A Hybrid Method for Automatic Text Su mmarization using Fuzzy Inference

سال انتشار: 1393
محل انتشار: همایش ملی مهندسی رایانه و مدیریت فناوری اطلاعات
کد COI اختصاصی: CSITM01_084
زبان مقاله: انگلیسی
تعداد مشاهده: 1192

نویسندگان

Payamnoor University of IRAN

چکیده

Due to the daily growth of information and electronically documents, and converting thesedocuments to the main medium for the transmission of information, large amount of data areproduced every day. Considering the massive amount of data, it is almost impossible for ahuman to study, research and analyze them all. Thus summarizing the main idea and extractingmajor concepts of the main text enables you to read the most important parts of the text morequickly and decide whether or not these are your required issues. Most of the existingsummarization approaches use statistical and probabilistic methods. But these methods are not soaccurate. Obviously, considering the meaning of the text can improve the accuracy ofsummarization. Thus, in this study we have used parameters and methods which consider themeaning of the text and also focus on the statistical methods.On the other hand, because of the uncertainty that exists in the summarization methods, in thisstudy, we tried to simulate human like methods using the fuzzy logic. As it will be discussed inthe results, the findings of this study indicate that the combination of the statistical methods andthe methods that regard to the meaning of the text, (the combination methods), associated withthe use of fuzzy logic to deal with uncertainty is better than previous methods and have betterresults.

کلیدواژه ها

Summarizing the Text, Fuzzy Logic, Semantic Relations, Syntax Relations, Hybrid Method

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.