EPIA 2026

Track Description

The Track on Natural Language, Text Mining and Applications (NLP-TeMA 2026) brings together researchers and practitioners working in Human Language Technologies, including Natural Language Processing (NLP), Computational Linguistics (CL), Natural Language Engineering (NLE), Text Mining (TM), Information Retrieval (IR), Large Language Model Research and Applications (LLMs), and related areas. As text remains the primary medium for creating and sharing knowledge, vast amounts of natural language data are generated daily across the Web and other digital platforms. This continuous growth presents significant opportunities and challenges for developing methods that can effectively understand, analyze, and extract value from textual information. Advances in NLP, Machine Learning, and Deep Learning have strengthened the role of language technologies in transforming semi-structured and unstructured data into actionable knowledge. NLP-TeMA 2026 welcomes contributions addressing both theoretical foundations and practical applications, fostering research that connects methodological innovation with real-world impact.

Topics of Interest

• Language and Cognitive Modeling
• Morphology, Word Segmentation, Tagging and Parsing
• Semantics, Discourse, Pragmatics and Text Inference
• Natural Language Understanding and Generation
• Language Modeling and Mathematical Properties of Language
• Lexical Resources, Acquisition and Word Sense Disambiguation
• Entity Recognition, Textual Entailment and Paraphrase
• NLP for Low-Resource and Multilingual Settings
• Machine Learning for NLP and Text Mining
• Large Language Models: Architectures, Tokenization, Prompting and Adaptation
• Text Clustering, Classification and Summarization
• Sentiment Analysis, Argument Mining and Offensive Speech Detection
• Information Retrieval and Information Extraction
• Question Answering and Dialogue Systems
• Machine Translation and Cross-Lingual Approaches
• Computational Social Science and Web Content Analysis
• Spatio-Temporal, Large-Scale and Predictive Text Mining
• Domain-Specific Text Mining Applications (e.g., Health, Biomedical, Legal)

Track Chairs

• Joaquim Silva - NOVA University Lisbon
• Pablo Gamallo - University of Santiago de Compostela
• Alípio Jorge - University of Porto