How to Read a Paper-如何高效的阅读论文

How to Read a Paper S. Keshav David R. Cheriton School of Computer Science, University of Waterloo Waterloo, ON, Canada keshav@uwaterloo.ca

ABSTRACT
Researchers spend a great deal of time reading research papers. However, this skill is rarely taught, leading to much wasted effort. This article outlines a practical and efficient threepass method for reading research papers. I also describe how to use this method to do a literature survey. Categories and Subject Descriptors: A.1 [Introductory and Survey]
General Terms: Documentation.
Keywords: Paper, Reading, Hints.

摘要

研究人员花费大量时间阅读研究论文。然而，很少有人教导他们如何阅读论文，导致事倍功半。本文概述了一种实用且有效的“三遍通读论文法“。我还将描述如何使用这种方法进行文献调查。
类别和主题描述： A.1 [简介和调查]
通用条款： 文档。
关键字： 论文，阅读，提示。

1-INTRODUCTION
Researchers must read papers for several reasons: to review them for a conference or a class, to keep current in their field, or for a literature survey of a new field. A typical researcher will likely spend hundreds of hours every year reading papers.

1．简介

因为以下原因，研究人员必须阅读论文：为准备一场会议或一堂课复习论文中的知识点，持续了解其研究领域的最新进展，或对一个全新领域进行文献方面的调查。典型的研究人员每年可能会花费数百小时来阅读论文。

Learning to efficiently read a paper is a critical but rarely taught skill. Beginning graduate students, therefore, must learn on their own using trial and error. Students waste much effort in the process and are frequently driven to frustration.

学习有效地阅读论文是一项至关重要却鲜有人教授的技能。因此，刚毕业的研究生必须自己不断尝试以找到适合的阅读方法。在这一过程中，学生浪费了很多精力，并经常感到挫折。

For many years I have used a simple approach to efficiently read papers. This paper describes the ‘threepass ’approach and its use in doing a literature survey.

多年来，我一直使用一种简单却有效的方法来阅读论文。本文介绍了“读三遍”方法及其在文献调查中的用途。

2-THE THREEPASS APPROACH
The key idea is that you should read the paper in up to three passes, instead of starting at the beginning and plowing your way to the end. Each pass accomplishes specific goals and builds upon the previous pass: The first pass gives you a general idea about the paper. The second pass lets you grasp the paper’s content, but not its details. The third pass helps you understand the paper in depth.

2. 三遍法

要诀是，你应该阅读三遍论文，并不是要求从头一直读到尾，每遍都以上一遍阅读所得为基础，并实现特定的目标：第一遍阅读，你应当了解论文的中心思想。第二遍阅读，你可以了解论文的主要内容，但不要过度专注于细节。而第三遍精读有助于深入了解论文。

2-1 The first pass
The first pass is a quick scan to get a bird’seye view of the paper. You can also decide whether you need to do any more passes. This pass should take about five to ten minutes and consists of the following steps:

2.1第一遍阅读

第一遍阅读需要从“上帝视角”快速了解论文的大致信息。你可以根据这些信息决定是否需要再深入的读几遍。这一过程大约需要五到十分钟，包括以下步骤：

1. Carefully read the title, abstract, and introduction
2. Read the section and subsection headings, but ignore everything else
3. Read the conclusions
4. Glance over the references, mentally ticking off the ones you’ve already read

1.仔细阅读标题，摘要和简介
2.阅读各大节和小节的标题，但忽略其他的所有内容
3.阅读结论
4.浏览参考文献，排除掉已读过的参考文献

At the end of the first pass, you should be able to answer the five Cs :

1. Category : What type of paper is this? A measurement paper? An analysis of an existing system? A description of a research prototype?
2. Context: Which other papers is it related to? Which theoretical bases were used to analyze the problem?
3. Correctness : Do the assumptions appear to be valid?
4. Contributions: What are the paper’s main contributions?
5. Clarity : Is the paper well written?

