{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran",
    "Information Technology Research Department, Iranian Research Institute for Information Science and Technology (IranDoc), Tehran, Iran"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Sara Ansar"
    },
    {
      "affs": [
        1
      ],
      "name": "Marzieh Zarinbal"
    },
    {
      "name": "Azadeh Mohebi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8cqg6knynwqrr.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0354459",
  "fulltext_url": null,
  "id": "8cqg6knynwqrr",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0354459",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "3311|Academic integrity and plagiarism"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognition/Memory/Memory recall"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Language/Multilingualism"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Learning and memory/Memory/Memory recall"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Language/Multilingualism"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Support vector machines"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Similarity measures/Cosine similarity"
    ],
    [
      "plos",
      "/Social sciences/Linguistics/Grammar/Syntax"
    ],
    [
      "plos",
      "/Social sciences/Linguistics/Semantics"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Language/Multilingualism"
    ]
  ],
  "openalex": "W7214900063",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0354459&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/8cqg6knynwqrr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:37Z",
      "native_id": "10.1371/journal.pone.0354459",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0354459"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "English-Persian cross-language plagiarism detection: Multilingual deep learning approach",
  "title_text": "English-Persian cross-language plagiarism detection: Multilingual deep learning approach",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:37Z",
  "url": "https://research.draconitic.com/paper/8cqg6knynwqrr",
  "venue": "PLOS One",
  "versions": []
}