Scholarlink

This study addresses sentiment preservation in multilingual text summarization by proposing a reinforcement learning framework with a composite reward function. The approach combines sentiment consistency, content retention, fluency, and diversity metrics, leveraging an adapted mT5 model with language-specific processing. Evaluation across five languages shows 12–15% improvement in sentiment preservation, with particularly strong results (34% reduction in errors) for morphologically complex languages like Finnish. The framework demonstrates practical value in e-commerce and mental health applications, achieving 22 higher customer satisfaction and 18% better emotional tone detection. While effective, computational overhead and challenges with low-resource languages remain for future optimization.

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

Rewarding Sentiment Consistency: Reinforcement Learning for Multilingual Summarization

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mikhail Krasitskii,
  • Olga Kolesnikova,
  • Liliana Chanona Hernandez,
  • Grigori Sidorov,
  • Alexander Gelbukh

摘要

This study addresses sentiment preservation in multilingual text summarization by proposing a reinforcement learning framework with a composite reward function. The approach combines sentiment consistency, content retention, fluency, and diversity metrics, leveraging an adapted mT5 model with language-specific processing. Evaluation across five languages shows 12–15% improvement in sentiment preservation, with particularly strong results (34% reduction in errors) for morphologically complex languages like Finnish. The framework demonstrates practical value in e-commerce and mental health applications, achieving 22 higher customer satisfaction and 18% better emotional tone detection. While effective, computational overhead and challenges with low-resource languages remain for future optimization.