在第一遍阅读结束时，你应该能够回答以下五个Cs：
1.类别：这是一篇什么类型的论文？测量方法论文？对现有系统的分析？研究原型的描述？
2.引用内容：这篇论文与哪些论文有关？哪些理论被用于分析问题？
3.正确性：这些假设有效吗？
5.贡献：论文的主要贡献是什么？
6.清晰度：论文思路清晰吗？

Using this information, you may choose not to read further. This could be because the paper doesn ’t interest you, or you don’t know enough about the area to understand the paper, or that the authors make invalid assumptions. The first pass is adequate for papers that aren’t in your research area, but may someday prove relevant.

通过这些信息，你可以选择不去深入阅读。这可能是因为你对这篇论文不感兴趣，或者你对该领域的了解不足，无法支撑你理解该论文，或者作者做出了无效的假设。对于不在研究领域中的论文，只读第一遍是足够的，但有一天可能会证明是相关的。

Incidentally, when you write a paper, you can expect most reviewers (and readers) to make only one pass over it. Take care to choose coherent section and subsection titles and to write concise and comprehensive abstracts. If a reviewer cannot understand the gist after one pass, the paper will likely be rejected; if a reader cannot understand the highlights of the paper after five minutes, the paper will likely never be read.

顺便，当您撰写论文时，你得考虑到期望大多数审稿人（和读者）只会读一遍，你需要谨慎选择有联系的小节和小节标题，并编写简洁而全面的摘要。如果读者在通读一遍后仍无法理解要点，则该论文很可能会被拒绝；如果读者在五分钟后仍无法理解论文的重点，那么这篇论文很可能没人愿意去读。

2-2 The second pass
In the second pass, read the paper with greater care, but ignore details such as proofs. It helps to jot down the key points, or to make comments in the margins, as you read.

2.2第二遍阅读

在第二遍阅读中，请仔细阅读论文，但忽略诸如证明之类的细节。在阅读时，记下要点或在空白处进行注释会大有帮助。

1. Look carefully at the figures, diagrams and other illustrations in the paper. Pay special attention to graphs. Are the axes properly labeled? Are results shown with error bars, so that conclusions are statistically significant? Common mistakes like these will separate rushed, shoddy work from the truly excellent.

1.仔细查看论文中的数字，图表和其他插图。特别注意其中的图形。轴是否正确标记？结果中是否包含误差条，从而使结论具有统计意义？诸如此类的常见错误可以区分草草完成的劣质论文和真正优秀的论文。

1. Remember to mark relevant unread references for further reading (this is a good way to learn more about the background of the paper).

2.要记得标记相关的未读参考文献，以供进一步阅读（这是了解论文背景的一种好方法）。

The second pass should take up to an hour. After this pass, you should be able to grasp the content of the paper. You should be able to summarize the main thrust of the paper, with supporting evidence, to someone else. This level of detail is appropriate for a paper in which you are interested, but does not lie in your research speciality.

第二遍阅读最多需要一个小时。在这个过程完成后，你应该能够掌握论文的内容。同时应该能够将论文的主要推论和支撑证据总结给其他人。这种详细程度适用于感兴趣的论文，并不取决于研究方向。

Sometimes you won’t understand a paper even at the end of the second pass. This may be because the subject matter is new to you, with unfamiliar terminology and acronyms. Or the authors may use a proof or experimental technique that you don’t understand, so that the bulk of the paper is incomprehensible. The paper may be poorly written with unsubstantiated assertions and numerous forward references. Or it could just be that it’s late at night and you’re tired. You can now choose to: (a) set the paper aside, hoping you don’t need to understand the material to be successful in your career, (b) return to the paper later, perhaps after reading background material or © persevere and go on to the third pass.

有时，即使在第二遍结束时，也不会理解一篇论文。这可能因为论文的主题是全新的，带有不熟悉的术语和缩写。或者作者可能会使用你不了解的证明方法或实验技术，从而使这篇论文的大部分难以理解。这篇论文可能写得很差，没有充分的依据和大量的前瞻性参考。也可能只是因为你熬得太晚过于疲劳。你可以选择：
（a）搁置论文，祈祷在在取得成功的过程中不需要弄懂这篇论文，
（b）待会再读这篇论文，也许是在阅读了背景材料之后，
（c）坚持不懈，进行第三遍。

2-3 The third pass
To fully understand a paper, particularly if you are reviewer, requires a third pass. The key to the third pass is to attempt to virtually reimplement the paper: that is, making the same assumptions as the authors, recreate the work. By comparing this recreation with the actual paper, you can easily identify not only a paper’s innovations, but also its hidden failings and assumptions.

