in the
proceedings.
• A position paper — clearly marked as such — should not exceed
eight (8) pages including references.
All submissions are to use the EACL stylesheets (for LaTeX / Overleaf
and MS Word); there will be a link soon (we hope) but last year's
https://2023.eacl.org/calls/styles is a good guess. Papers should be
submitted electronically, only in PDF, via the LaTeCH-CLfL2024
submission website on the SoftConf pages at
https://softconf.com/eacl2024/LaTeCH-CLfL-2024/.
Reviewing will be double-blind. Please do not include the authors’ names
and affiliations, or any references to Web sites, project names,
acknowledgements and so on — anything that immediately reveals the
authors’ identity. Self-references should be kept to a reasonable
minimum, and anonymous citations cannot be used. We will make an
exception for demo papers: the review may be single-blind.
Accepted papers will be published in the workshop proceedings available
as usual in the ACL Anthology.
*Important dates* (still tentative)
Workshop paper due: December 18, 2023
Notification of acceptance: January 20, 2024
Camera-ready papers due: January 30 2024
Workshop date: March 21 or 22, 2024
*More on the organizers*
Yuri Bizzoni, Center for Humanities Computing / School for Communication
and Culture, Århus University
Stefania Degaetano-Ortlieb, Language Science and Technology, Saarland
University
Anna Kazantseva, National Research Council Canada
Stan Szpakowicz, School of Electrical Engineering and Computer Science,
University of Ottawa
*Contact*
latech-clfl(a)googlegroups.com