Guest Editors

Florian Boudin, JFLI/LS2N, Nantes University
Akiko Aizawa, National Institute of Informatics

Guest Reviewers

Iana Atanassova, CRIT, Université de Franche-Comté
Davide Buscaldi, LIPN, Université Paris 13
Beatrice Daille, LS2N, Nantes Université
Liana Ermakova, HCTI, Université de Bretagne Occidentale

Context

The body of scholarly literature is steadily and rapidly expanding. In arXiv alone, the number of scientific articles submitted in 2022 exceeded 185,000, averaging nearly 500 submissions per day. In the face of this exponential growth, researchers and institutions are continually challenged to keep pace with the sheer volume of new knowledge being created. Automated methods for analyzing and interpreting scientific papers are therefore urgently needed to assist researchers in navigating through the expanding volume of scientific information, enabling more efficient and targeted acquisition of new knowledge across various fields. More precisely, the development of methods capable of extracting reliable, valuable and verifiable information from scientific papers is crucial for many downstream tasks including retrieval, recommendation, summarization, question-answering and document understanding.

The uniqueness of scientific papers, marked by intricate technical language, discipline-specific terminology, a distinct structural organization and the inclusion of complex elements such as equations, tables, and figures, poses a significant challenge for existing natural language processing and information retrieval methods. Furthermore, these methods should also account for additional features provided at the collection level (e.g., citation networks) or embedded in rich paper metadata (e.g., authors, keywords, publication venues), each introducing its own set of challenges. This special issue of the TAL journal is dedicated to papers describing work that address these challenges, and more broadly to papers describing research on *natural language processing and information retrieval of scholarly and scientific documents*. Relevant topics for this issue include, but are not limited to, the following areas (in alphabetical order):

- Bibliometrics, scientometrics
- Citation analysis and recommendation
- Claim verification
- Datasets, tools and resources
- Information extraction, NER
- Large Language Models (LLMs)
- Plagiarism detection
- Question-answering
- Retrieval and recommendation
- Scientific document analysis
- Scientific writing assistance
- Text simplification
- Summarization and generation

IMPORTANT DATES

• Submission deadline: March, 15th 2024
  
• Notification to the authors after first review: May 2024
  
• Notification to the authors after second review: September, 2024
  
• Publication : December, 2024

THE JOURNAL

TAL (Traitement Automatique des Langues / Natural Language Processing) is an international journal published by ATALA (French Association for Natural Language Processing, http://www.atala.org) since 1959 with the support of CNRS (National Centre for Scientific Research). TAL has an electronic mode of publication.