2.3第三遍阅读

尤其当你是审稿人时，要完全理解一篇论文，需要读第三遍。第三遍的关键是试图模拟重现论文：即，与作者一样做出相同的假设，然后重复作者的工作。将复现结果与实际论文进行比较，您不仅可以轻松确定论文的创新之处和其隐藏的缺陷和假设。

This pass requires great attention to detail. You should identify and challenge every assumption in every statement. Moreover, you should think about how you yourself would present a particular idea. This comparison of the actual with the virtual lends a sharp insight into the proof and presentation techniques in the paper and you can very likely add this to your repertoire of tools. During this pass, you should also jot down ideas for future work.

这个过程需要非常注意细节。你需要鉴别和挑战每一个陈述中的每一个假设。此外，应该考虑自己会如何提出一个特定的想法。通过将实际与假设进行比较，可以更深入地了解论文中的证明和表述技术，并为己所用。在此过程中，您还应该记下对未来工作的想法。

This pass can take about four or five hours for beginners, and about an hour for an experienced reader. At the end of this pass, you should be able to reconstruct the entire structure of the paper from memory, as well as be able to identify its strong and weak points. In particular, you should be able to pinpoint implicit assumptions, missing citations to relevant work, and potential issues with experimental or analytical techniques.

对于初学者来说，这个过程可能需要大约四个小时或五个小时，而对于有经验的读者来说，则可能需要一个小时左右。在此过程的最后，您应该能够在脑海中重建论文的整个结构，并能够确定其优缺点。特别是，您应该能够指出隐含的假设，被遗漏的对相关工作的引用，以及实验或分析技术的潜在问题。

3- DOING A LITERATURE SURVEY
Paper reading skills are put to the test in doing a literature survey. This will require you to read tens of papers, perhaps in an unfamiliar field. What papers should you read? Here is how you can use the threepass approach to help.

3.进行文献调查

进行文献调查时会检验论文阅读技巧。这可能需要阅读可能处于陌生领域的数十篇论文。你应该读什么论文？你可以尝试使用以下三个步骤。

First, use an academic search engine such as Google Scholar or CiteSeer and some wellchosen keywords to find three to five recent papers in the area. Do one pass on each paper to get a sense of the work, then read their related work sections. You will find a thumbnail summary of the recent work, and perhaps, if you are lucky, a pointer to a recent survey paper. If you can find such a survey, you are done. Read the survey, congratulating yourself on your good luck.

首先，使用学术搜索引擎（例如Google Scholar或CiteSeer），通过精选的关键字找出三五个该领域的最新论文。先读一遍每篇论文，以了解大致内容，然后阅读其相关工作部分。您将找到最近工作简略摘要，或者，如果幸运的话，可能会指向关于最新研究的论文。如果可以找到这样的研究，就可以了。阅读最新的研究，庆幸一下自己的好运气。

Otherwise, in the second step, find shared citations and repeated author names in the bibliography. These are the key papers and researchers in that area. Download the key papers and set them aside. Then go to the websites of the key researchers and see where they’ve published recently.That will help you identify the top conferences in that field because the best researchers usually publish in the top conferences.

否则，在第二步中，阅读这些参考论文，找到相同的的引用和重复出现的作者姓名。这些是该领域的关键论文和研究人员。下载关键文件并放在一边。然后访问主要研究人员的网站，查看他们最近发表的论文。这将帮助您确定该领域的顶级会议，因为最好的研究人员通常会在这些顶级会议上发表论文。

The third step is to go to the website for these top conferences and look through their recent proceedings. A quick scan will usually identify recent highquality related work. These papers, along with the ones you set aside earlier, constitute the first version of your survey. Make two passes through these papers. If they all cite a key paper that you did not find earlier, obtain and read it, iterating as necessary.

