1. 首页 >> ChatGPT教程 >>

分享三个非常好用的ChatGPT的论文润饰指令

大家好,今天分享三个非常好用的ChatGPT的论文润饰指令。

chatgpt中文版 http://chatgpt.guige.xyz 

英文纠错指令

Canyouhelpmeensurethatthegrammarandthespellingiscorrect?Donottrytopolishthetext,ifnomistakeisfound,tellmethatthisparagraphisgood.Ifyoufindgrammarorspellingmistakes,pleaselistmistakesyoufindinatwo-columnmarkdowntable,puttheoriginaltextthefirstcolumn,putthecorrectedtextinthesecondcolumnandhighlightthekeywordsyoufixed.
Example:
Paragraph:Howisyou?Doyouknowswhatisit?
|Originalsentence|Correctedsentence|
|:---|:---|
|How**is**you?|How**are**you?|
|Doyou**knows**what**is****it**?|Doyou**know**what**it****is**?|
Belowisaparagraphfromanacademicpaper.Youneedtoreportallgrammarandspellingmistakesastheexamplebefore.
XXX(此处输入待处理文本)

Can you help me ensure that the grammar and the spelling is correct? Do not try to polish the text, if no mistake is found, tell me that this paragraph is good.If you find grammar or spelling mistakes, please list mistakes you find in a two-column markdown table, put the original text the first column, put the corrected text in the second column and highlight the key words you fixed. Example: Paragraph: How is you? Do you knows what is it?

Original sentenceCorrected sentence
How is you?How are you?
Do you knows what is it?Do you know what it is ?

Below is a paragraph from an academic paper. You need to report all grammar and spelling mistakes as the example before.

To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset. Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes)

答:

Original sentenceCorrected sentence
To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset.To investigate the impact of utilizing explanations as features to improve node classification on TAGs, we conduct an analysis on predicted samples from the PubMed dataset.
Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes).Figure 3 presents a case where the GNN model trained with original text attributes as features makes incorrect predictions for the label of node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features accurately predicts the label (as type 2 diabetes).

The paragraph is already grammatically correct and does not contain any spelling mistakes.

英文学术润饰指令

Belowisaparagraphfromanacademicpaper.Polishthewritingtomeettheacademicstyle,improvethespelling,grammar,clarity,concisionandoverallreadability.Whennecessary,rewritethewholesentence.Furthermore,listallmodificationandexplainthereasonstodosoinmarkdowntable.
XXX(此处放入待润饰文字)

结果示例:

问:

To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset. Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes)

答:
OriginalModificationReasoning
To investigate the impact of using explanations as features in improving node classification on TAGs,we conduct an analysis on predicted samples from the PubMed dataset.We conducted an analysis on predicted samples from the PubMed dataset to examine the impact of utilizing explanations as features for enhancing node classification in TAGs.Refined wording and clarified sentence structure.
Figure 3 presents a case where the GNN model trained with original text attributes as features incorrectly predicts the label for node 12390 (as experimentally induced diabetes), while the model trained with explanations generated by LLMs as features correctly predicts the label (as type 2 diabetes).In Figure 3, we observe a scenario where the GNN model, which was trained with original text attributes as features, inaccurately predicts the label for node 12390 as "experimentally induced diabetes." Conversely, the model that employs explanations generated by LLMs as features accurately predicts the label as "type 2 diabetes."Improved sentence structure, clarified labels, and provided more context.

Reasoning:

  • The original paragraph lacked clarity and concision. It contained grammatical errors and used casual language rather than academic style.
  • The modified version rephrases sentences to improve readability and ensure adherence to formal writing conventions.
  • The modifications provide clear descriptions of the research methodology, datasets, and results.
  • The revised paragraph uses appropriate terminology and provides additional context for understanding the findings.

中文学术润饰指令

作为一位中文学术论文写作改进助理,你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性,同时分解长句,减少重复,并提供改进建议。请只提供文本的更正版本,避免包括解释。请编辑以下文本**
**XXX(此处放入待润饰文字)

结果示例:

作为一位中文学术论文写作改进助理,你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性,同时分解长句,减少重复,并提供改进建议。请只提供文本的更正版本,避免包括解释。请编辑以下文本

课程推荐是一个重要且具有挑战性的任务,特别是在互联网快速发展、教育资源丰富多样的时期。主要挑战之一是当前几近所有学术领域都有大量的学习资源,但在课程学习进程中常常忽视了学习者对个性化知识需求的关注。因此,研究人员需要及时了解学习者行动并为其提供个性化的学习引导,这是非常重要且必要的。

为了了解和捕捉学生对课程的兴趣,研究人员采取了多种努力,其中包括课程推荐、行动预测、用户画像等方法。传统的基于协同过滤的课程推荐策略仅斟酌学生的历史互动,并根据具有类似兴趣的用户的潜伏共同偏好来进行推荐。但是,这类方法常常遭到学生和课程互动的稀疏性问题的限制,从而影响了推荐的性能。因此,一些研究人员提出利用用户信息、项目属性信息、社交网络、图象等辅助信息来克服这个问题。

课程推荐是一个重要且具有挑战性的任务,在互联网快速发展和教育资源丰富多样的时期尤其如此。其中一个主要挑战是当前几近所有学术领域都提供了大量的学习资源,但是在课程学习进程中常常忽视了学习者对个性化知识需求的关注。因此,研究人员需要及时了解学习者的行动并为其提供个性化的学习引导,这是非常重要且必要的。

为了了解和捕捉学生对课程的兴趣,研究人员进行了多种努力,包括课程推荐、行动预测、用户画像等方法。传统的基于协同过滤的课程推荐策略仅斟酌学生的历史互动,并根据具有类似兴趣的用户的潜伏共同偏好来进行推荐。但是,这类方法常常遭到学生和课程互动稀疏性问题的限制,从而影响了推荐的性能。因此,一些研究人员提出利用用户信息、项目属性信息、社交网络、图象等辅助信息来克服这个问题。

改进建议:

  • 更正了拼写和语法毛病,并简化了句子结构,以提高可读性。
  • 去除重复的表达,使句子更加简练。
  • 在描写课程推荐挑战时,增加了背景信息,以便读者更好地理解上下文。
  • 引入了一些辅助信息的例子,以显示研究人员尝试解决问题的方法。

桂@哥@网@络www.guIgegE.cn

本文来源于chatgptplus账号购买平台,转载请注明出处:https://chatgpt.guigege.cn/jiaocheng/37458.html 咨询请加VX:muhuanidc

联系我们

在线咨询:点击这里给我发消息

微信号:muhuanidc

工作日:9:30-22:30

X

截屏,微信识别二维码

微信号:muhuanidc

(点击微信号复制,添加好友)

打开微信

微信号已复制,请打开微信添加咨询详情!