Applications of Information Extraction, Knowledge Graphs, and Large Language Models

 Dear Colleagues,

Information extraction (IE), knowledge graphs (KGs), and large language models (LLMs) have emerged as powerful tools for organizing, analyzing, and harnessing the potential of vast amounts of data. This Special Issue aims to explore the synergies and applications of IE, KGs, and LLMs, showcasing their collective impact on information management, knowledge representation, and decision-making processes.

Information extraction involves automatically identifying and extracting structured information from unstructured or semi-structured data sources, such as text documents, websites, social media posts, and scientific literature. Knowledge graphs provide a powerful framework for representing and organizing knowledge, enabling efficient navigation, querying, and inference over interconnected entities and their relationships. Large language models, such as GPT-3.5, have pushed the boundaries of natural language understanding and generation, demonstrating remarkable capabilities in tasks such as text completion, translation, summarization, and question answering.

This Special Issue invites original research papers and reviews that showcase the combined applications, methodologies, and advancements in the field of information extraction, knowledge graphs, and large language models. We welcome submissions on, but not limited to, the following topics:

1. Knowledge Graph Construction: techniques and methodologies for constructing knowledge graphs from diverse data sources, incorporating the outputs of large language models for improved entity recognition, relation extraction, and ontology design.
2. Semantic Search and Recommendation Systems: leveraging the power of large language models and knowledge graphs to enhance search engines and recommendation systems, enabling more accurate and context-aware information retrieval and personalized recommendations.
3. Natural Language Processing (NLP) with Large Language Models: exploring the integration of large language models, such as GPT-3.5, with knowledge graphs for tasks such as question answering, sentiment analysis, summarization, and named entity recognition.
4. Knowledge Graphs in Healthcare and Life Sciences: harnessing the potential of information extraction, large language models, and knowledge graphs to facilitate biomedical data integration, clinical decision support systems, drug discovery, and personalized medicine.
5. Industry Applications and Ethical Considerations: Real-world case studies demonstrating the adoption and impact of combined IE, KG, and LLM technologies in various domains such as finance, e-commerce, manufacturing, transportation, and energy. Additionally, papers addressing the ethical implications and responsible use of large language models in knowledge extraction and representation are encouraged.

Papers that showcase innovative approaches, novel algorithms, and practical implementations that advance the state of the art in information extraction, knowledge graphs, and large language models are welcome. We particularly encourage papers that demonstrate the successful deployment of these technologies in real-world scenarios and their impact on decision making, knowledge discovery, and information management.

Dr. Junwen Duan
Dr. Fangfang Li
Dr. Tudor Groza
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• information extraction
• knowledge graphs
• large language model
• natural language processing
• healthcare applications
• industry applications
• data integration