第三步是访问这些顶级会议的网站，并浏览它们最近的会议记录。快速浏览近期的高质量相关研究。这些论文以及先前查到的论文构成了调查的第一版。通读两遍这些文章。如果他们都引用了之前没有找到的关键论文，获取并阅读这些论文，并在必要时反复阅读。

4-EXPERIENCE
I’ve used this approach for the last 15 years to read conference proceedings, write reviews, do background research, and to quickly review papers before a discussion. This disciplined approach prevents me from drowning in the details before getting a bird’s eyeview. It allows me to estimate the amount of time required to review a set of papers. Moreover, I can adjust the depth of paper evaluation depending on my needs and how much time I have.

4.经验

在过去的15年中，我一直使用这种方法来阅读会议记录，撰写评论，进行背景研究，并在进行讨论之前快速回顾论文。这种严格的方法可以防止我在纵观全文时被各种细节淹没。它使我能够估计出审阅一组论文所需要的时间。此外，我可以根据自己的需求和时间来调整论文评估的深度。

5-RELATED WORK
If you are reading a paper to do a review, you should also read Timothy Roscoe’s paper on “Writing reviews for systems conferences ”[2]. If you’re planning to write a technical paper, you should refer both to Henning Schulzrinne ’s comprehensive web site [3] and George Whitesides’s excellent overview of the process [4]. Finally, Simon Peyton Jones has a website that covers the entire spectrum of research skills [1].

5.相关工作

如果您正在阅读一篇论文进行审阅，则还应该阅读蒂莫西·罗斯科（Timothy Roscoe）的论文“为系统会议撰写审稿” [2]。如果您打算撰写技术论文，则应同时参考Henning Schulzrinne的综合网站[3]和George Whitesides对该过程的优秀概述[4]。最后，西蒙·佩顿·琼斯（Simon Peyton Jones）拥有一个涵盖所有研究技能的网站[1]。

6-A REQUEST
I would like to make this a living document, updating it as I receive comments. Please take a moment to email me any comments or suggestions for improvement. You can also add comments at CCRo, the online edition of CCR [5].

6.一个请求

我想让这个文档“活起来”，并在收到评论时对其进行更新。请花一点时间通过电子邮件将改进的意见或建议发送给我。您还可以在CCRo中添加评论（CCCR [5]的在线版本）。

7-ACKNOWLEDGMENTS
The first version of this document was drafted by my students: Hossein Falaki, Earl Oliver, and Sumair Ur Rahman. My thanks to them. I also bene fited from Christophe Diot’s perceptive comments and Nicole Keshav ’s eagleeyed copyediting.
This work was supported by grants from the National Science and Engineering Council of Canada, the Canada Research Chair Program, Nortel Networks, Microsoft, Intel Corporation, and Sprint Corporation.

7.致谢

本文的第一版是由我的学生们起草的：侯赛因·法拉基（Hossein Falaki），厄尔·奥利弗（Earl Oliver）和苏美尔·厄·拉赫曼（Sumair Ur Rahman）。我感谢他们。我也受益于克里斯托弗·迪奥（Christophe Diot）的建设性意见和妮可·克沙夫（Nicole Keshav）敏锐的文案编辑。
这项工作得到了加拿大国家科学和工程理事会，加拿大工程理事会，北电网络，微软，英特尔公司和Sprint公司的资助。

8-REFERENCES
[1] S. Peyton Jones, “Research Skills,” http://research.microsoft.com/ simonpj/Papers/giving
atalk/givingatalk.htm.
[2] T. Roscoe, “Writing Reviews for Systems Conferences,”
http://people.inf.ethz.ch/troscoe/pubs/review
writing.pdf.
[3] H. Schulzrinne, “Writing Technical Articles,” http://www.cs.columbia.edu/ hgs/etc/writing
style.html.
[4] G.M. Whitesides, “Whitesides’Group: Writing a Paper,”
http://www.che.iitm.ac.in/misc/dd/writepaper.pdf. [5] ACM SIGCOMM Computer Communication Review
Online, http://www.sigcomm.org/ccr/drupal/.

8.参考文献

[1] S. Peyton Jones，“研究技能”
[2] T. Roscoe，“系统会议的书面评论”
[3] H. Schulzrinne，“技术文章写作”
[4] G.M.Whitesides，“ Whitesides’Group：撰写论文”
[5] ACM SIGCOMM计算机通信评论在线

论文精读报告-How to Read a Paper相关推荐

1. 论文无法复现「真公开处刑」，PapersWithCode上线「论文复现报告」

   点击上方"视学算法",选择加"星标"或"置顶" 重磅干货,第一时间送达 来源丨机器之心 编辑丨极市平台 导读 近日,机器学习资源网站 Pap ...

