applsci-logo

Journal Browser

Journal Browser

Construction of Knowledge System Based on Natural Language Processing

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 30 September 2026 | Viewed by 2603

Special Issue Editor


E-Mail Website
Guest Editor
Institute of Artificial Intelligence, Beihang University, Beijing, China
Interests: trustworthy large language models; AI for science

Special Issue Information

Dear Colleagues,

The rapid advancement of natural language processing (NLP) has profoundly reshaped how knowledge is acquired, represented, and utilized across scientific, industrial, and societal domains. With the emergence of large language models, knowledge graphs, and multimodal foundation models, there is a growing opportunity to move beyond isolated understanding of a text toward the systematic construction of machine-interpretable knowledge systems. Such systems aim to organize, integrate, and reason over large-scale, heterogeneous knowledge sources, enabling more robust intelligent decision-making, scientific discovery, and trustworthy AI applications. Despite notable progress, significant challenges remain in knowledge extraction, representation, alignment, reasoning, evolution, and validation, particularly in complex, dynamic, and domain-specific environments. Addressing these challenges is critical for advancing NLP from surface-level language processing to deep semantic understanding and knowledge-centric intelligence.

We are pleased to invite you to contribute to the Special Issue “Construction of Knowledge System Based on Natural Language Processing”, which aims to provide a focused forum for presenting research regarding recent advances, theoretical foundations, and practical systems that leverage NLP techniques to construct, maintain, and apply structured knowledge systems. This Issue seeks to bridge NLP, knowledge representation, machine reasoning, and domain applications, fostering interdisciplinary research that promotes scalable, explainable, and trustworthy knowledge-driven AI.

Suggested themes and article types for submission:

In this Issue, original research articles and review papers are welcome. Topics of interest include, but are not limited to, the following:

  • Knowledge extraction and structuring from unstructured and semi-structured text;
  • Knowledge graph construction, completion, and evolution using NLP methods;
  • Large language models for knowledge acquisition, organization, and reasoning;
  • Hybrid approaches combining symbolic knowledge systems and neural language models;
  • Multimodal knowledge system construction integrating text, vision, and other data sources;
  • Domain-specific knowledge systems for science, medicine, finance, law, and engineering;
  • Causality, reasoning, and inference over knowledge systems;
  • Knowledge quality assessment, uncertainty modeling, and trustworthiness;
  • Evaluation benchmarks and datasets for knowledge-centric NLP;
  • Applications of NLP-based knowledge systems in real-world intelligent systems.

We look forward to your contributions and to fostering a vibrant exchange of ideas that will advance the construction and application of knowledge systems grounded in natural language processing.

Prof. Dr. Lei Sha
Guest Editor

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 250 words) can be sent to the Editorial Office for assessment.

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. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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.

Keywords

  • LLM
  • NLP
  • knowledge graph
  • causality reasoning

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

20 pages, 3017 KB  
Article
Deep-Research Eval: An Automated Framework for Assessing Quality and Reliability in Long-Form Reports
by Yeerpan Tuohetiyaer, Yuye Zhu, Yan Hu, Siyuan Lu and Zhongfeng Wang
Appl. Sci. 2026, 16(5), 2546; https://doi.org/10.3390/app16052546 - 6 Mar 2026
Viewed by 2357
Abstract
Deep Research Agents (DRAs) generate detailed literature surveys but often suffer from hallucinations and inconsistent structures. Existing evaluation methods face significant limitations. Human evaluation is time-consuming and requires domain expertise. Meanwhile, current LLM judges struggle with long reports due to context limits and [...] Read more.
Deep Research Agents (DRAs) generate detailed literature surveys but often suffer from hallucinations and inconsistent structures. Existing evaluation methods face significant limitations. Human evaluation is time-consuming and requires domain expertise. Meanwhile, current LLM judges struggle with long reports due to context limits and the inability to verify source reliability. To address this, we propose Deep-Research Eval. This framework standardizes the page as the basic unit for evaluation. It features an adaptive scoring system that assesses the logical quality of each page. Furthermore, it employs Paged-RAG with a constructible reference database to verify facts against specific evidence. Experiments on five agents show that our method effectively identifies errors. It achieves a strong correlation with human judgment, reaching a Composite Consistency Index (CCI) of 0.7585, an absolute increase of 0.4588 over baselines. Additionally, the Paged-RAG module improves factual verification accuracy, increasing the QA-F1 score by up to 6.9 times compared to standard retrieval methods. This work offers a scalable and practical approach for assessing AI-generated academic content. Full article
(This article belongs to the Special Issue Construction of Knowledge System Based on Natural Language Processing)
Show Figures

Figure 1

Back to TopTop