论文中译英的最佳解决方案？ChatGPT自我反思翻译法了解一下！

我是娜姐 @迪娜学姐 ，一个SCI医学期刊编辑，探索用AI工具提效论文写作和发表。

之前娜姐写过，中译英的论文，一开始在结构上就有很强的中文味。后期如果润色来改善，其实是需要在句子结构上大改动的。

一般来说，会有以下几种中译英论文中独有的中式表达：

① 太长的前置状语。
因为中文习惯经常说“在...的基础上，本文调查了” “为了评估..., 我们进行了”，直译过来，就是“Based on..., we investigated”, "To evaluate the..., we performed..."其实在英文语言中，主谓宾才是句子的核心结构，越早出现越好。但是这种中译英论文会满篇都是状语前置句，读起来很Changlish。

例如：为了评估治疗效果，我们进行了长期的随访研究。
直译式：to evaluate the treatment effectiveness, we carried out a long-term follow-up study.
改进译法：We conducted a long-term follow-up study to evaluate the treatment effectiveness.

② 句子语法错误，是中式结构。

例如：我们使用新方法进行手术。

直译式：We use new method do surgery.
改进译法：We performed surgery using a new method.

③ 语义重复：

例如：我们需要控制并降低病人的血压。

直译式：We need to control and reduce the patient's blood pressure.
改进译法：We need to control the patient's blood pressure.

④ 意思表达不充分

例如：心脏为身体提供血液。

直译式英语：The heart provides blood to the body.
改进译法：The heart serves as a pump, circulating blood throughout the body to deliver oxygen and nutrients to tissues, while also removing waste products.

我们对病人进行了治疗。

直译式英语：We treated the patient.
改进译法：We administered a comprehensive treatment regimen to the patient, including medication, physiotherapy, and lifestyle counseling.

之前娜姐提供的解决方案是先用DeepL来完成中译英，再用ChatGPT润色。但是，对于一些中式的句子结构还是改的不够彻底，总是差了点什么。

最近，娜姐根据吴恩达老师的翻译智能体方案，尝试让ChatGPT自己改进，翻译质量大大提升。我们来看看效果：

以发表在《中华护理杂志》上的一篇论文为例：

协同护理模式在全髋关节置换术后恐动症患者中的应用

摘要：目的 探讨协同护理模式对全髋关节置换术后恐动症患者的影响。方法 选取2019年8月—2020年7月郑州市某三级甲等综合医院收治的92例全髋关节置换术后恐动症患者作为研究对象,其中2020年2月—7月入院的46例作为试验组,实施协同护理模式;2019年8月—2020年1月入院的46例作为对照组,实施常规护理。比较两组干预前后恐动症水平、疼痛程度、髋关节功能及出院准备度的差异。结果 干预后试验组恐动症评估简表评分、疼痛视觉模拟评分表评分、牛津髋关节功能量表评分低于对照组,出院准备度量表评分高于对照组,两组比较,差异均有统计学意义（P<0.05）。结论 协同护理模式可降低全髋关节置换术后患者的恐动症水平,减轻患者疼痛,促进其髋关节功能恢复,提升出院准备度。

DeepL翻译：

Objective: To explore the effect of collaborative care model on agoraphobic patients after total hip arthroplasty.

Methods: Ninety-two patients with agoraphobia after total hip arthroplasty admitted to a tertiary general hospital in Zhengzhou from August 2019 to July 2020 were selected as the study subjects. Forty-six patients admitted in January 2020 were used as the control group, and conventional care was implemented. The differences in agoraphobia level, pain level, hip function and readiness for discharge between the two groups were compared before and after the intervention.

Results: After the intervention, the test group scored lower than the control group on the Short Form of Assessment of Agoraphobia, the Visual Analogue Scale of Pain and the Oxford Hip Function Scale, and higher than the control group on the Readiness for Discharge Scale.

Conclusion: The collaborative care model can reduce the level of agoraphobia in patients after total hip arthroplasty, reduce their pain, promote their hip function recovery, and improve their readiness for discharge.

（点评：Methods第一句”……患者作为研究对象”翻译成了“……were selected as the study subjects”，典型的中式翻译。而且，Results部分“两组比较,差异均有统计学意义(P＜0.05)”这么重要的结果居然漏掉没翻译。效果很一般）

ChatGPT翻译：

Application of Collaborative Care Model in Patients with Kinesiophobia After Total Hip Arthroplasty

Abstract:
Objective: To explore the effect of the collaborative care model on patients with kinesiophobia after total hip arthroplasty.

Methods: A total of 92 patients with kinesiophobia after total hip arthroplasty, admitted to a tertiary general hospital in Zhengzhou from August 2019 to July 2020, were selected as the study subjects. Among them, 46 patients admitted from February to July 2020 were assigned to the experimental group and received the collaborative care model, while 46 patients admitted from August 2019 to January 2020 were assigned to the control group and received routine care. The differences in kinesiophobia levels, pain intensity, hip joint function, and readiness for discharge were compared between the two groups before and after the intervention.

Results: After the intervention, the Tampa Scale for Kinesiophobia scores, Visual Analogue Scale pain scores, and Oxford Hip Score in the experimental group were lower than those in the control group, while the Readiness for Hospital Discharge Scale score was higher in the experimental group. The differences between the two groups were statistically significant (P<0.05).

Conclusion: The collaborative care model can reduce the level of kinesiophobia, alleviate pain, promote hip joint function recovery, and improve discharge readiness in patients after total hip arthroplasty.


ChatGPT自我反思后的改进稿：

点评：

1 整体读一遍，所有的单词和句式改动，都更符合英文学术论文的表达规范了；

2 标题：在“协同护理”前面加了the，全髋关节置换术“后”的恐动症--After Total Hip Arthroplasty改成了Following Total Hip Arthroplasty更贴切；

3 Methods第一句，之前说的“were selected as the study subjects”删除，改成了“The study included 92 patients……”；“比较两组……的差异”原来的翻译“The differences in…… were compared”改后直接删除The differences，”，更符合英文表达；

4 Results部分，中文原文最后一句“两组比较，差异均有统计学意义”，删除了原文翻译，而是在结果的表述中加入significantly lower/higher，保留句尾（P<0.05），更加符合学术论文中对统计学差异的陈述习惯；

5 Conclusion部分，将can reduce改成了effectively reduces（一般现在时，表示一个确定性的共识结果），时态的改动更符合此处的表达。

这只是摘要的示例，全文翻译都可以这样，让AI自己翻译自己反思改进。译文质量大大提升，并且非常符合学术规范。可以说，是目前中译英最好的解决方案。

如果你对于英文论文写作犯怵，也习惯于先写中文初稿，再来全文翻译。那么，娜姐的这个ChatGPT自我反思式中译英+之前研发的ChatGPT通用润色，基本上可以完美解决你的语言障碍问题，将你的论文英文提升到top期刊发表级别。