2. 公开处刑：PapersWithCode上线“论文复现报告”，遏制耍流氓行为！

   点击上方"3D视觉工坊",选择"星标" 干货第一时间送达 成功复现一篇论文到底有多难? 大概就像这样吧: 可太TM难了--相信这是大多数机器学习研究者都吐槽过的 ...

3. 【推荐系统论文精读系列】(八)--Deep Crossing：Web-Scale Modeling without Manually Crafted Combinatorial Features

   文章目录 一.摘要 二.介绍 三.相关工作 四.搜索广告 五.特征表示 5.1 独立特征 5.2 组合特征 六.模型架构 6.1 Embedding层 6.2 Stacking层 6.3 Residu ...

4. Text to image论文精读GR-GAN：逐步细化文本到图像生成 GRADUAL REFINEMENT TEXT-TO-IMAGE GENERATION

   目录 一.原文摘要 二.为什么提出GR-GAN 三.GR-GAN 3.1.整体框架 3.2.逐步求精生成器:GRG 3.2.1.图像初始化阶段 3.2.2.句子级细化阶段 3.2.3.单词级细化阶段 ...

5. 【论文精读】 使用空间梯度和噪声分割标签（伪标签）的深度学习配准

   Deep learning based registration using spatial gradients and noisy segmentation labels Théo Estienne ...

6. 每周论文精读05-A2J:AnchortoJointRegressionNetwork for 3D ArticulatedPoseEstimation from a SingleDepthImage

   https://download.csdn.net/download/Jason_____Wang/16502249 论文精读--A2J: Anchor-to-Joint Regression Net ...

7. Zero-Shot相关论文阅读报告

   Zero-Shot相关论文阅读报告 Zero-Shot Learning with Semantic Output Codes 论文:Zero-Shot Learning with Semantic ...

8. CNN基础论文 精读+复现----VGG(一)

   文章目录 前言 第1页 第2-3页 第四页 第五页 前言 原文Github地址:https://github.com/shitbro6/paper/blob/main/VGG.pdf 原文arxiv地 ...

9. 论文精读 ——《BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection》

   文章目录 BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection 论文精读 摘要(Abstract·) 1 ...

最新文章

1. iptables基础篇
2. POJ2262Goldbach's Conjecture 简单的素数判定
3. 域传送漏洞（vulhub）
4. 单文件组件的组件传值_移动端组件化架构（下）
5. Visual Studio启用64位 IIS Express 解决 x64位的dll 而出现 未能加载文件或程序集“xxxxxxxx”或它的某一个依赖项。试图加载格式不正确的程序。...
6. DDD开发框架ABP之导航菜单
7. 软件工程知识点总结(含各类软件工程各类图的画法)
8. 西威变频器avo下载调试资料_全程图解变频器应用与检测技能
9. WinAPI双人贪吃蛇
10. stm32智能避障小车（三）之L298N
11. 在python编译器中调用JAVA程序——JPype使用总结
12. 剑指offer整理（附python代码）——递归
13. 如何判定多边形是顺时针还是逆时针
14. 人艰不拆，一句话毁掉小清新！
15. 计算机配置35%卡住不动了,win7配置更新35%不动怎么回事_win7配置windows update完成35卡住不动了如何解决...
16. win10弹出计算机内存不足,主编解答win10系统提示“计算机内存不足”的解决方案...
17. JavaScript中的静态函数
18. VS2015 更换序列号
19. 博弈论——重复博弈和制度建设
20. 获取元素在屏幕的相对位置

热门文章

1. C语言 before string,c语言中expected expression before是什么意思？
2. Java面试题（自己不会的查大佬的贴，持续记录中）
3. 传说中的“高温补贴”
4. 91 python高级 - 作用域
5. 计算机考证可直接考二级吗
6. java坦克大战课设报告_java课程设计之坦克大战
7. 【Paraview教程】第一章安装与基础介绍
8. 操作系统总结（二）系统调用及系统结构
9. 链游是什么意思 链游和游戏的区别是什么
10. VUE开源项目大全地址