Call for Papers: Natural Language Processing for Health and Accessibility

The journal Traitement Automatique des Langues (TAL) invites submissions for a special issue dedicated to NLP for Health and Accessibility. This issue aims to explore the potential contributions of NLP in rapidly evolving fields such as medicine, public health, disability, accessibility, and, more broadly, in contexts of care, prevention, and assistance.

NLP plays an increasingly important role in digital systems designed to improve healthcare delivery, accessibility, and quality. Positioned at the intersection of computational linguistics, artificial intelligence, and health sciences, this field holds significant promise, but also raises major technical, ethical, methodological, and societal challenges. This special issue seeks to bring together research work that explores, supports, or questions the role of NLP in these complex environments, taking into account the diversity of target populations, disability situations, and medical contexts.

One potential analytical framework is that of so-called “6P medicine” — Preventive, Personalized, Predictive, Participatory, Pathway-based, and Proof-based — which proposes an integrated and proactive approach to healthcare. NLP can act as a catalyst for leveraging massive, often unstructured textual data (medical records, patient feedback, scientific literature, etc.). These technologies could eventually facilitate early identification of clinical signals, treatment personalization, risk modeling, or care pathway analysis. However, many challenges remain: managing data variability, evaluating performance in real-world settings, ensuring model interpretability, mitigating algorithmic biases, and more. This issue therefore encourages contributions that address these research challenges without assuming that solutions are already fully developed or generalizable.

In parallel, this issue aims to open space for contributions focused on accessibility challenges and the needs of people with disabilities, who are often marginalized in mainstream NLP approaches. Linguistic technologies can play a crucial role in improving access to information, supporting communication, and fostering autonomy: text simplification, generation of easy-toread content, voice interfaces, navigation assistants, intelligent screen readers, and even sign language processing and translation. These developments also raise important questions about evaluation, co-design with affected users, and integration into diverse social and institutional contexts. The intersection of NLP, disability, and accessibility thus constitutes a rich field for
innovation, at the crossroads of language technologies, digital humanities, and social justice.

This special issue welcomes a wide range of contributions: case studies, critical reflections, methodological developments, system evaluations, or interdisciplinary analyses. Particular attention will be given to submissions that cross disciplinary boundaries, that make use of under-explored corpora or underrepresented languages, and that address issues of equity, ethics, or inclusivity in tool design.

This special issue seeks original and high-quality research papers focusing on technical and theoretical challenges and advancements in NLP for health and disability. We welcome contributions in the following areas or related topics (the list is not exhaustive):

• Modeling clinical text in standard NLP tasks: challenges in tagging, chunking, parsing, entity identification, entity linking/normalization, relation extraction, coreference resolution, and summarization within clinical contexts.
• De-identification and privacy: handling protected health information through deidentification methods and ensuring privacy compliance using techniques such as differential privacy for sensitive health data.
• Disease detection and clinical document coding: automating the coding of clinical documents (e.g., ICD-10) and detecting diseases from unstructured medical text, including disease classification.
• Structuring clinical documents: identifying and categorizing sections within clinical documents (e.g., medical history, diagnoses, treatments) to improve document organization and facilitate automated processing.
• Information extraction from clinical text: Extracting structured information, such as medical entities and relationships, from unstructured clinical text to create actionable insights for decision support.
• Integration of structured and textual data: combining structured (e.g., lab results) and unstructured (e.g., clinical notes) data for enhanced analysis and clinical decision-making, addressing the challenges of multimodal data integration.
• Domain adaptation and transfer learning: applying transfer learning and domain adaptation techniques to adapt NLP models for clinical tasks across different healthcare environments and domains, including specialty-specific language.
• Generation of clinical notes: techniques for generating clinical notes, such as summarizing patient encounters and generating clinical notes from clinical conversations or dictations.
• Annotation schemes and methodology: developing robust annotation schemes and methodologies to annotate clinical data accurately for training NLP models, addressing challenges in consistent labeling of complex medical information.
• Evaluation techniques for clinical NLP: developing specialized evaluation metrics and techniques for assessing the performance of NLP models in clinical applications, including accuracy, usability, and safety.
• Bias and fairness in clinical text: addressing the presence of bias in clinical NLP systems and ensuring fairness, especially when dealing with diverse patient populations, underrepresented groups, and healthcare disparities.
• Explainable and interpretable models: enhancing model transparency and interpretability in critical health applications, including feature attribution and causal analysis.
• Multimodal approaches: integration of textual data with images, speech, or sensor data using cross-modal learning and fusion techniques for comprehensive analysis.
• NLP for disability and accessibility: adapting NLP models to address health-related data on disability, including the design of assistive technologies, the interpretation of patient narratives on accessibility challenges, the processing of sign language, and the enhancement of inclusion in health-related information and tools.

By focusing on technical innovations, theoretical advancements, and addressing critical challenges in NLP for health and disability, this special issue aims to advance the field while aligning with the principles of 6P medicine. We look forward to your submissions!

IMPORTANT DATES

• Submission deadline: October 20th, 2025 
  
• Notification to the authors after first review: December 15th, 2025
  
• Notification to the authors after second review: March 16th, 2026
  
• Publication : June, 2026

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.