Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.6
2.2
Journals
Mathematics
Special Issues
Mathematical Foundations in NLP: Applications and Challenges
share announcement

Mathematical Foundations in NLP: Applications and Challenges

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 15436

Special Issue Editors

Dr. Jizheng Wan

E-Mail Website
Guest Editor
School of Computer Science, University of Birmingham, Birmingham B15 2TT, UK
Interests: artificial intelligence; natural language processing; machine learning & deep learning; knowledge graph
Dr. Mubashir Ali

E-Mail Website
Guest Editor
School of Computer Science, University of Birmingham, Birmingham B15 2TT, UK
Interests: data science; machine learning; natural language processing; time series analysis

Special Issue Information

Dear Colleagues,

We are pleased to invite you to contribute to our Special Issue, titled "AI for Natural Language Processing: Applications and Challenges". The field of Natural Language Processing (NLP) has witnessed significant growth and innovation, driven by advancements in Artificial Intelligence (AI). As AI continues to evolve, its applications in NLP are becoming increasingly sophisticated, enabling machines to understand, interpret, and generate human language with unprecedented accuracy.

NLP is at the core of many transformative technologies, including chatbots, machine translation, sentiment analysis, and more. The integration of AI into NLP has opened new avenues for research, allowing for the development of models and algorithms that can handle the complexity and nuances of human language. This Special Issue aims to bring together cutting-edge research that explores the intersection of AI and NLP, showcasing the latest methodologies, applications, and theoretical advancements.

This Special Issue aims to highlight the latest research contributions that advance our understanding and application of AI in NLP. Its goal is to provide a platform for researchers to share innovative solutions and new theoretical insights that push the boundaries of what is possible in this dynamic field. By aligning with the broader scope of this journal, this Special Issue will offer a comprehensive overview of the current state of AI-driven NLP, while also identifying emerging trends and future directions.

We are particularly interested in contributions that address challenges and opportunities in this area, including, but not limited to, improvements in machine learning models, novel applications of deep learning in NLP, and interdisciplinary approaches that combine AI with other fields, such as cognitive science, linguistics, and data science.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but need not be limited to) the following:

  • AI-driven Text Processing: Innovations in algorithms and models for text analysis, including parsing, tagging, and sentiment analysis.
  • Large Language Models (LLMs) and their applications: Exploration of large-scale pre-trained models like GPT, BERT, and others that have transformed the landscape of NLP by enabling high-quality text generation, comprehension, and translation.
  • Deep Learning in NLP: Applications of neural networks and other deep learning techniques in understanding and generating natural language.
  • Machine Translation: Advances in AI techniques that improve the accuracy and fluency of machine translation systems.
  • Speech Recognition and Synthesis: AI methods for converting spoken language into text and vice versa, with a focus on accuracy and naturalness.
  • Ethical AI in NLP: Discussions on the ethical implications of AI in language processing, including issues related to bias, fairness, and transparency.
  • Multilingual and Cross-lingual NLP: AI approaches to processing and understanding languages beyond English, with an emphasis on resource-scarce languages.
  • Interactive and Conversational AI: Development of AI systems that can engage in natural and meaningful conversations with humans.
  • Question Answering (QA) Systems: Research on AI-driven systems designed to answer questions posed in natural language, including advancements in accuracy, context understanding, and real-time processing.

We look forward to receiving your contributions and believe that this Special Issue will serve as a valuable resource for researchers and practitioners working at the forefront of AI in NLP.

Dr. Jizheng Wan
Dr. Mubashir Ali
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 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. Mathematics 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 2600 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

  • NLP; LLMs; machine learning; deep learning; text generation; speech recognition; sentiment analysis; conversational AI; ethical AI

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 (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

24 pages, 2575 KB  
Article
An Intelligent Predictive Fairness Model for Analyzing Law Cases with Feature Engineering
by Ahmed M. Shamsan Saleh, Yahya AlMurtadha and Abdelrahman Osman Elfaki
Mathematics 2026, 14(2), 244; https://doi.org/10.3390/math14020244 - 8 Jan 2026
Viewed by 214
Abstract
Artificial intelligence (AI) is transforming numerous sectors, and its integration into the legal domain holds significant potential for automating labor-intensive tasks, enhancing judicial decision-making, and improving overall system efficiency. This study introduces an AI-powered model, named the Legal Judgment Prediction Ensemble (LJPE), which [...] Read more.
Artificial intelligence (AI) is transforming numerous sectors, and its integration into the legal domain holds significant potential for automating labor-intensive tasks, enhancing judicial decision-making, and improving overall system efficiency. This study introduces an AI-powered model, named the Legal Judgment Prediction Ensemble (LJPE), which is designed to predict legal case outcomes by leveraging historical judicial data. By using natural language processing (NLP) techniques, feature engineering, and a complex two-level stacking ensemble, the LJPE model has better predictive accuracy at 94.68% compared to modern legal language and conventional machine learning models. Moreover, the findings underline the predictive strength of textual features obtained from case facts, vote margins, and legal-specific features. This study offers a solid technical solution for predicting legal judgments for the responsible use of the model, helping to create a more efficient, transparent, and fair legal system. Full article
(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
►▼ Show Figures

