Proceedings

Published in CEUR-WS: https://ceur-ws.org/Vol-3625/

Objective

The Doctoral Symposium intends to provide a venue for student researchers in Natural Language Processing to present their work. Students will receive constructive feedback and guidance from researchers with experience in their area of work.

Importantes dates

  • Proposals submission: June 19, 2023
  • Review period: June 20, 2023 – July 14, 2023
  • Notification of review: July 21, 2023
  • Doctoral Symposium (SEPLN 2023): September 28, 2023
  • Publication of proceedings in CEUR: November, 2023

Instructions for authors

  • Papers should include, among others, the following sections:
    • Reason for the proposed research;
    • Background and related work (including important references);
    • Description of the proposed research, including the main hypotheses for research;
    • Methodology and the proposed experiments (if necessary);
    • Specific issues of research to be discussed;
    • References
  • Papers must be signed by a single person (predoctoral candidate) and must conform to the CEUR format. For this purpose, the CEUR template in LaTeX or Word format or the template provided through Overleaf (1 column format) should be used.
  • Papers should be between 5 and 9 pages in length (including references) and should be written in English.
  • The conference name should be replaced by: \conference{Doctoral Symposium on Natural Language Processing from the PERTE Nueva Economía de la Lengua, 28 September 2023, Jaén, Spain.}
  • The author’s name will be formed by the full name (without initials), e.g. “María Pérez” instead of “M. Pérez”.
  • The title should be written using the emphasizing capitalized style, e.g. “Filling an Author Agreement by Autocompletion” instead of “Filling an author agreement by autocompletion”.
  • Authors must complete and sign by hand this agreement, which will be sent with the paper through the following Google Form.

Registration, travel and accommodation

The registration type for students who will participate in the symposium is “PhD Symposium fee”. This has a cost of zero euros.

Once the article has been submitted, the symposium organisers will contact each student to arrange travel and accommodation in Jaén.

Topics

  • Mathematical and psycholinguistic language models
  • Machine Learning in NLP
  • Computer Lexicography and Terminology
  • Corpus linguistics
  • Development of linguistic resources and tools
  • Grammars and formalisms for morphological and syntactic analysis
  • Semantics, pragmatics, and discourse
  • Resolution of lexical ambiguity
  • Monolingual and multilingual text generation
  • Automatic translation
  • Speech recognition and synthesis
  • Dialogue systems
  • Auto-indexation
  • Monolingual and multilingual information retrieval and extraction
  • Search systems for answers
  • Evaluation of NLP systems
  • Automatic analysis of text content
  • Sentiment analysis and opinion mining
  • Plagiarism detection
  • Negation processing and speculation
  • Text mining in the blogosphere and social networks
  • Automatic text overview
  • Language generation
  • Image recovery
  • NLP in the biomedical field
  • Generation of educational resources based on NLP
  • NLP for languages with limited resources
  • NLP industrial applications

Organizing committee

María Teresa Martín Valdivia. Universidad de Jaén (España)

Eugenio Martínez Cámara. Universidad de Jaén (España)

María Dolores Molina González. Universidad de Jaén (España)

Salud María Jiménez Zafra. Universidad de Jaén (España)