人人都在用的Grammarly也有语法错误？CEO官方回应 

Grammarly是一款帮助检查语法及拼写错误的工具，在国外一直都非常流行，现在在国内也逐渐普及起来。但是Grammarly真的好用吗？人工智能是否真的能代替人工修正语法？Grammarly的CEO又是怎么评价这款软件的呢？

If you frequently Google language-related questions, whether out of interest or need, you have probably seen an advertisement for Grammarly, an automated grammar-checker. In ubiquitous YouTube spots, Grammarly touts its ability not only to fix mistakes, but to improve style and polish too. Over more than a decade, it has sprawled into many applications: it can check emails, phone messages, or longer texts composed in Microsoft Word and Google Docs, among other formats.

如果你常在谷歌搜索语言类的问题，不论是因为兴趣还是工作学习需要，你可能都已经看到过Grammarly—一款自动语法检查工具的广告。大家都在用的YouTube网站上，Grammarly号称自己不仅能够修正语法错误，还能改善行文风格和语言润色。近十年来，Grammarly已经逐渐“入侵”各大应用程序：它能够检查邮件、短信、Word文档、谷歌文档和其他各种格式文档中存在的错误。

Does it achieve what it purports to? Sometimes. But sometimes Grammarly does not do what it should, and sometimes it even does what it should not. These strengths and failings hint at the essence of language and the peculiarity of human intelligence, as opposed to the artificial sort as it stands today.

它是否将自己说到的功能都实现了呢？有时候好用，但有时候却检查的不准确。不论优点还是缺点，Grammarly只是表明了语言的本质和人类智力的特性，但并不是人们今天所说的人工智能。

Begin with the strengths. In a rough piece of student writing, Johnson counted 14 errors. Grammarly flagged five. For example, it sensibly suggested inserting a hyphen in “post cold war [world]”. It spotted a missing “the” in the phrase “with [the] European economy”. And it noticed an absent “about” in “wondering [about] the state of Europe”. By using Grammarly, the author of this essay could have avoided some red ink.

先说其优点。在一篇学生的初稿中，Johnson(作者)找到了14处错误，而Grammarly只识别出5处。比如，Grammarly合理的建议在冷战后（post cold war）这个词组中加入一个连字符（post–cold war）；在欧洲经济（European economy）前加入一个定冠词（the European economy）；注意到了欧洲状况感到疑惑（wondering the state of Europe）的词组搭配中少介词about（wondering about the state of Europe）。对于上面的情况，Grammarly确实可以帮助作者避免一些错误。

On the other hand, Grammarly has a problem with false positives, calling out mistakes that are not. The other two suggestions are not disastrous, but neither did they relate to “critical errors” as Grammarly maintains. In the assertion that enlargement had “created a fatigue” within the European Union, Grammarly needlessly suggested deleting the “a”.

再谈及缺点，Grammarly会检索到不相关的错误，也就是指出一些并不是问题的问题。Grammarly识别出的5处错误中的另外两条修改建议虽然不会对文章产生严重的影响，但它们也达不到是关键错误的程度。文中提到：不断扩大规模已经对欧盟造成了一种“疲劳感”（created a fatigue）。Grammarly指出需要去掉疲累之前的不定冠词a（created fatigue），其实没有这个必要。

In another error-ridden sentence, it recommended removing a comma, which fixed none of the problems. This false-positive tendency is not a deal-breaker for reasonably skilled writers who just want a second pair of eyes; you can dismiss any suggestion you like. But truly struggling scribblers might not know when Grammarly’s ideas would make their prose worse rather than better.

然而在另一个漏洞百出的句子中，Grammarly只建议删除一个逗号，这样的修改没有解决任何问题。检索不相关错误的问题对于具备写作能力、仅仅需要查错的作者来说其实无伤大雅，他们可以不接受Grammarly的修改意见。但是，对于那些在写作中苦苦挣扎的人们来说，他们可能并不知道Grammarly给出的建议可能会让文章变得更糟。

Then there are the false negatives, or the mistakes Grammarly fails to notice. Depending on the text, Grammarly can seem to miss more errors than it marks. The company’s chief executive, Brad Hoover, describes it as a “coach, not a crutch” — which sets expectations more appropriately than some of the ads do.

