A Method for Multi-text Summarization Based on Multi-Objective Optimization use Imperialist Competitive Algorithm
سال انتشار: 1401
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 268
فایل این مقاله در 9 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JCR-15-1_002
تاریخ نمایه سازی: 9 مرداد 1401
چکیده مقاله:
In this research, we discuss the methods that have been proposed so far to solve automatic summarization, in which both single-text and multi-text are summarized with emphasis on experimental methods and text extraction techniques. In multi-text summarization, retrieving redundant information that is readable and coherent and contains maximum information from the original text and minimum redundancy has made research in this field very important. An extraction approach based on several methods for identifying sentence similarities and a meta-heuristic optimization algorithm that has been modified and optimized for faster convergence is presented. In this algorithm, changes are made based on density detection through the probability distribution function to avoid being placed in local optimization and try to search more extensively for the response space. The experimental results obtained from the implementation of the algorithm show that the efficiency on criteria such as ROUGE and the accuracy of the proposed method is effectively increased.
کلیدواژه ها:
نویسندگان
Amir Shahab Shahabi
Department of Computer Engineering, Science and Research Branch, Islamic Azad University,Tehran, Iran
Mohammad Reza Kangavari
Department of Computer Engineering, Science and Industry University,Tehran, Iran
Amir Masoud Rahmani
Department of Computer Engineering, Science and Research Branch, Islamic Azad University,Tehran, Iran
مراجع و منابع این مقاله:
لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :