Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 53 min ago
Peer-reviewedCC BY 4.0PLOS One

English-Persian cross-language plagiarism detection: Multilingual deep learning approach

  • Sara Ansar1
  • Marzieh Zarinbal2
  • Azadeh Mohebi
  1. 1Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
  2. 2Information Technology Research Department, Iranian Research Institute for Information Science and Technology (IranDoc), Tehran, Iran
Open at sourcePDFDOICite

Abstract

Cross-lingual plagiarism detection (CLPD) remains a critical challenge in Natural Language Processing, particularly for low-resource language pairs where translation and paraphrasing obscure source materials. This study introduces a robust framework for Persian-English CLPD by integrating state-of-the-art sentence representations with optimized machine learning classifiers. We utilized the BAAI/bge-m3 model to generate high-dimensional embeddings, employing cosine similarity to measure contrastive linguistic distances. To evaluate classification performance, we compared various architectures, including XGBoost, LSTM, and Logistic Regression (LR), across three categories: Exact, Semi-Exact, and Different. While deep learning and ensemble methods were initially considered, experimental results on an expanded dataset demonstrated that a fine-tuned LR model provided superior stability and generalization. The optimized LR approach significantly increased classification accuracy from 89% to 96% (p < 0.05). These findings suggest that high-quality embeddings can enhance detection performance in low-resource contexts without the computational overhead of complex architectures. To ensure transparency and reproducibility, our dataset and source code are available on GitHub.

Related

  1. Cross-modal alignment with language tokens for unified multilingual image-to-text generation.
    Abubakar Sulaiman Gezawa, Naveed Ur Rehman Junejo, Saud Adam Abdulkadir +2
    Frontiers in computational neurosciencePeer-reviewedCC BYFull textNeuroscienceEurope PMCPMC
  2. Differential language recovery in an English-Polish bilingual individual with severe aphasia: a four-year longitudinal case study.
    Katarzyna E Polanowska, Aleksandra J Zielińska-Michalak
    Postepy psychiatrii neurologiiPeer-reviewedCC BY-NC-NDFull textNeuroscienceEurope PMC
  3. Vernacular english literacy practices among language students using AI: A case study in Saudi Arabia
    Nada Bin Dahmash
    PLOS OnePeer-reviewedCC BY 4.0Full textNeurosciencePLOS
  4. Learner perceptions of AI-mediated affective support in L2 English learning: A cross-sectional survey
    Qiuxi Zhuo
    PLOS OnePeer-reviewedCC BY 4.0Full textNeurosciencePLOSPMC
  5. A Vision-Language Model as a Teacher for Bird Vocalization Detection
    G. Vengrovski, T. J. Gardner
    bioRxivPreprintAll rights reservedFull textZoology & animal behaviourbioRxiv

Cite

BibTeXRIS
BibTeX
@article{ansar2026englishpersian,
  title = {{English-Persian cross-language plagiarism detection: Multilingual deep learning approach}},
  author = {Sara Ansar and Marzieh Zarinbal and Azadeh Mohebi},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0354459},
  url = {https://doi.org/10.1371/journal.pone.0354459},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - English-Persian cross-language plagiarism detection: Multilingual deep learning approach
AU  - Sara Ansar
AU  - Marzieh Zarinbal
AU  - Azadeh Mohebi
PY  - 2026
DA  - 2026/09/30
JO  - PLOS One
DO  - 10.1371/journal.pone.0354459
UR  - https://doi.org/10.1371/journal.pone.0354459
AB  - Cross-lingual plagiarism detection (CLPD) remains a critical challenge in Natural Language Processing, particularly for low-resource language pairs where translation and paraphrasing obscure source materials. This study introduces a robust framework for Persian-English CLPD by integrating state-of-the-art sentence representations with optimized machine learning classifiers. We utilized the BAAI/bge-m3 model to generate high-dimensional embeddings, employing cosine similarity to measure contrastive linguistic distances. To evaluate classification performance, we compared various architectures, including XGBoost, LSTM, and Logistic Regression (LR), across three categories: Exact, Semi-Exact, and Different. While deep learning and ensemble methods were initially considered, experimental results on an expanded dataset demonstrated that a fine-tuned LR model provided superior stability and generalization. The optimized LR approach significantly increased classification accuracy from 89% to 96% (p < 0.05). These findings suggest that high-quality embeddings can enhance detection performance in low-resource contexts without the computational overhead of complex architectures. To ensure transparency and reproducibility, our dataset and source code are available on GitHub.
SN  - 1932-6203
ER  -