3麻烦帮忙翻译一下吧！！！

来源：百度知道 编辑：UC知道 时间：2024/06/28 01:41:51
This paper describes some exploratory research on automatic methods of obtaining abstracts. The system outlined here begins with the document in machine-read- able form and proceeds by means of a programmed sampling process comparable to the scanning a human reader would do. However, instead of sampling at ran- dom, as a reader normally does when scanning, the new mechanical method selects those among all the sentences of an article that are the most representative of pertinent information. These key sentences are then enumerated to serve as clues for judging the character of the article. Thus, citations of the author’s own statements constitute the “auto-abstract.’’ The programs for creating auto-abstracts must be based on properties of writing ascertained by analysis of specific types of literature. Because the use of abstracts is an established practice in science and technology, it seemed desirable to develop the method first for

本文描述对获得摘要自动方法的一些试探性研究。系统被概述这里从文件开始在机器读了能形式并且收益通过一被编程的抽样的处理可比较与一个人的读者会做的扫描。但是, 而不是抽样在跑了dom, 如同读者通常当扫描, 新机械方法选择那些在是恰当信息多数代表文章的所有句子之中。这些关键句子然后被列举起线索作用对于判断文章的字符。因而, 作者的自己的声明的引证构成"auto-abstract 。" 节目为创造auto-abstracts 必须根据文字物产由对具体类型的分析查明文学。由于对摘要的用途是建立的实践在科学和技术, 它似乎中意首先开发方法为纸和文章在这个区域。de- velopment 的一个主要宗旨将到达在能利用一个现代电子数据处理系统的能力譬如IBM 704 或705, 当同时尽可能简单地保留计划的系统