applsci-logo

Journal Browser

Journal Browser

Deep Learning and Its Applications in 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: 20 February 2026 | Viewed by 902

Special Issue Editors


E-Mail Website
Guest Editor
1. School of Computer Science and Information Systems, University of Melbourne, Melbourne, Australia
2. School of Computer Science, University of Sydney, Sydney, Australia
Interests: natural langauge processing; multimodal learning

E-Mail Website
Guest Editor
School of Computer Science, University of Sydney, Sydney, Australia
Interests: natural langauge processing; medical text mining

E-Mail Website
Guest Editor Assistant
School of Physics, Maths and Computing, Computer Science and Software Engineering, University of Western Australia, Perth, Australia
Interests: natural langauge processing; large language model

E-Mail Website
Guest Editor Assistant
School of Computing and Information Systems, University of Melbourne, Melbourne, Australia
Interests: natural langauge processing; visually rich document understanding

Special Issue Information

Dear Colleagues,

This Special Issue, entitled “Deep Learning and Its Applications in Natural Language Processing”, aims to showcase the latest advancements and innovative techniques in the intersection of deep learning and NLP. In recent years, deep learning has revolutionized the way that machines understand and generate human language, unlocking new capabilities across various NLP tasks such as machine translation, text summarization, sentiment analysis, and conversational agents. This Special Issue aims to explore both theoretical developments and practical applications, emphasizing emerging models like transformers, large language models, and multimodal architectures. We welcome contributions that address challenges such as model interpretability, bias mitigation, and multilingual understanding. In addition, we encourage submissions focused on novel methods for data augmentation, domain adaptation, and task-specific fine-tuning. By gathering insights from leading researchers, this Special Issue aims to provide an in-depth perspective on the evolving role of deep learning in NLP, contributing to our understanding and the development of future AI-driven language technologies.

Dr. Caren Han
Dr. Josiah Poon
Guest Editors

Dr. Siwen Luo
Dr. Yihao Ding
Guest Editor Assistants

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. 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

  • deep learning
  • natural language processing (NLP)
  • large language models (LLMs)
  • multimodal models
  • text generation
  • NLP applications
  • financial NLP
  • medical NLP

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

17 pages, 1467 KiB  
Article
Confidence-Based Knowledge Distillation to Reduce Training Costs and Carbon Footprint for Low-Resource Neural Machine Translation
by Maria Zafar, Patrick J. Wall, Souhail Bakkali and Rejwanul Haque
Appl. Sci. 2025, 15(14), 8091; https://doi.org/10.3390/app15148091 - 21 Jul 2025
Viewed by 317
Abstract
The transformer-based deep learning approach represents the current state-of-the-art in machine translation (MT) research. Large-scale pretrained transformer models produce state-of-the-art performance across a wide range of MT tasks for many languages. However, such deep neural network (NN) models are often data-, compute-, space-, [...] Read more.
The transformer-based deep learning approach represents the current state-of-the-art in machine translation (MT) research. Large-scale pretrained transformer models produce state-of-the-art performance across a wide range of MT tasks for many languages. However, such deep neural network (NN) models are often data-, compute-, space-, power-, and energy-hungry, typically requiring powerful GPUs or large-scale clusters to train and deploy. As a result, they are often regarded as “non-green” and “unsustainable” technologies. Distilling knowledge from large deep NN models (teachers) to smaller NN models (students) is a widely adopted sustainable development approach in MT as well as in broader areas of natural language processing (NLP), including speech, and image processing. However, distilling large pretrained models presents several challenges. First, increased training time and cost that scales with the volume of data used for training a student model. This could pose a challenge for translation service providers (TSPs), as they may have limited budgets for training. Moreover, CO2 emissions generated during model training are typically proportional to the amount of data used, contributing to environmental harm. Second, when querying teacher models, including encoder–decoder models such as NLLB, the translations they produce for low-resource languages may be noisy or of low quality. This can undermine sequence-level knowledge distillation (SKD), as student models may inherit and reinforce errors from inaccurate labels. In this study, the teacher model’s confidence estimation is employed to filter those instances from the distilled training data for which the teacher exhibits low confidence. We tested our methods on a low-resource Urdu-to-English translation task operating within a constrained training budget in an industrial translation setting. Our findings show that confidence estimation-based filtering can significantly reduce the cost and CO2 emissions associated with training a student model without drop in translation quality, making it a practical and environmentally sustainable solution for the TSPs. Full article
(This article belongs to the Special Issue Deep Learning and Its Applications in Natural Language Processing)
Show Figures

Figure 1

Back to TopTop