Scholarlink

<p>In today’s era of global information exchange, accessing and understanding news across diverse languages remains a challenge. This paper presents a deep learning framework for translating, summarizing, and analyzing multilingual news. The system leverages M2M100 and mBART for seamless neural machine translation and abstractive summarization, while supporting multimodal inputs such as URLs, PDFs, images, and plain text. To enhance accessibility, it includes text-to-speech capabilities, along with a news categorization module and a credibility checker enhanced with NLP-based fake news detection, semantic similarity, and fact-checking services. Together, these components provide an end-to-end solution for cross-language processing, ensuring accurate translation, reliable verification, and accessible news delivery.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Leveraging Transformer Models for Scalable Multilingual News Translation and Summarization

  • 期刊论文

  • 发表日期：

    2026年3月30日

查看全文
  • B. Revathi,
  • M. Subhekshana Thilaga

摘要

In today’s era of global information exchange, accessing and understanding news across diverse languages remains a challenge. This paper presents a deep learning framework for translating, summarizing, and analyzing multilingual news. The system leverages M2M100 and mBART for seamless neural machine translation and abstractive summarization, while supporting multimodal inputs such as URLs, PDFs, images, and plain text. To enhance accessibility, it includes text-to-speech capabilities, along with a news categorization module and a credibility checker enhanced with NLP-based fake news detection, semantic similarity, and fact-checking services. Together, these components provide an end-to-end solution for cross-language processing, ensuring accurate translation, reliable verification, and accessible news delivery.