Figure 1

37 pages, 372 KB  
Article
Emotion and Intention Detection in a Large Language Model
by Emmanuel Castro, Hiram Calvo and Olga Kolesnikova
Mathematics 2025, 13(23), 3768; https://doi.org/10.3390/math13233768 - 24 Nov 2025
Viewed by 2249
Abstract
Large language models (LLMs) have recently shown remarkable capabilities in natural language processing. In this work, we investigate whether an advanced LLM can recognize user emotions and intentions from text, focusing on the open-source model DeepSeek. We evaluate zero-shot emotion classification and dialog [...] Read more.
Large language models (LLMs) have recently shown remarkable capabilities in natural language processing. In this work, we investigate whether an advanced LLM can recognize user emotions and intentions from text, focusing on the open-source model DeepSeek. We evaluate zero-shot emotion classification and dialog act (intention) classification using two benchmark conversational datasets (IEMOCAP and MELD). We test the model under various prompting conditions, including those with and without conversational context, as well as with auxiliary information (dialog act labels or emotion labels). Our results show that DeepSeek achieves an accuracy of up to 63% in emotion recognition on MELD, utilizing context and dialog-act information. In the case of intention recognition, the model improved from 45% to 61% with the aid of context, but no further improvement was observed with the provision of emotional cues. Supporting the hypothesis that providing conversational context aids emotion and intention detection. However, conversely, adding emotion cues did not enhance intent classification, suggesting an asymmetric relationship. These findings highlight both the potential and limitations of current LLMs in understanding affective and intentional aspects of dialogue. For comparison, we also ran the same emotion and intention detection tasks on GPT-4 and Gemini-2.5. DeepSeek-r1 performed as well as Gemini-2.5 and better than GPT-4, confirming its place as a strong, competitive model in the field. Full article
(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
►▼ Show Figures

Figure 1

35 pages, 7934 KB  
Article
Analyzing Diagnostic Reasoning of Vision–Language Models via Zero-Shot Chain-of-Thought Prompting in Medical Visual Question Answering
by Fatema Tuj Johora Faria, Laith H. Baniata, Ahyoung Choi and Sangwoo Kang
Mathematics 2025, 13(14), 2322; https://doi.org/10.3390/math13142322 - 21 Jul 2025
Viewed by 5561
Abstract
Medical Visual Question Answering (MedVQA) lies at the intersection of computer vision, natural language processing, and clinical decision-making, aiming to generate accurate responses from medical images paired with complex inquiries. Despite recent advances in vision–language models (VLMs), their use in healthcare remains limited [...] Read more.
Medical Visual Question Answering (MedVQA) lies at the intersection of computer vision, natural language processing, and clinical decision-making, aiming to generate accurate responses from medical images paired with complex inquiries. Despite recent advances in vision–language models (VLMs), their use in healthcare remains limited by a lack of interpretability and a tendency to produce direct, unexplainable outputs. This opacity undermines their reliability in medical settings, where transparency and justification are critically important. To address this limitation, we propose a zero-shot chain-of-thought prompting framework that guides VLMs to perform multi-step reasoning before arriving at an answer. By encouraging the model to break down the problem, analyze both visual and contextual cues, and construct a stepwise explanation, the approach makes the reasoning process explicit and clinically meaningful. We evaluate the framework on the PMC-VQA benchmark, which includes authentic radiological images and expert-level prompts. In a comparative analysis of three leading VLMs, Gemini 2.5 Pro achieved the highest accuracy (72.48%), followed by Claude 3.5 Sonnet (69.00%) and GPT-4o Mini (67.33%). The results demonstrate that chain-of-thought prompting significantly improves both reasoning transparency and performance in MedVQA tasks. Full article
(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
►▼ Show Figures

