本文選題：機(jī)器學(xué)習(xí) + 自然語(yǔ)言處理�。� 參考：《計(jì)算機(jī)科學(xué)》2017年S1期

【摘要】：使用基于機(jī)器學(xué)習(xí)的文本分類方法對(duì)《史記》的偽作識(shí)別進(jìn)行了研究。《史記》是我國(guó)第一部紀(jì)傳體通史,其偽作的識(shí)別歷來(lái)是其研究中的重點(diǎn)問(wèn)題。但傳統(tǒng)的研究方法較為主觀,不能定量,且多種結(jié)論互相矛盾。文中提出一種基于文本分類技術(shù)的偽作鑒定方法,對(duì)《史記》的偽作識(shí)別給出定量的研究。該方法具有通用性,可以應(yīng)用于多個(gè)文史問(wèn)題的研究中。
[Abstract]:The text classification method based on machine learning is used to study the identification of false works in Records of History, which is the first general history of chronology in China, and the recognition of false works has always been a key issue in its research. However, the traditional research methods are subjective, can not be quantified, and many conclusions contradict each other. In this paper, a method of pseudo-identification based on text classification technology is proposed, and a quantitative study on pseudo-identification of "Records of the historian" is given. The method is universal and can be applied to the study of multiple literary and historical problems.
【作者單位】： 福建師范大學(xué)福清分校電子與信息工程學(xué)院;大連理工大學(xué);大慶油田熱電廠;
【分類號(hào)】：K204.2;TP181;TP391.1
，

本文編號(hào)：1776549