此外，Grammarly会检测不到相关的错误，也就是没有注意到错误的存在。基于不同的文本，Grammarly虽然会标记一些错误，但漏掉的错误更多。公司首席执行官Brad Hoover表示，这款软件于用户而言，更像是一位教练，而不是可以依赖的拐杖。这个评价反而比一些广告宣传的用词更加客观。

Artificial-intelligence systems like Grammarly are trained with data; for instance, translation software is fed sentences translated by humans. Grammarly’s training data involve a large number of standard error-free sentences (so it knows what good English should look like) and human-corrected sentences (so the software can find the patterns of fixes that human editors might make).

像Grammarly这样的人工智能系统是通过数据训练的。比如，翻译软件是使用人工翻译的句子训练而成的。Grammarly的训练数据包含了大量标准无错的句子（所以它知道正确的英语应该是什么样子）和人工纠错后的句子（软件可以找到人工编辑的纠错模式）。

Developers also manually add certain rules to the patterns Grammarly has taught itself. The software then looks at a user’s prose: if a string of words seems ungrammatical, it tries to spot how the putative mistake most closely resembles one from its training inputs.

开发者也会手动在Grammarly的训练规律中添加一些规则。软件会浏览用户的文本：如果一个单词串存在语法问题，软件会试图找出系统推断的错误与训练输入最接近的错误。

All this shows how far artificial “intelligence” is from the human kind (which Grammarly wants to correct to “humankind”). Computers outpace humans at problems that can be cracked with pure maths, such as chess. Advances in language technology have been impressive in, for example, speech recognition, which involves another sort of statistical guess — whether or not a stretch of sound matches a certain string of words. One Grammarly feature that works fairly well is sentiment analysis. It can rate the tone of an email before you send it, after being trained on text that has been assessed by humans, for example as “admiring” or “confident”.

从上述内容可以看出，人工智能与人类（human kind）还相距甚远（Grammarly会给出修改建议，将human kind改为humankind）。计算机在纯数学问题上是可以超越人类速度的，比如国际象棋。在语言技术方面的进步也有目共睹，比如语音识别，但也有另一种猜测：一段声音是否能与一串单词相匹配？此外，Grammarly在情感分析方面做得很好。被人为评估过的训练后的文本，例如在“赞美”或“自信”这类被评估过的训练后的文本，Grammarly可以依此在你发送邮件之前对邮件的语调进行评级。

But grammar is the real magic of language, binding words into structures, binding those structures into sentences, and doing so in a way that maps onto meaning. And at this crucial structure-meaning interface, machines are no match for humans. Computers can prase sentences fairly well, labelling things like nouns and verb phrases. But they struggle with sentences that are difficult to analyse, precisely because they are ungrammatical — in other words, written by the kind of person who needs Grammarly.

但语法真的是语言的玄妙之处，能够将单词相互绑定成为一种结构，将结构串联成为句子，再通过句子映射出含义。在这个关键的结构–意义交互中，计算机是无法与人的能力相比的。计算机可以整理句子，以及标注动词名词。但计算机不能处理那些不符合语法、难以分析的句子，而写出这些句子的人，才是真正需要Grammarly的用户。

To correct such prose requires knowing what the writer intended. But computers do not work in meaning or intention; they work in formulae. Humans, by contrast, can usually understand even rather mangled syntax, because of the ability to guess the contents of other minds. Grammar-checking computers illustrate not how bad humans are with language, but just how good.

要修正此类文本，需要明确作者的真正意图。但计算机无法在文本含义和意图上下功夫。计算机的运作是完全基于公式的。相反，人类可以理解混乱的语法，因为我们可以猜测他人的想法。语法检查程序不能说明人类语言水平低，反而证明了人类语言的高明之处。