Figure 1

24 pages, 595 KB  
Article
An Empirical Comparison of Machine Learning and Deep Learning Models for Automated Fake News Detection
by Yexin Tian, Shuo Xu, Yuchen Cao, Zhongyan Wang and Zijing Wei
Mathematics 2025, 13(13), 2086; https://doi.org/10.3390/math13132086 - 25 Jun 2025
Cited by 6 | Viewed by 3252
Abstract
Detecting fake news is a critical challenge in natural language processing (NLP), demanding solutions that balance accuracy, interpretability, and computational efficiency. Despite advances in NLP, systematic empirical benchmarks that directly compare both classical and deep models—across varying input richness and with careful attention [...] Read more.
Detecting fake news is a critical challenge in natural language processing (NLP), demanding solutions that balance accuracy, interpretability, and computational efficiency. Despite advances in NLP, systematic empirical benchmarks that directly compare both classical and deep models—across varying input richness and with careful attention to interpretability and computational tradeoffs—remain underexplored. In this study, we systematically evaluate the mathematical foundations and empirical performance of five representative models for automated fake news classification: three classical machine learning algorithms (Logistic Regression, Random Forest, and Light Gradient Boosting Machine) and two state-of-the-art deep learning architectures (A Lite Bidirectional Encoder Representations from Transformers—ALBERT and Gated Recurrent Units—GRUs). Leveraging the large-scale WELFake dataset, we conduct rigorous experiments under both headline-only and headline-plus-content input scenarios, providing a comprehensive assessment of each model’s capability to capture linguistic, contextual, and semantic cues. We analyze each model’s optimization framework, decision boundaries, and feature importance mechanisms, highlighting the empirical tradeoffs between representational capacity, generalization, and interpretability. Our results show that transformer-based models, especially ALBERT, achieve state-of-the-art performance (macro F1 up to 0.99) with rich context, while classical ensembles remain viable for constrained settings. These findings directly inform practical fake news detection. Full article
(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
►▼ Show Figures

Figure 1

18 pages, 901 KB  
Article
A Hierarchical Latent Modulation Approach for Controlled Text Generation
by Jincheng Zou, Guorong Chen, Jian Wang, Bao Zhang, Hong Hu and Cong Liu
Mathematics 2025, 13(5), 713; https://doi.org/10.3390/math13050713 - 22 Feb 2025
Viewed by 1833
Abstract
Generative models based on Variational Autoencoders (VAEs) represent an important area of research in Controllable Text Generation (CTG). However, existing approaches often do not fully exploit the potential of latent variables, leading to limitations in both the diversity and thematic consistency of the [...] Read more.
Generative models based on Variational Autoencoders (VAEs) represent an important area of research in Controllable Text Generation (CTG). However, existing approaches often do not fully exploit the potential of latent variables, leading to limitations in both the diversity and thematic consistency of the generated text. To overcome these challenges, this paper introduces a new framework based on Hierarchical Latent Modulation (HLM). The framework incorporates a hierarchical latent space modulation module for the generation and embedding of conditional modulation parameters. By using low-rank tensor factorization (LMF), the approach combines multi-layer latent variables and generates modulation parameters based on conditional labels, enabling precise control over the features during text generation. Additionally, layer-by-layer normalization and random dropout mechanisms are employed to address issues such as the under-utilization of conditional information and the collapse of generative patterns. We performed experiments on five baseline models based on VAEs for conditional generation, and the results demonstrate the effectiveness of the proposed framework. Full article
(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
►▼ Show Figures

Figure 1

Review

Jump to: Research

42 pages, 571 KB  
Review
Integrating Cognitive, Symbolic, and Neural Approaches to Story Generation: A Review on the METATRON Framework
by Hiram Calvo, Brian Herrera-González and Mayte H. Laureano
Mathematics 2025, 13(23), 3885; https://doi.org/10.3390/math13233885 - 4 Dec 2025
Cited by 1 | Viewed by 1126
Abstract
The human ability to imagine alternative realities has long supported reasoning, communication, and creativity through storytelling. By constructing hypothetical scenarios, people can anticipate outcomes, solve problems, and generate new knowledge. This link between imagination and reasoning has made storytelling an enduring topic in [...] Read more.
The human ability to imagine alternative realities has long supported reasoning, communication, and creativity through storytelling. By constructing hypothetical scenarios, people can anticipate outcomes, solve problems, and generate new knowledge. This link between imagination and reasoning has made storytelling an enduring topic in artificial intelligence, leading to the field of automatic story generation. Over the decades, different paradigms—symbolic, neural, and hybrid—have been proposed to address this task. This paper reviews key developments in story generation and identifies elements that can be integrated into a unified framework. Building on this analysis, we introduce the METATRON framework for neuro-symbolic generation of fiction stories. The framework combines a classical taxonomy of dramatic situations, used for symbolic narrative planning, with fine-tuned language models for text generation and coherence filtering. It also incorporates cognitive mechanisms such as episodic memory, emotional modeling, and narrative controllability, and explores multimodal extensions for text–image–audio storytelling. Finally, the paper discusses cognitively grounded evaluation methods, including theory-of-mind and creativity assessments, and outlines directions for future research. Full article
(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop