首页|Researchers Submit Patent Application, "A Text Summarization Performance Evaluat ion Method Sensitive To Text Categorization And A Summarization System Using The Said Method", for Approval (USPTO 20240061874)
Researchers Submit Patent Application, "A Text Summarization Performance Evaluat ion Method Sensitive To Text Categorization And A Summarization System Using The Said Method", for Approval (USPTO 20240061874)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-From Washington, D.C., NewsRx journali sts report that a patent application by the inventors ARSLAN, Mustafa Levent (IS TANBUL, TR); ERDEN, Mustafa (ISTANBUL, TR); GUSER, Abdullah Samil (ISTANBUL, TR) ; SARACLAR, Murat (ISTANBUL, TR), filed on December 2, 2021, was made available online on February 22, 2024. The patent's assignee is Sestek Ses Ve Iletisim Bilgisayar Tek.san.tic.A.S. (Ist anbul, Turkey). News editors obtained the following quote from the background information suppli ed by the inventors: "The process of rewriting a text in a shorter manner withou t losing the main idea is known as text summarization. There are two types of su mmarization methods in the literature. Extractive or selective summarization, wh ich is a summarization approach, creates a summary by selecting important elemen ts in the text and bringing them together without changing them or with minimal changes. In the method of abstractive summarization, which is the other approach, a summary, which preserves the main idea and meaning in the text, is created b y generating new sentences without preserving the text in the document literally . "It is quite important to automatically evaluate the quality of the summaries ex tracted by different methods. Carrying out this evaluation with the human factor causes the evaluation result to be subjective and this method is a very time-co nsuming and expensive evaluation. As an alternative to human evaluation, several automatic evaluation methods have been proposed in the literature. The ROUGE me tric used in the state-of-the-art works by comparing an automatically created su mmary with a reference summary usually created by humans. There are different ty pes of the ROUGE metric, such as the ROUGE-1, ROUGE-2, and ROUGE-L.
CyborgsEmerging TechnologiesMachine LearningSestek Ses Ve Iletisim Bilgisayar Tek.san.tic.A.S
NETL
NSTL
